Best AI papers explained
By Enoch H. Kang
Listen to a podcast, please open Podcast Republic app. Available on Google Play Store and Apple App Store.
Image by Enoch H. Kang
Category: Technology
Open in Apple Podcasts
Open RSS feed
Open Website
Rate for this podcast
Subscribers: 1
Reviews: 0
Episodes: 733
Description
Cut through the noise. We curate and break down the most important AI papers so you don’t have to.
| Episode | Date |
|---|---|
|
Magentic Marketplace: An Open-Source Environment for studying Agentic Markets
|
May 05, 2026 |
|
Hyperloop Transformers
|
May 05, 2026 |
|
Scaling Self-Play with Self-Guidance
|
May 04, 2026 |
|
RL Token: Bootstrapping Online RL with Vision-Language-Action Models
|
May 03, 2026 |
|
Agentic Data Environments
|
May 03, 2026 |
|
AI organizations are more effective but less aligned than individual agents
|
May 01, 2026 |
|
Text-to-Distribution Prediction with Quantile Tokens and Neighbor Context
|
Apr 28, 2026 |
|
Distortion of AI alignment revisited: RLHF is a decent utilitarian aligner
|
Apr 27, 2026 |
|
Llms get lost in multi-turn conversation
|
Apr 25, 2026 |
|
Transformers are inherently succint
|
Apr 23, 2026 |
|
The Coasean Singularity? Demand, Supply, and Market Design with AI Agents
|
Apr 23, 2026 |
|
Demystifying the unreasonable effectiveness of online alignment methods
|
Apr 21, 2026 |
|
Specialization after generalization: towards understanding test-time training in foundation models
|
Apr 21, 2026 |
|
Exploration and Exploitation Errors Are Measurable for Language Model Agents
|
Apr 20, 2026 |
|
A Mechanistic Analysis of Looped Reasoning Language Models
|
Apr 19, 2026 |
|
Sample Complexity of Autoregressive Reasoning: Chain-of-Thought vs. End-to-End
|
Apr 19, 2026 |
|
Why AI systems don’t learn and what to do about it
|
Apr 17, 2026 |
|
The Illusion of Learning from Observational Data: An Empirical Bayes Perspective
|
Apr 17, 2026 |
|
Ads in AI chatbots? An analysis of how large language models navigate conflicts of interest
|
Apr 17, 2026 |
|
Beyond Semantic Manipulation: Token-Space Attacks on Reward Models
|
Apr 13, 2026 |
|
LLM Evaluation as Tensor Completion: Low-Rank Efficiency and Uncertainty Quantification
|
Apr 12, 2026 |
|
Neural Computers
|
Apr 11, 2026 |
|
How AI Aggregation Affects Knowledge
|
Apr 11, 2026 |
|
World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry
|
Apr 10, 2026 |
|
In-Place Test-Time Training
|
Apr 09, 2026 |
|
Test-Time Scaling Makes Overtraining Compute-Optimal
|
Apr 07, 2026 |
|
AI Agent Prevalence and Data Quality Across Multiple Online Sample Providers
|
Apr 07, 2026 |
|
POLCA: Stochastic Generative Optimization with LLM
|
Apr 04, 2026 |
|
Agentic Markets: Equilibrium Effects of Improving Consumer Search
|
Apr 04, 2026 |
|
One Model, Two Markets: Bid-Aware Generative Recommendation
|
Apr 01, 2026 |
|
How Well Do LLMs Predict Human Behavior? A Measure of their Pretrained Knowledge
|
Apr 01, 2026 |
|
Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum
|
Apr 01, 2026 |
|
Agentic AI and the next intelligence explosion
|
Mar 30, 2026 |
|
Understanding Behavior Cloning with Action Quantization
|
Mar 29, 2026 |
|
HyperAgents: : Open-Ended Metacognitive Self-Improvement for Any Computable Task
|
Mar 27, 2026 |
|
Harness design for long-running application development \ Anthropic
|
Mar 26, 2026 |
|
Reasonably reasoning AI agents can avoid game-theoretic failures in zero-shot, provably
|
Mar 24, 2026 |
|
How Log-Barrier Helps Exploration in Policy Optimization
|
Mar 22, 2026 |
|
The Finetuner’s Fallacy: When to Pretrain with Your Finetuning Data
|
Mar 22, 2026 |
|
TURNWISE: The Gap between Single- and Multi-turn Language Model Capabilities
|
Mar 22, 2026 |
|
Temporal Straightening for Latent Planning
|
Mar 20, 2026 |
|
Fine-Tuning Strategies for Preserving In-Context Learning in Linear Attention
|
Mar 19, 2026 |
|
LLMs Can Learn to Reason Via Off-Policy RL
|
Mar 19, 2026 |
|
Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning
|
Mar 17, 2026 |
|
Provable and practical in-context policy optimization for self-improvement
|
Mar 17, 2026 |
|
Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models
|
Mar 16, 2026 |
|
Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights
|
Mar 14, 2026 |
|
AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization
|
Mar 14, 2026 |
|
∇−reasoner: LLM reasoning via test-time gradient descent in latent space
|
Mar 14, 2026 |
|
Inference for Regression with Variables Generated by AI or Machine Learning
|
Mar 12, 2026 |
|
Fast KV Compaction via Attention Matching
|
Mar 12, 2026 |
|
Position: stop anthropomorphizing intermediate tokens as reasoning/thinking traces!
|
Mar 11, 2026 |
|
Code World Models for General Game Playing
|
Mar 08, 2026 |
|
Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought
|
Mar 07, 2026 |
|
Task Descriptors Help Transformers Learn Linear Models In-Context
|
Mar 07, 2026 |
|
Equivalence of Context and Parameter Updates in Modern Transformer Blocks
|
Mar 07, 2026 |
|
Learning without training: The implicit dynamics of in-context learning
|
Mar 07, 2026 |
|
Causal Identification from Counterfactual Data: Completeness and Bounding Results
|
Mar 07, 2026 |
|
Is Cosine-Similarity of Embeddings Really About Similarity?
