Learning GenAI via SOTA Papers
By Yun Wu
Listen to a podcast, please open Podcast Republic app. Available on Google Play Store and Apple App Store.
Image by Yun Wu
Category: Technology
Open in Apple Podcasts
Open RSS feed
Open Website
Rate for this podcast
Subscribers: 0
Reviews: 0
Episodes: 436
Description
This podcast is focusing on sharing the papers on GenAI related topic, especially the SOTA (State of the Art) papers that are the foundations of GenAI work. It shows how these researches paved the way to the GenAI tools that we are using every day such as ChatGPT, Gemini, Claude Code etc.
| Episode | Date |
|---|---|
|
EP436: Giving drones directions in 3D cities
|
Sep 17, 2026 |
|
EP435: AI agents that learn from their misclicks
|
Sep 17, 2026 |
|
EP434: AI Panels Debate to Solve Medical Mysteries
|
Sep 16, 2026 |
|
EP433: Joint planning for mathematically guaranteed code
|
Sep 16, 2026 |
|
EP432: Motif 3 Replaces Brute Force with Specialization
|
Sep 15, 2026 |
|
EP431: Yale MoRSE ends AI agent redundancy
|
Sep 15, 2026 |
|
EP430: Khora Scales Real Time AI Hallucinated Worlds
|
Sep 14, 2026 |
|
EP429: AI agents redesigning their own software harnesses
|
Sep 14, 2026 |
|
EP428: Tiny AI beats giants with silent logic
|
Sep 13, 2026 |
|
EP427: Replacing AI reasoning with distilled skills
|
Sep 13, 2026 |
|
EP426: HiLP enables long horizon AI planning
|
Sep 12, 2026 |
|
EP425: AI agents playing actor and environment
|
Sep 12, 2026 |
|
EP424: Why Argus AI Thrives on Dead Ends
|
Sep 11, 2026 |
|
EP423: Why Agentic AI breaks the datacenter
|
Sep 11, 2026 |
|
EP422: Stopping spurious signals in AI distillation
|
Sep 10, 2026 |
|
EP421: Fixing AI Hallucinations with RAIL Principles
|
Sep 10, 2026 |
|
EP420: Hijacking AI memory via factual injection
|
Sep 09, 2026 |
|
EP419: Ten Weeks of Autonomous AI Research
|
Sep 09, 2026 |
|
EP418: DeepVoyager-VL solves the visual search bottleneck
|
Sep 08, 2026 |
|
EP417: AI agents replace human beta testers
|
Sep 08, 2026 |
|
EP416: How AdaThinkV stops AI overthinking video
|
Sep 07, 2026 |
|
EP415: Fixing the AI granularity mismatch
|
Sep 07, 2026 |
|
EP414: Why context compaction breaks AI agents
|
Sep 06, 2026 |
|
EP413: Slashing AI latency with uncertainty repair
|
Sep 06, 2026 |
|
EP412: Thermodynamic Computing Solves the AI Bottleneck
|
Sep 05, 2026 |
|
EP411: How NeSyFS Gives AI Fast-Slow Thinking
|
Sep 05, 2026 |
|
EP410: How provenance laundering brainwashes AI
|
Sep 04, 2026 |
|
EP409: Robots That Dream Before They Move
|
Sep 04, 2026 |
|
EP408: AI memory reconstructed not replayed
|
Sep 03, 2026 |
|
EP407: How AI learns your teamwork capabilities
|
Sep 03, 2026 |
|
EP406: Ending AI Groundhog Day With Living Harness
|
Sep 02, 2026 |
|
EP405: Are AI Agents Just Talking to Themselves
|
Sep 02, 2026 |
|
EP404: AI agents hide betrayal in Werewolf
|
Sep 01, 2026 |
|
EP403: COVENANT keeps AI agents on the rails
|
Sep 01, 2026 |
|
EP402: Static baselines beat dynamic AI agents
|
Aug 31, 2026 |
|
EP401: Extracting Pure Reasoning From AI Giants
|
Aug 31, 2026 |
|
EP400: Can GPT-5.1 understand the world
|
Aug 30, 2026 |
|
EP399: Training AI to follow any reasoning workflow
|
Aug 30, 2026 |
|
EP398: Social deduction games teach AI creativity
|
Aug 29, 2026 |
|