|
Mar 06, 2026 |
|
Diffusion LLMs are Natural Adversaries for any LLM
|
Mar 05, 2026 |
|
Are you going to finish that? A Practical Study of the Partial Token Problem
|
Mar 04, 2026 |
|
Language Models Struggle to Use Representations Learned In-Context
|
Mar 02, 2026 |
|
LLMs are Bayesian, In Expectation, Not in Realization
|
Mar 01, 2026 |
|
Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs
|
Feb 27, 2026 |
|
LLMs Can Learn to Reason Via Off-Policy RL
|
Feb 27, 2026 |
|
Test-Time Training with KV Binding Is Secretly Linear Attention
|
Feb 27, 2026 |
|
Unified Latents (UL): How to train your latents
|
Feb 26, 2026 |
|
Spectral Bellman Method: Unifying RL Representation and Exploration
|
Feb 25, 2026 |
|
Prescriptive Scaling Reveals the Evolution of Language Model Capabilities
|
Feb 24, 2026 |
|
Experiential Reinforcement Learning
|
Feb 23, 2026 |
|
Learning Personalized Agents from Human Feedback
|
Feb 21, 2026 |
|
Learning to summarize user information for personalized RLHF
|
Feb 20, 2026 |
|
Intrinsic Credit Assignment for Long Horizon Interaction
|
Feb 20, 2026 |
|
Learning to Continually Learn via Meta-learning Agentic Memory Designs
|
Feb 20, 2026 |
|
Why Self-Rewarding Works: Theoretical Guarantees for Iterative Alignment of Language Models
|
Feb 19, 2026 |
|
PAD: Personalized Alignment of LLMs at Decoding-Time
|
Feb 19, 2026 |
|
The Reward Model Selection Crisis in Personalized Alignment
|
Feb 19, 2026 |
|
Causal-JEPA: Learning World Models through Object-Level Latent Interventions
|
Feb 18, 2026 |
|
How Sampling Shapes LLM Alignment: From One-Shot Optima to Iterative Dynamics
|
Feb 17, 2026 |
|
Deriving neural scaling laws from the statistics of natural language
|
Feb 15, 2026 |
|
Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL
|
Feb 15, 2026 |
|
Scaling In-Context Online Learning Capability of LLMs via Cross-Episode Meta-RL
|
Feb 14, 2026 |
|
Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning
|
Feb 12, 2026 |
|
Owning the AI Pareto Frontier — Jeff Dean
|
Feb 12, 2026 |
|
Learning to Reason in 13 Parameters
|
Feb 11, 2026 |
|
Nearly Optimal Active Preference Learning and Its Application to LLM Alignment
|
Feb 08, 2026 |
|
Language Model Circuits Are Sparse in the Neuron Basis
|
Feb 08, 2026 |
|
Rethinking the Trust Region in LLM Reinforcement Learning
|
Feb 08, 2026 |
|
Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward
|
Feb 08, 2026 |
|
Self-distillation enables continual learning
|
Feb 07, 2026 |
|
Maximum Likelihood Reinforcement Learning
|
Feb 06, 2026 |
|
In-Context Algorithm Emulation in Fixed-Weight Transformers
|
Feb 05, 2026 |
|
PPI-SVRG: Unifying Prediction-Powered Inference and Variance Reduction for Semi-Supervised Optimization
|
Feb 05, 2026 |
|
When Models Don’t Collapse: On the Consistency of Iterative MLE
|
Feb 03, 2026 |
|
An orthogonal learner for individualized outcomes In markov decision processes
|
Feb 03, 2026 |
|
Shaping capabilities with token-level data filtering
|
Feb 01, 2026 |
|
Self-Improving Pretraining: using post-trained models to pretrain better models
|
Feb 01, 2026 |
|
Success Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success
|
Jan 31, 2026 |
|
Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning
|
Jan 31, 2026 |
|
GameTalk: Training LLMs for Strategic Multi-Turn Conversation
|
Jan 30, 2026 |
|
Reinforcement Learning via Self-Distillation
|
Jan 30, 2026 |
|
Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning
|
Jan 28, 2026 |
|
On the alignment between supervised and self-supervised contrastive learning
|
Jan 28, 2026 |
|
Rethinking the value of multi-agent work-flow: a strong single agent baseline
|
Jan 24, 2026 |
|
Greedy Sampling Is Provably Efficient for RLHF
|
Jan 24, 2026 |
|
A Generalization Theory for Zero-Shot Prediction
|
Jan 24, 2026 |
|
Learning to Discover at Test Time
|
Jan 23, 2026 |
|
How Does the Pretraining Distribution Shape In-Context Learning? Task Selection, Generalization, and Robustness
|
Jan 23, 2026 |
|
Highlighting What Matters: Promptable Embeddings for Attribute-Focused Retrieval
|
Jan 20, 2026 |
|
Activation Reward Models for Few-Shot Model Alignment
|
Jan 20, 2026 |
|
Reward is enough: LLMs are in-context reinforcement learners
|
Jan 19, 2026 |
|
Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO
|
Jan 19, 2026 |
|
The End of Reward Engineering: How LLMs Are Redefining Multi-Agent Coordination
|
Jan 18, 2026 |
|
PRL: Process Reward Learning Improves LLMs’ Reasoning Ability and Broadens the Reasoning Boundary
|
Jan 18, 2026 |
|
Coverage Improvement and Fast Convergence of On-policy Preference Learning
|
Jan 17, 2026 |
|
Stagewise Reinforcement Learning and the Geometry of the Regret Landscape
|
Jan 16, 2026 |
|
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
|
Jan 16, 2026 |
|
Learning Latent Action World Models In The Wild
|
Jan 16, 2026 |
|
From Unstructured Data to Demand Counterfactuals: Theory and Practice
|
Jan 14, 2026 |
|
In-context reinforcement learning through bayesian fusion of context and value prior
|
Jan 14, 2026 |
|
Digital RedQueen: Adversarial Program Evolution in Core War with LLMs
|
Jan 14, 2026 |
|
Extending the Context of Pretrained LLMs by Dropping Their Positional Embeddings
|
Jan 13, 2026 |
|
Representation-Based Exploration for Language Models: from test-time to post-training
|
Jan 12, 2026 |
|
NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation
|
Jan 10, 2026 |
|
RelayLLM: Efficient Reasoning via Collaborative Decoding
|
Jan 10, 2026 |
|
A Unified Definition of Hallucination, Or: It’s the World Model, Stupid
|
Jan 08, 2026 |
|
Deep sequence models tend to memorize geometrically; it is unclear why.
|
Jan 08, 2026 |
|
From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence
|
Jan 08, 2026 |
|
Diffusion Language Models are Provably Optimal Parallel Samplers
|
Jan 07, 2026 |
|
Universal Reasoning Model
|
Jan 06, 2026 |
|
Recursive language models
|
Jan 06, 2026 |
|
Adapting fast and slow: transportable circuits for few shot learning
|
Jan 04, 2026 |
|
Position: Probabilistic Modelling is Sufficient for Causal Inference
|
Jan 03, 2026 |
|
End-to-End Test-Time Training for Long Context
|
Jan 03, 2026 |
|
Parallel Token Generation for Language Models
|
Jan 02, 2026 |
|
Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning
|
Dec 31, 2025 |
|
Activation oracles: training and evaluating llms as general-purpose activation explainers
|
Dec 30, 2025 |
|
Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning
|
Dec 29, 2025 |
|
Joint-Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction
|
Dec 29, 2025 |
|
Monitoring Monitorability/ OpenAI
|
Dec 28, 2025 |
|
Detailed Balance in Large Language Model-Driven Agents
|
Dec 28, 2025 |
|
Learning to reason in LLMs by expectation maximization
|
Dec 28, 2025 |
|
Exploratory Causal Inference in SAEnce
|
Dec 25, 2025 |
|
Detailed balance in large language model-driven agents
|
Dec 24, 2025 |
|
The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding
|
Dec 24, 2025 |
|
Adaptation of Agentic AI
|
Dec 23, 2025 |
|
Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning
|
Dec 22, 2025 |
|
Let’s (not) just put things in Context: Test-Time Training for Long-Context LLMs
|
Dec 21, 2025 |
|
TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models
|
Dec 20, 2025 |
|
What’s In My Human Feedback? Learning Interpretable Descriptions of Preference Data
|
Dec 19, 2025 |
|
Bolmo: Byteifying the Next Generation of Language Models
|
Dec 19, 2025 |
|
What happened with sparse autoencoders?
|
Dec 17, 2025 |
|
What Matters Right Now in Mechanistic Interpretability
|
Dec 16, 2025 |
|
CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning
|
Dec 16, 2025 |
|
Self-Improving AI and Human Co-Improvement for Safer Co-Superintelligence
|
Dec 16, 2025 |
|
Towards a Science of Scaling Agent Systems / Google Deepmind
|
Dec 15, 2025 |
|
Emergent hierarchical reasoning in LLMs through reinforcement learning
|
Dec 14, 2025 |
|
AI revolution finally comes to Relational foundational models for structured data
|
Dec 13, 2025 |
|
REFRAG: Rethinking RAG based Decoding
|
Dec 13, 2025 |
|
Provable Long-Range Benefits of Next-Token Prediction
|
Dec 12, 2025 |
|
Jeff Dean on TPUs, AI Research, and Funding
|
Dec 12, 2025 |
|
Latent Debate: surrogate framework for Interpreting LLM Thinking
|
Dec 11, 2025 |
|
Distribution-calibrated inference time compute for thinking llm-as-a-judge
|
Dec 11, 2025 |
|
Principled RL for diffusion LLMs emerges from sequence level perspective
|
Dec 11, 2025 |
|
Algorithmic Thinking Theory
|
Dec 10, 2025 |
|
On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models
|
Dec 10, 2025 |
|
Natural language actor-critic: Scalable off-policy learning in language space
|
Dec 09, 2025 |
|
Beyond the Transformer: Titans, MIRAS, and the Future of Infinite Context
|
Dec 07, 2025 |
|
On the Limits of Test-Time Compute: Sequential Reward Filtering for Better Inference
|
Dec 07, 2025 |
|
The Universal Weight Subspace Hypothesis
|
Dec 07, 2025 |
|
Stabilizing Reinforcement Learning with LLMs: Formulation and Practices
|
Dec 07, 2025 |
|
Benchmarking In-context Experiential Learning Through Repeated Product Recommendations
|
Dec 04, 2025 |
|
Training LLMs for Honesty via Confessions
|
Dec 04, 2025 |
|
STOIC REASONER: Dual-Mode Transformers that Compress to Think and Decompress to Speak
|
Dec 04, 2025 |
|
E-GEO: A Testbed for Generative Engine Optimization in E-Commerce
|
Dec 04, 2025 |
|
1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities
|
Dec 04, 2025 |
|
Treatment Effect Estimation for Optimal Decision-Making
|
Dec 04, 2025 |
|
Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems
|
Dec 03, 2025 |
|
Debugging misaligned completions with sparse-autoencoder latent attribution
|
Dec 02, 2025 |
|
Building Effective AI Agents \ Anthropic
|
Dec 02, 2025 |
|
How to Correctly Report LLM-as-a-Judge Evaluations
|
Dec 02, 2025 |
|
In-Context Learning with Hypothesis-Class Guidance
|
Dec 02, 2025 |
|
Selecting Belief-State Approximations in Simulators with Latent States
|
Dec 01, 2025 |
|
Latent Collaboration in Multi-Agent Systems
|
Nov 29, 2025 |
|
CausalPFN: Amortized Causal Effect Estimation via In-Context Learning
|
Nov 28, 2025 |
|
DELTA: How Does RL Unlock and Transfer New Algorithms in LLMs?
|
Nov 28, 2025 |
|
Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing
|
Nov 27, 2025 |
|
Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs
|
Nov 27, 2025 |
|
Ilya Sutskever – We're moving from the age of scaling to the age of research
|
Nov 26, 2025 |
|
Cognitive Foundations for Reasoning and Their Manifestation in LLMs
|
Nov 26, 2025 |
|
Natural emergent misalignment from reward hacking in production RL
|
Nov 25, 2025 |
|
Evolution Strategies at the Hyperscale
|
Nov 25, 2025 |
|
The Path Not Taken: RLVR Provably Learns Off the Principals
|
Nov 23, 2025 |
|
Back to Basics: Let Denoising Generative Models Denoise
|
Nov 23, 2025 |
|
LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization
|
Nov 22, 2025 |
|
Black-Box On-Policy Distillation of Large Language Models
|
Nov 20, 2025 |
|
Solving a million step LLM task with zero errors
|
Nov 20, 2025 |
|
Not All Thoughts Matter: Selective Attention for Efficient Reasoning
|
Nov 19, 2025 |
|
Sample-Efficient Parametric Learning from Natural Language
|
Nov 19, 2025 |
|
Bayesian Optimization in Language space: An Eval-Efficient AI Self-Improvement Framework
|
Nov 18, 2025 |
|
Context Engineering: Sessions, Memory
|
Nov 16, 2025 |
|
The Era of Agentic Organization: Learning to Organize with Language Models
|
Nov 15, 2025 |
|
Understanding neural networks through sparse circuits
|
Nov 14, 2025 |
|
Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning
|
Nov 14, 2025 |
|
Multi-Agent Evolve: LLM Self-Improvement Through Co-Evolution
|
Nov 14, 2025 |
|
LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
|
Nov 14, 2025 |
|
PREFDISCO: Evaluating Proactive Personalization through Interactive Preference Discovery
|
Nov 12, 2025 |
|
Reusing pre-training data at test time is a compute multiplier
|
Nov 10, 2025 |
|
Scaling Agent Learning via Experience Synthesis
|
Nov 09, 2025 |
|
Continuous Autoregressive Language Models
|
Nov 08, 2025 |
|
Toward a Theory of Agents as Tool-Use Decision-Makers
|
Nov 07, 2025 |
|
Nested Learning: The Illusion of Deep Learning Architectures
|
Nov 05, 2025 |
|
GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding
|
Nov 05, 2025 |
|
Beyond a million tokens: benchmarking and enhancing long-term memory in llms
|
Nov 04, 2025 |
|
Agentic Economic Modeling
|
Nov 03, 2025 |
|
Emergent Introspective Awareness in Large Language Models
|
Nov 03, 2025 |
|
Can Large reasoning models self-train?
|
Nov 01, 2025 |
|
ALITA-G: Self-Evolving Generative Agent for Agent Generation
|
Nov 01, 2025 |
|
Self-improving LLM agents at test-time
|
Oct 30, 2025 |
|
Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization
|
Oct 30, 2025 |
|
Language models are injective and hence invertible
|
Oct 30, 2025 |
|
ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
|
Oct 29, 2025 |
|
RLAD: Training LLMs to Discover Abstractions
|
Oct 29, 2025 |
|
How to Train Your Advisor: Steering Black-Box LLMs with ADVISOR MODELS
|
Oct 29, 2025 |
|
Self-improving LLM agents at Test-Time
|
Oct 27, 2025 |
|
KL-Regularized Reinforcement Learning is designed to Mode Collapse
|
Oct 27, 2025 |
|
How do LLMs use their depth?
|
Oct 27, 2025 |
|
Thought Communication in Multiagent Collaboration
|
Oct 27, 2025 |
|
Reasoning with Sampling: Base Models Outperform RL
|
Oct 26, 2025 |
|
Continual Learning via Sparse Memory Finetuning
|
Oct 26, 2025 |
|
Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences
|
Oct 24, 2025 |
|
The Coverage Principle: How Pre-Training Enables Post-Training
|
Oct 24, 2025 |
|
The Era of Real-World Human Interaction: RL from User Conversations
|
Oct 24, 2025 |
|
Agent Learning via Early Experience
|
Oct 24, 2025 |
|
Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL
|
Oct 22, 2025 |
|
Rewriting History: A Recipe for Interventional Analyses to Study Data Effects on Model Behavior
|
Oct 22, 2025 |
|
A Definition of AGI
|
Oct 22, 2025 |
|
Provably Learning from Language Feedback
|
Oct 21, 2025 |
|
In-Context Learning for Pure Exploration
|
Oct 21, 2025 |
|
On the Role of Preference Variance in Preference Optimization
|
Oct 20, 2025 |
|
Training LLM Agents to Empower Humans
|
Oct 20, 2025 |
|
Richard Sutton Declares LLMs a Dead End
|
Oct 20, 2025 |
|
Demystifying Reinforcement Learning in Agentic Reasoning
|
Oct 19, 2025 |
|
Emergent coordination in multi-agent language models
|
Oct 19, 2025 |
|
Learning-to-measure: in-context active feature acquisition
|
Oct 19, 2025 |
|
Andrej Karpathy's insights: AGI, Intelligence, and Evolution
|
Oct 19, 2025 |
|
Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data
|
Oct 18, 2025 |
|
Representation-Based Exploration for Language Models: From Test-Time to Post-Training
|
Oct 18, 2025 |
|
The attacker moves second: stronger adaptive attacks bypass defenses against LLM jail- Breaks and prompt injections
|
Oct 18, 2025 |
|
When can in-context learning generalize out of task distribution?
|
Oct 16, 2025 |
|
The Art of Scaling Reinforcement Learning Compute for LLMs
|
Oct 16, 2025 |
|
A small number of samples can poison LLMs of any size
|
Oct 16, 2025 |
|
Dual Goal Representations
|
Oct 14, 2025 |
|
Welcome to the Era of Experience
|
Oct 14, 2025 |
|
Value Flows: Flow-Based Distributional Reinforcement Learning
|
Oct 14, 2025 |
|
Self-Adapting Language Models
|
Oct 12, 2025 |
|
The Markovian Thinker
|
Oct 12, 2025 |
|
Moloch’s Bargain: emergent misalignment when LLMs compete for audiences
|
Oct 12, 2025 |
|
Transformer Predictor Dynamics and Task Diversity
|
Oct 11, 2025 |
|
Base models know how to reason, thinking models learn when
|
Oct 11, 2025 |
|
Spectrum tuning: Post-training for distributional coverage and in-context steerability
|
Oct 11, 2025 |
|
Understanding Prompt Tuning and In-Context Learning via Meta-Learning
|
Oct 11, 2025 |
|
MLPs Learn In-Context on Regression and Classification tasks
|
Oct 11, 2025 |
|
Is Pre-Training Truly Better than Meta-Learning?
|
Oct 11, 2025 |
|
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
|
Oct 11, 2025 |
|
Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs
|
Oct 09, 2025 |
|
Learning dynamics of LLM finetuning
|
Oct 09, 2025 |
|
Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF
|
Oct 09, 2025 |
|
OpenAI Agent Builder and n8n: Orchestrating Reasoning Versus Automating Process
|
Oct 08, 2025 |
|
Training Agents Inside of Scalable World Models
|
Oct 08, 2025 |
|
Small Language Models are the Future of Agentic AI
|
Oct 07, 2025 |
|
Activation Steering in Generative Settings via Contrastive Causal Mediation Analysis
|
Oct 06, 2025 |
|
Eliciting Secret Knowledge from Language Models
|
Oct 06, 2025 |
|
Temporal difference flow
|
Oct 06, 2025 |
|
Personalized reasoning: just-in-time personalization and why LLMs fail at it
|
Oct 05, 2025 |
|
Prompt Curriculum Learning for Efficient LLM Post-Training
|
Oct 05, 2025 |
|
Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning
|
Oct 04, 2025 |
|
Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward
|
Oct 04, 2025 |
|
Learning to summarize user information for personalized reinforcement learning from human feedback
|
Oct 04, 2025 |
|
Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF
|
Oct 03, 2025 |
|
LIMI: Less is More for Agency
|
Oct 01, 2025 |
|
LoRA Without Regret
|
Oct 01, 2025 |
|
Actor-Critic without Actor: Critic-Guided Denoising for RL
|
Sep 29, 2025 |
|
DELTA-Code: How Does RL Unlock and Transfer New Programming Algorithms in LLMs?
|
Sep 29, 2025 |
|
Linear Transformers Implicitly Discover Unified Numerical Algorithms
|
Sep 29, 2025 |
|
Regularizing Extrapolation in Causal Inference
|
Sep 27, 2025 |
|
DoubleGen - Debiased Generative Modeling of Counterfactuals
|
Sep 27, 2025 |
|
What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT
|
Sep 27, 2025 |
|
Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision
|
Sep 27, 2025 |
|
Learning without training: The implicit dynamics of in-context learning
|
Sep 24, 2025 |
|
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model
|
Sep 24, 2025 |
|
Open Problems in Mechanistic Interpretability
|
Sep 21, 2025 |
|
Maestro: Joint Graph & Config Optimization for Reliable AI Agents
|
Sep 21, 2025 |
|
Thought Anchors: Which LLM Reasoning Steps Matter?
|
Sep 21, 2025 |
|
RL's Razor: Why Online RL Forgets Less
|
Sep 07, 2025 |
|
Why Language Models Hallucinate
|
Sep 06, 2025 |
|
ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning
|
Sep 06, 2025 |
|
Sample Efficient Preference Alignment in LLMs via Active Exploration
|
Sep 06, 2025 |
|
Adventures in Demand Analysis Using AI
|
Sep 04, 2025 |
|
Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
|
Sep 01, 2025 |
|
On the Theoretical Limitations of Embedding-Based Retrieval
|
Aug 31, 2025 |
|
Performance Prediction for Large Systems via Text-to-Text Regression
|
Aug 30, 2025 |
|
Demystifying the Visual Quality Paradox in Multimodal Large Language Models
|
Aug 30, 2025 |
|
Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL
|
Aug 30, 2025 |
|
Compute-Optimal Scaling for Value-Based Deep RL
|
Aug 25, 2025 |
|
LLM-based Conversational Recommendation Agents with Collaborative Verbalized Experience
|
Aug 23, 2025 |
|
Signal and Noise: Evaluating Language Model Benchmarks
|
Aug 23, 2025 |
|
Breaking Feedback Loops in Recommender Systems with Causal Inference
|
Aug 21, 2025 |
|
RAG is Dead, Context Engineering is King: Building Reliable AI Systems
|
Aug 20, 2025 |
|
A Survey of Personalization: From RAG to Agent
|
Aug 20, 2025 |
|
Facilitating the Adoption of Causal Infer-ence Methods Through LLM-Empowered Co-Pilot
|
Aug 19, 2025 |
|
Performance Prediction for Large Systems via Text-to-Text Regression
|
Aug 16, 2025 |
|
Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning
|
Aug 15, 2025 |
|
DINOv3: Vision Models for Self-Supervised Learning
|
Aug 15, 2025 |
|
Agent Lightning: Training Any AI Agents with Reinforcement Learning
|
Aug 14, 2025 |
|
Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier
|
Aug 14, 2025 |
|
From Model Weights to Agent Workflows: Charting the New Frontier of Optimization in Large Language Models
|
Aug 12, 2025 |
|
Is Chain-of-Thought Reasoning a Mirage?
|
Aug 12, 2025 |
|
Agentic Web: Weaving the Next Web with AI Agents
|
Aug 11, 2025 |
|
The Assimilation-Accommodation Gap in LLM Intelligence
|
Aug 10, 2025 |
|
The Minimalist AI Kernel: A New Frontier in Reasoning
|
Aug 06, 2025 |
|
Statistical Rigor for Interpretable AI
|
Aug 06, 2025 |
|
Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value
|
Aug 04, 2025 |
|
A foundation model to predict and capture human cognition
|
Aug 04, 2025 |
|
Generative Recommendation with Semantic IDs: A Practitioner’s Handbook
|
Aug 04, 2025 |
|
Hierarchical Reasoning Model
|
Aug 04, 2025 |
|
Test-time Offline Reinforcement Learning on Goal-related Experience
|
Aug 04, 2025 |
|
Interpreting Chain of Thought: A Walkthrough and Discussion
|
Aug 04, 2025 |
|
The wall confronting large language models
|
Aug 04, 2025 |
|
COLLABLLM: LLMs From Passive to Collaborative
|
Jul 31, 2025 |
|
A decade's battle on dataset bias: are we there yet?
|
Jul 29, 2025 |
|
GEPA: Generative Feedback for AI System Optimization
|
Jul 29, 2025 |
|
From AI-Curious to AI-First: Engineering Production AI Systems
|
Jul 28, 2025 |
|
Context Engineering: Beyond Simple Prompting to LLM Architecture
|
Jul 28, 2025 |
|
Agentic Misalignment: LLMs as Insider Threats
|
Jul 28, 2025 |
|
Small Language Models: Future of Agentic AI
|
Jul 28, 2025 |
|
Learning without training: The implicit dynamics of in-context learning
|
Jul 28, 2025 |
|
Inverse Scaling in Test-Time Compute
|
Jul 28, 2025 |
|
LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra
|
Jul 28, 2025 |
|
Microsoft's Blueprint: AI, Quantum, and the Agentic Future
|
Jul 26, 2025 |
|
Zuckerberg's AI Vision Analyzed
|
Jul 26, 2025 |
|
Inside Claude: Scaling, Agency, and Interpretability
|
Jul 26, 2025 |
|
Personalized language modeling from personalized human feedback
|
Jul 26, 2025 |
|
Position: Empowering Time Series Reasoning with Multimodal LLMs
|
Jul 25, 2025 |
|
An empirical risk minimization approach for offline inverse RL and Dynamic Discrete Choice models
|
Jul 22, 2025 |
|
Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities
|
Jul 22, 2025 |
|
The Invisible Leash: Why RLVR May Not Escape Its Origin
|
Jul 20, 2025 |
|
Language Model Personalization via Reward Factorization
|
Jul 20, 2025 |
|
Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
|
Jul 18, 2025 |
|
Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective
|
Jul 17, 2025 |
|
Soft Best-of-n Sampling for Model Alignment
|
Jul 16, 2025 |
|
On Temporal Credit Assignment and Data-Efficient Reinforcement Learning
|
Jul 15, 2025 |
|
Bradley–Terry and Multi-Objective Reward Modeling Are Complementary
|
Jul 15, 2025 |
|
Probing Foundation Models for World Models
|
Jul 15, 2025 |
|
GenAI-Powered Statistical Inference (with Unstructured Data)
|
Jul 14, 2025 |
|
Interpretable Reward Modeling with Active Concept Bottlenecks
|
Jul 14, 2025 |
|
PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications
|
Jul 14, 2025 |
|
A Collectivist, Economic Perspective on AI
|
Jul 14, 2025 |
|
Textual Bayes: Quantifying Uncertainty in LLM-Based Systems
|
Jul 12, 2025 |
|
The Winner's Curse in Data-Driven Decisions
|
Jul 11, 2025 |
|
SPIRAL: Self-Play for Reasoning Through Zero-Sum Games
|
Jul 11, 2025 |
|
Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence
|
Jul 11, 2025 |
|
Aligning Learning and Endogenous Decision-Making
|
Jul 11, 2025 |
|
Reliable Statistical Inference with Synthetic Data from Large Language Models
|
Jul 11, 2025 |
|
Multi-Turn Reinforcement Learning from Human Preference Feedback
|
Jul 10, 2025 |
|
Provably Learning from Language Feedback
|
Jul 09, 2025 |
|
Markets with Heterogeneous Agents: Dynamics and Survival of Bayesian vs. No-Regret Learners
|
Jul 05, 2025 |
|
Why Neural Network Can Discover Symbolic Structures with Gradient-based Training: An Algebraic and Geometric Foundation
|
Jul 05, 2025 |
|
Causal Abstraction with Lossy Representations
|
Jul 04, 2025 |
|
The Winner's Curse in Data-Driven Decisions
|
Jul 04, 2025 |
|
Embodied AI Agents: Modeling the World
|
Jul 04, 2025 |
|
Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence
|
Jul 04, 2025 |
|
What Has a Foundation Model Found? Inductive Bias Reveals World Models
|
Jul 04, 2025 |
|
Language Bottleneck Models: A Framework for Interpretable Knowledge Tracing and Beyond
|
Jul 03, 2025 |
|
Learning to Explore: An In-Context Learning Approach for Pure Exploration
|
Jul 03, 2025 |
|
Human-AI Matching: The Limits of Algorithmic Search
|
Jun 25, 2025 |
|
Uncertainty Quantification Needs Reassessment for Large-language Model Agents
|
Jun 25, 2025 |
|
Bayesian Meta-Reasoning for Robust LLM Generalization
|
Jun 25, 2025 |
|
General Intelligence Requires Reward-based Pretraining
|
Jun 25, 2025 |
|
Deep Learning is Not So Mysterious or Different
|
Jun 25, 2025 |
|
AI Agents Need Authenticated Delegation
|
Jun 25, 2025 |
|
Probabilistic Modelling is Sufficient for Causal Inference
|
Jun 25, 2025 |
|
Not All Explanations for Deep Learning Phenomena Are Equally Valuable
|
Jun 25, 2025 |
|
e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs
|
Jun 17, 2025 |
|
Extrapolation by Association: Length Generalization Transfer in Transformers
|
Jun 17, 2025 |
|
Uncovering Causal Hierarchies in Language Model Capabilities
|
Jun 17, 2025 |
|
Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers
|
Jun 17, 2025 |
|
Improving Treatment Effect Estimation with LLM-Based Data Augmentation
|
Jun 17, 2025 |
|
LLM Numerical Prediction Without Auto-Regression
|
Jun 17, 2025 |
|
Why in-context learning models are good few-shot learners?
|
Jun 17, 2025 |
|
Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina∗
|
Jun 14, 2025 |
|
The Logic of Machines: The AI Reasoning Debate
|
Jun 12, 2025 |
|
Layer by Layer: Uncovering Hidden Representations in Language Models
|
Jun 12, 2025 |
|
Causal Attribution Analysis for Continuous Outcomes
|
Jun 12, 2025 |
|
Training a Generally Curious Agent
|
Jun 12, 2025 |
|
Estimation of Treatment Effects Under Nonstationarity via Truncated Difference-in-Q’s
|
Jun 12, 2025 |
|
Strategy Coopetition Explains the Emergence and Transience of In-Context Learning
|
Jun 12, 2025 |
|
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
|
Jun 11, 2025 |
|
Agentic Supernet for Multi-agent Architecture Search
|
Jun 11, 2025 |
|
Sample Complexity and Representation Ability of Test-time Scaling Paradigms
|
Jun 11, 2025 |
|
Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators
|
Jun 10, 2025 |
|
LLMs Get Lost In Multi-Turn Conversation
|
Jun 09, 2025 |
|
PromptPex: Automatic Test Generation for Prompts
|
Jun 08, 2025 |
|
General Agents Need World Models
|
Jun 08, 2025 |
|
The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models
|
Jun 07, 2025 |
|
Decisions With Algorithms
|
Jun 07, 2025 |
|
Adapting, fast and slow: Causal Approach to Few-Shot Sequence Learning
|
Jun 06, 2025 |
|
Conformal Arbitrage for LLM Objective Balancing
|
Jun 06, 2025 |
|
Simulation-Based Inference for Adaptive Experiments
|
Jun 06, 2025 |
|
Agents as Tool-Use Decision-Makers
|
Jun 06, 2025 |
|
Quantitative Judges for Large Language Models
|
Jun 06, 2025 |
|
Self-Challenging Language Model Agents
|
Jun 06, 2025 |
|
Learning to Explore: An In-Context Learning Approach for Pure Exploration
|
Jun 06, 2025 |
|
How Bidirectionality Helps Language Models Learn Better via Dynamic Bottleneck Estimation
|
Jun 06, 2025 |
|
A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models
|
Jun 05, 2025 |
|
Simplifying Bayesian Optimization Via In-Context Direct Optimum Sampling
|
Jun 05, 2025 |
|
Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models
|
Jun 05, 2025 |
|
IPO: Interpretable Prompt Optimization for Vision-Language Models
|
Jun 05, 2025 |
|
Evolutionary Prompt Optimization discovers emergent multimodal reasoning strategies
|
Jun 05, 2025 |
|
Evaluating the Unseen Capabilities: How Many Theorems Do LLMs Know?
|
Jun 04, 2025 |
|
Diffusion Guidance Is a Controllable Policy Improvement Operator
|
Jun 02, 2025 |
|
Alita: Generalist Agent With Self-Evolution
|
Jun 02, 2025 |
|
A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning
|
Jun 02, 2025 |
|
Learning Compositional Functions with Transformers from Easy-to-Hard Data
|
Jun 02, 2025 |
|
Preference Learning with Response Time
|
Jun 02, 2025 |
|
Accelerating RL for LLM Reasoning with Optimal Advantage Regression
|
May 31, 2025 |
|
Algorithms for reliable decision-making need causal reasoning
|
May 31, 2025 |
|
Belief Attribution as Mental Explanation: The Role of Accuracy, Informativity, and Causality
|
May 31, 2025 |
|
Distances for Markov chains from sample streams
|
May 31, 2025 |
|
When and Why LLMs Fail to Reason Globally
|
May 31, 2025 |
|
IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis
|
May 31, 2025 |
|
No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference
|
May 31, 2025 |
|
Accelerating RL for LLM Reasoning with Optimal Advantage Regression
|
May 31, 2025 |
|
Statistical Inference for Online Algorithms
|
May 31, 2025 |
|
Prismatic Synthesis for Diverse LLM Reasoning Data
|
May 31, 2025 |
|
Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents
|
May 31, 2025 |
|
The Agentic Economy
|
May 30, 2025 |
|
Statistics for Large Language Models
|
May 29, 2025 |
|
Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search
|
May 29, 2025 |
|
Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning
|
May 29, 2025 |
|
Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL
|
May 29, 2025 |
|
Value-Guided Search for Efficient Chain-of-Thought Reasoning
|
May 29, 2025 |
|
Shallow Preference Signals: Large Language model aligns even better without truncated data?
|
May 29, 2025 |
|
Gaming Tool Preferences in Agentic LLMs
|
May 29, 2025 |
|
Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)
|
May 29, 2025 |
|
LLM Populations Form Social Conventions and Collective Bias
|
May 29, 2025 |
|
LLM Generated Persona is a Promise with a Catch
|
May 29, 2025 |
|
Large Language Models for Digital Twin Simulation
|
May 29, 2025 |
|
From RL Distillation to Autonomous LLM Agents
|
May 29, 2025 |
|
Prompting, Auto-Prompting, and Human-AI Communication
|
May 29, 2025 |
|
Textual Gradients for LLM Optimization
|
May 29, 2025 |
|
Large Language Models as Markov Chains
|
May 28, 2025 |
|
Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
|
May 28, 2025 |
|
Selective induction heads: how transformers select causal structures in context
|
May 28, 2025 |
|
The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains
|
May 28, 2025 |
|
How Transformers Learn Causal Structure with Gradient Descent
|
May 28, 2025 |
|
Planning anything with rigor: general-purpose zero-shot planning with llm-based formalized programming
|
May 28, 2025 |
|
Automated Design of Agentic Systems
|
May 28, 2025 |
|
What’s the Magic Word? A Control Theory of LLM Prompting
|
May 28, 2025 |
|
BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling
|
May 27, 2025 |
|
RL with KL penalties is better viewed as Bayesian inference
|
May 27, 2025 |
|
Asymptotics of Language Model Alignment
|
May 27, 2025 |
|
Qwen 2.5, RL, and Random Rewards
|
May 27, 2025 |
|
Theoretical guarantees on the best-of-n alignment policy
|
May 27, 2025 |
|
Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models
|
May 27, 2025 |
|
Improved Techniques for Training Score-Based Generative Models
|
May 27, 2025 |
|
Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator
|
May 27, 2025 |
|
AlphaEvolve: A coding agent for scientific and algorithmic discovery
|
May 27, 2025 |
|
Harnessing the Universal Geometry of Embeddings
|
May 27, 2025 |
|
Goal Inference using Reward-Producing Programs in a Novel Physics Environment
|
May 27, 2025 |
|
Trial-Error-Explain In-Context Learning for Personalized Text Generation
|
May 27, 2025 |
|
Reinforcement Learning for Reasoning in Large Language Models with One Training Example
|
May 27, 2025 |
|
Test-Time Reinforcement Learning (TTRL)
|
May 27, 2025 |
|
Interpreting Emergent Planning in Model-Free Reinforcement Learning
|
May 26, 2025 |
|
Agentic Reward Modeling_Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
|
May 26, 2025 |
|
Beyond Reward Hacking: Causal Rewards for Large LanguageModel Alignment
|
May 26, 2025 |
|
Learning How Hard to Think: Input-Adaptive Allocation of LM Computation
|
May 26, 2025 |
|
Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval
|
May 26, 2025 |
|
UFT: Unifying Supervised and Reinforcement Fine-Tuning
|
May 26, 2025 |
|
Understanding High-Dimensional Bayesian Optimization
|
May 26, 2025 |
|
Inference time alignment in continuous space
|
May 25, 2025 |
|
Efficient Test-Time Scaling via Self-Calibration
|
May 25, 2025 |
|
Conformal Prediction via Bayesian Quadrature
|
May 25, 2025 |
|
Predicting from Strings: Language Model Embeddings for Bayesian Optimization
|
May 25, 2025 |
|
Self-Evolving Curriculum for LLM Reasoning
|
May 25, 2025 |
|
Online Decision-Focused Learning in Dynamic Environments
|
May 25, 2025 |
|
FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain
|
May 25, 2025 |
|
Reward Shaping from Confounded Offline Data
|
May 25, 2025 |
|
Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning
|
May 25, 2025 |
|
Understanding Best-of-N Language Model Alignment
|
May 25, 2025 |
|
Maximizing Acquisition Functions for Bayesian Optimization - and its relation to Gradient Descent
|
May 24, 2025 |
|
Bayesian Prompt Ensembles: Model Uncertainty Estimation for Black-Box Large Language Models
|
May 24, 2025 |
|
Prompting Strategies for Enabling Large Language Models to Infer Causation from Correlation
|
May 24, 2025 |
|
The Parallel Knowledge Gradient Method for Batch Bayesian Optimization
|
May 24, 2025 |
|
FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch
|
May 24, 2025 |
|
Automated Social Science: A Structural Causal Model-Based Approach
|
May 24, 2025 |
|
Causal Interpretation of Transformer Self-Attention
|
May 24, 2025 |
|
A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment
|
May 24, 2025 |
|
Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs
|
May 24, 2025 |
|
Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation
|
May 24, 2025 |
|
Prompts from Reinforcement Learning (PRL)
|
May 24, 2025 |
|
Logits are All We Need to Adapt Closed Models
|
May 24, 2025 |
|
Large Language Models Are (Bayesian) Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning
|
May 23, 2025 |
|
Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
|
May 23, 2025 |
|
From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models
|
May 23, 2025 |
|
LLM In-Context Learning as Kernel Regression
|
May 23, 2025 |
|
Personalizing LLMs via Decode-Time Human Preference Optimization
|
May 23, 2025 |
|
Almost Surely Safe LLM Inference-Time Alignment
|
May 23, 2025 |
|
Survey of In-Context Learning Interpretation and Analysis
|
May 23, 2025 |
|
From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models
|
May 23, 2025 |
|
LLM In-Context Learning as Kernel Regression
|
May 23, 2025 |
|
Where does In-context Learning Happen in Large Language Models?
|
May 23, 2025 |
|
Auto-Differentiating Any LLM Workflow: A Farewell to Manual Prompting
|
May 22, 2025 |
|
metaTextGrad: Learning to learn with language models as optimizers
|
May 22, 2025 |
|
Semantic Operators: A Declarative Model for Rich, AI-based Data Processing
|
May 22, 2025 |
|
Isolated Causal Effects of Language
|
May 22, 2025 |
|
Sleep-time Compute: Beyond Inference Scaling at Test-time
|
May 22, 2025 |
|
J1: Incentivizing Thinking in LLM-as-a-Judge
|
May 22, 2025 |
|
ShiQ: Bringing back Bellman to LLMs
|
May 22, 2025 |
|
Policy Learning with a Natural Language Action Space: A Causal Approach
|
May 22, 2025 |
|
Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models
|
May 22, 2025 |
|
End-to-End Learning for Stochastic Optimization: A Bayesian Perspective
|
May 21, 2025 |
|
TEXTGRAD: Automatic Differentiation via Text
|
May 21, 2025 |
|
Steering off Course: Reliability Challenges in Steering Language Models
|
May 20, 2025 |
|
Past-Token Prediction for Long-Context Robot Policies
|
May 20, 2025 |
|
Recovering Coherent Event Probabilities from LLM Embeddings
|
May 20, 2025 |
|
Systematic Meta-Abilities Alignment in Large Reasoning Models
|
May 20, 2025 |
|
Predictability Shapes Adaptation: An Evolutionary Perspective on Modes of Learning in Transformers
|
May 20, 2025 |
|
Efficient Exploration for LLMs
|
May 19, 2025 |
|
Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation
|
May 18, 2025 |
|
Bayesian Concept Bottlenecks with LLM Priors
|
May 17, 2025 |
|
Transformers for In-Context Reinforcement Learning
|
May 17, 2025 |
|
Evaluating Large Language Models Across the Lifecycle
|
May 17, 2025 |
|
Active Ranking from Human Feedback with DopeWolfe
|
May 16, 2025 |
|
Optimal Designs for Preference Elicitation
|
May 16, 2025 |
|
Dual Active Learning for Reinforcement Learning from Human Feedback
|
May 16, 2025 |
|
Active Learning for Direct Preference Optimization
|
May 16, 2025 |
|
Active Preference Optimization for RLHF
|
May 16, 2025 |
|
Test-Time Alignment of Diffusion Models without reward over-optimization
|
May 16, 2025 |
|
Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback
|
May 16, 2025 |
|
GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment
|
May 16, 2025 |
|
Advantage-Weighted Regression: Simple and Scalable Off-Policy RL
|
May 16, 2025 |
|
Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective
|
May 16, 2025 |
|
Transformers can be used for in-context linear regression in the presence of endogeneity
|
May 15, 2025 |
|
Bayesian Concept Bottlenecks with LLM Priors
|
May 15, 2025 |
|
In-Context Parametric Inference: Point or Distribution Estimators?
|
May 15, 2025 |
|
Enough Coin Flips Can Make LLMs Act Bayesian
|
May 15, 2025 |
|
Bayesian Scaling Laws for In-Context Learning
|
May 15, 2025 |
|
Posterior Mean Matching Generative Modeling
|
May 15, 2025 |
|
Can Generative AI Solve Your In-Context Learning Problem? A Martingale Perspective
|
May 15, 2025 |
|
Dynamic Search for Inference-Time Alignment in Diffusion Models
|
May 15, 2025 |
|
Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective
|
May 12, 2025 |
|
Leaked Claude Sonnet 3.7 System Instruction tuning
|
May 12, 2025 |
|
Converging Predictions with Shared Information
|
May 11, 2025 |
|
Test-Time Alignment Via Hypothesis Reweighting
|
May 11, 2025 |
|
Rethinking Diverse Human Preference Learning through Principal Component Analysis
|
May 11, 2025 |
|
Active Statistical Inference
|
May 10, 2025 |
|
Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework
|
May 10, 2025 |
|
AI-Powered Bayesian Inference
|
May 10, 2025 |
|
Can Unconfident LLM Annotations Be Used for Confident Conclusions?
|
May 09, 2025 |
|
Predictions as Surrogates: Revisiting Surrogate Outcomes in the Age of AI
|
May 09, 2025 |
|
Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control
|
May 09, 2025 |
|
How to Evaluate Reward Models for RLHF
|
May 09, 2025 |
|
LLMs as Judges: Survey of Evaluation Methods
|
May 09, 2025 |
|
The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs
|
May 09, 2025 |
|
Limits to scalable evaluation at the frontier: LLM as Judge won’t beat twice the data
|
May 09, 2025 |
|
Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation
|
May 09, 2025 |
|
Accelerating Unbiased LLM Evaluation via Synthetic Feedback
|
May 09, 2025 |
|
Prediction-Powered Statistical Inference Framework
|
May 09, 2025 |
|
Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL
|
May 09, 2025 |
|
RM-R1: Reward Modeling as Reasoning
|
May 09, 2025 |
|
Reexamining the Aleatoric and Epistemic Uncertainty Dichotomy
|
May 08, 2025 |
|
Decoding Claude Code: Terminal Agent for Developers
|
May 07, 2025 |
|
Emergent Strategic AI Equilibrium from Pre-trained Reasoning
|
May 07, 2025 |
|
Benefiting from Proprietary Data with Siloed Training
|
May 06, 2025 |
|
Advantage Alignment Algorithms
|
May 06, 2025 |
|
Asymptotic Safety Guarantees Based On Scalable Oversight
|
May 06, 2025 |
|
What Makes a Reward Model a Good Teacher? An Optimization Perspective
|
May 06, 2025 |
|
Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems
|
May 06, 2025 |
|
Identifiable Steering via Sparse Autoencoding of Multi-Concept Shifts
|
May 06, 2025 |
|
You Are What You Eat - AI Alignment Requires Understanding How Data Shapes Structure and Generalisation
|
May 06, 2025 |
|
Interplay of LLMs in Information Retrieval Evaluation
|
May 03, 2025 |
|
Trade-Offs Between Tasks Induced by Capacity Constraints Bound the Scope of Intelligence
|
May 03, 2025 |
|
Toward Efficient Exploration by Large Language Model Agents
|
May 03, 2025 |
|
Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT
|
May 02, 2025 |
|
Self-Consuming Generative Models with Curated Data
|
May 02, 2025 |
|
Bootstrapping Language Models with DPO Implicit Rewards
|
May 02, 2025 |
|
DeepSeek-Prover-V2: Advancing Formal Reasoning
|
May 01, 2025 |
|
THINKPRM: Data-Efficient Process Reward Models
|
May 01, 2025 |
|
Societal Frameworks and LLM Alignment
|
Apr 29, 2025 |
|
Risks from Multi-Agent Advanced AI
|
Apr 29, 2025 |
|
Causality-Aware Alignment for Large Language Model Debiasing
|
Apr 29, 2025 |
|
Reward Models Evaluate Consistency, Not Causality
|
Apr 28, 2025 |
|
Causal Rewards for Large Language Model Alignment
|
Apr 28, 2025 |
|
Sycophancy to subterfuge: Investigating reward-tampering in large language models
|
Apr 28, 2025 |
|
Bidirectional AI Alignment
|
Apr 28, 2025 |
|
Why Do Multi-Agent LLM Systems Fail?
|
Apr 27, 2025 |
|
LLMs as Greedy Agents: RL Fine-tuning for Decision-Making
|
Apr 27, 2025 |
|
LLM Feedback Loops and the Lock-in Hypothesis
|
Apr 27, 2025 |
|
Representational Alignment Drives Effective Teaching and Learning
|
Apr 27, 2025 |
|
Adaptive Parallel Reasoning with Language Models
|
Apr 27, 2025 |
|
AI: Rewiring the Flow of Ideas and Human Knowledge
|
Apr 27, 2025 |
|
Learning and Equilibrium with Ranking Feedback
|
Apr 27, 2025 |
|
Designing Human-AI Collaboration: A Sufficient-Statistic Approach
|
Apr 27, 2025 |
|
GOAT: Generative Adversarial Training for Human-AI Coordination
|
Apr 27, 2025 |
|
π0.5: Generalization in Robotic Manipulation via Diverse Data
|
Apr 27, 2025 |
|
NoWag: Unified Compression for Large Language Models
|
Apr 26, 2025 |
|
Optimal Tool Calls in Language Model Reasoning
|
Apr 26, 2025 |
|
Data Selection for Empirical Risk Minimization
|
Apr 26, 2025 |
|
LoRe: Low-Rank Reward Modeling for Personalized LLMs
|
Apr 26, 2025 |
|
ParaPO: Reducing Language Model Verbatim Reproduction
|
Apr 26, 2025 |
|
Test-Time RL: Self-Evolving LLMs via Majority Voting Rewards
|
Apr 25, 2025 |
|
Tina: Tiny LoRA Reasoning Models
|
Apr 25, 2025 |
|
Evaluating large language models in theory of mind tasks
|
Apr 25, 2025 |
|
QUEST: Quality Sampling for Machine Translation
|
Apr 24, 2025 |
|
Offline Preference Learning via Simulated Trajectory Feedback
|
Apr 24, 2025 |
|
Reasoning Elicitation in Language Models via Counterfactual Feedback
|
Apr 24, 2025 |
|
Eliciting Human Preferences with Language Models
|
Apr 24, 2025 |
|
Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning
|
Apr 24, 2025 |
|
γ-Bench: Evaluating LLMs in Multi-Agent Games
|
Apr 24, 2025 |
|
DRAFT: Self-Driven LLM Tool Mastery via Documentation Refinement
|
Apr 24, 2025 |
|
Optimal Prediction Sets for Enhanced Human-AI Accuracy
|
Apr 24, 2025 |
|
Self-Correction via Reinforcement Learning for Language Models
|
Apr 24, 2025 |
|
Tractable Multi-Agent Reinforcement Learning through Behavioral Economics
|
Apr 24, 2025 |
|
Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement
|
Apr 24, 2025 |
|
Iterative Nash Policy Optimization for Language Model Alignment
|
Apr 24, 2025 |
|
SycEval: Benchmarking LLM Sycophancy in Mathematics and Medicine
|
Apr 23, 2025 |
|
Stack AI: Democratizing Enterprise AI Development
|
Apr 22, 2025 |
|
Evaluating Modern Recommender Systems: Challenges and Future Directions
|
Apr 22, 2025 |
|
AI in the Enterprise: Seven Lessons from Frontier Companies by OpenAI
|
Apr 22, 2025 |
|
Discussion: Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
|
Apr 21, 2025 |
|
AI Agent Protocols and Human Preference
|
Apr 21, 2025 |
|
Cross-Environment Cooperation for Zero-Shot Multi-Agent Coordination
|
Apr 20, 2025 |
|
Sutton and Silver: The Era of Experience: Learning Beyond Human Data
|
Apr 19, 2025 |
|
Sample, Don't Search: Rethinking Test-Time Alignment for Language Models
|
Apr 19, 2025 |
|
AI Agents: Echoes of Past Technology Pivots?
|
Apr 19, 2025 |
|
Minimalist LLM Reasoning: Rejection Sampling to Reinforcement
|
Apr 19, 2025 |
|
Securing the Model Context Protocol in Enterprise Environments
|
Apr 19, 2025 |
|
Improving Multi-Turn Tool Use with Reinforcement Learning
|
Apr 19, 2025 |
|
Cultural Knowledge Conservation and Control in Large Language Models
|
Apr 19, 2025 |
|
Data Quality, Repetition, and Scaling of Language Models
|
Apr 18, 2025 |
|
Compute-Optimal Scaling Laws for Language Models Revisited
|
Apr 18, 2025 |
|
Concise Reasoning via Reinforcement Learning
|
Apr 18, 2025 |
|
Throughput Limits for LLM Inference and AI Agent Scheduling
|
Apr 14, 2025 |
|
RL Post-training Amplifies Pretraining Behaviors in Language Models
|
Apr 14, 2025 |
|
Fast Adaptation of Behavioral Foundation Models
|
Apr 14, 2025 |
|
Proprietary Reward Models: Sustaining Advantage in Agentic AI
|
Apr 13, 2025 |
|
Why Multi-Agent LLM Systems Fail: A Comprehensive Study
|
Apr 12, 2025 |
|
Play2Prompt: Zero-Shot Tool Instruction Optimization via Tool Play
|
Apr 12, 2025 |
|
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
|
Apr 12, 2025 |
|
API and GUI Agents: Divergence, Convergence, and Hybrid Approaches
|
Apr 12, 2025 |
|
AI, Chess, and Competitive Advantage: Substitution and Complementation
|
Apr 12, 2025 |
|
Knowledge of the Firm and Replication of Technology
|
Apr 12, 2025 |
|
Firm Resources and Sustained Competitive Advantage
|
Apr 12, 2025 |
|
Evaluating Pharmaceutical Marketing to Physicians with Panel Data
|
Apr 12, 2025 |
|
Theory of the firm in the era of Agents
|
Apr 12, 2025 |
|
Large Language Models: An Applied Econometric Framework
|
Apr 12, 2025 |
|
Evaluating the World Model Implicit in a Generative Model
|
Apr 12, 2025 |
|
Machine Learning for Hypothesis Generation in Social Science
|
Apr 11, 2025 |
|
Active Learning for Moral Preference Elicitation: Challenges and Nuances
|
Apr 11, 2025 |
|
Gradient-Based Surveys for Nonparametric Discrete Choice Experiments
|
Apr 11, 2025 |
|
Explainable Data-driven Share-of-choice Product Line Design Optimization
|
Apr 11, 2025 |
|
The More You Ask, the Less You Get: When Additional Questions Hurt External Validity
|
Apr 11, 2025 |
|
Conjoint topics from Handbook of Marketing Analytics: Methods and Applications
|
Apr 11, 2025 |
|
Choice-Based Conjoint Analysis: Methods and Applications
|
Apr 11, 2025 |
|
Beyond Conjoint Analysis: The Future of Preference Measurement
|
Apr 11, 2025 |
|
An Optimization Framework for Adaptive Questionnaire Design
|
Apr 11, 2025 |
|
Adaptive Self-Explication of Multiattribute Preferences
|
Apr 11, 2025 |
|
Conjoint Analysis: Methods, Applications, and Recent Developments
|
Apr 11, 2025 |
|
Current Issues and a “Wish List” for Conjoint Analysis
|
Apr 11, 2025 |
|
Ellipsoidal Methods for Adaptive Choice-Based Conjoint Analysis
|
Apr 11, 2025 |
|
Adaptive Polyhedral Methods for Conjoint Analysis
|
Apr 11, 2025 |
|
MSL: Enhancing LLM Recommenders via Masked Softmax Loss
|
Apr 11, 2025 |
|
Self-Supervised Deep Reinforcement Learning for Optimal Question Ranking
|
Apr 11, 2025 |
|
Adaptive Language Elicitation for Latent Information Discovery
|
Apr 10, 2025 |
|
LLM Persona Bias: Promise and Peril in Simulation
|
Apr 10, 2025 |
|
AutoTools: Automating Tool Use for Large Language Models
|
Apr 10, 2025 |
|
Tool Learning with Large Language Models: A Comprehensive Survey
|
Apr 10, 2025 |
|
All Roads Lead to Likelihood: RL for Fine-Tuning Value
|
Apr 08, 2025 |
|
ATLAS: Tuning Agents via Critical Step Learning
|
Apr 08, 2025 |
|
Thinking Faster by Writing Less: Chain of Draft Reasoning
|
Apr 08, 2025 |
|
Meta Plan Optimization for Boosting LLM Agents
|
Apr 08, 2025 |
|
L1: Length Controlled Reasoning with Reinforcement Learning
|
Apr 08, 2025 |
|
WikiBigEdit: Benchmarking Lifelong Knowledge Editing in LLMs
|
Apr 08, 2025 |
|
PLAN-AND-ACT: LLM Agent Planning with Synthetic Data
|
Apr 08, 2025 |
|
SEARCH-R1: LLMs Learn to Reason and Search via Reinforcement Learning
|
Apr 08, 2025 |
|
The Theory of the Firm: Information, Incentives, and Organization
|
Apr 08, 2025 |
|
Four Formalizable Theories of the Firm
|
Apr 08, 2025 |
|
Efficient Tool Use with Chain-of-Abstraction Reasoning
|
Apr 06, 2025 |
|
CodeTool: Process Supervision for Enhanced LLM Tool Invocation
|
Apr 06, 2025 |
|
Evaluating LLM Agents in Multi-Turn Conversations: A Survey
|
Apr 06, 2025 |
|
Epistemic Alignment in User-LLM Knowledge Delivery
|
Apr 06, 2025 |
|
MCP is (not) all you need
|
Apr 06, 2025 |
|
AI, Human Skills, and Competitive Advantage in Chess
|
Apr 05, 2025 |
|
Inference-Time Scaling for Generalist Reward Modeling
|
Apr 04, 2025 |
|
Optimal Pure Exploration in Linear Bandits via Sampling
|
Apr 04, 2025 |
|
Presidential Address: The Economist as Designer in the Innovation Process for Socially Impactful Digital Products
|
Apr 04, 2025 |
|
Emergent Symbolic Mechanisms for Reasoning in Large Language Models
|
Apr 03, 2025 |
|
Inference-Time Alignment: Coverage, Scaling, and Optimality
|
Apr 03, 2025 |
|
Sharpe Ratio-Guided Active Learning for Preference Optimization
|
Apr 03, 2025 |
|
Active Learning for Adaptive In-Context Prompt Design
|
Apr 03, 2025 |
|
Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
|
Apr 03, 2025 |
|
On the Biology of a Large Language Model
|
Apr 01, 2025 |
|
Async-TB: Asynchronous Trajectory Balance for Scalable LLM RL
|
Apr 01, 2025 |
|
Instacart's Economics Team: A Hybrid Role in Tech
|
Mar 31, 2025 |
|
Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework
|
Mar 31, 2025 |
|
Why MCP won
|
Mar 31, 2025 |
|
SWEET-RL: Training LLM Agents for Collaborative Reasoning
|
Mar 31, 2025 |
|
TheoryCoder: Bilevel Planning with Synthesized World Models
|
Mar 30, 2025 |
|
Driving Forces in AI: Scaling to 2025 and Beyond (Jason Wei, OpenAI)
|
Mar 29, 2025 |
|
Expert Demonstrations for Sequential Decision Making under Heterogeneity
|
Mar 28, 2025 |
|
TextGrad: Backpropagating Language Model Feedback for Generative AI Optimization
|
Mar 27, 2025 |
|
MemReasoner: Generalizing Language Models on Reasoning-in-a-Haystack Tasks
|
Mar 27, 2025 |
|
RAFT: In-Domain Retrieval-Augmented Fine-Tuning for Language Models
|
Mar 27, 2025 |
|
Inductive Biases for Exchangeable Sequence Modeling
|
Mar 26, 2025 |
|
InverseRLignment: LLM Alignment via Inverse Reinforcement Learning
|
Mar 26, 2025 |
|
Prompt-OIRL: Offline Inverse RL for Query-Dependent Prompting
|
Mar 26, 2025 |
|
Alignment from Demonstrations for Large Language Models
|
Mar 25, 2025 |
|
Q♯: Distributional RL for Optimal LLM Post-Training
|
Mar 18, 2025 |
|
Scaling Test-Time Compute Without Verification or RL is Suboptimal
|
Mar 14, 2025 |
|
Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning
|
Mar 14, 2025 |
|
Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning
|
Mar 14, 2025 |
|
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
|
Mar 14, 2025 |
|
Revisiting Superficial Alignment Hypothesis
|
Mar 14, 2025 |
|
Diagnostic uncertainty: teaching language Models to describe open-ended uncertainty
|
Mar 14, 2025 |
|
Language Model Personalization via Reward Factorization
|
Mar 14, 2025 |
|
How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach
|
Mar 14, 2025 |
|
Can Large Language Models Extract Customer Needs as well as Professional Analysts?
|
Mar 13, 2025 |
|
Spurlens: finding spurious correlations in Multimodal llms
|
Mar 13, 2025 |
|
Improving test-time search with backtrack- Ing Improving test-time search with backtrack- Ing against in-context value verifiersagainst in-context value verifiers
|
Mar 13, 2025 |
|
Adaptive elicitation of latent information Using natural language
|
Mar 13, 2025 |
|
Document Valuation in LLM Summaries: A Cluster Shapley Approach
|
Mar 13, 2025 |
|
s1: simple test time scaling
|
Mar 13, 2025 |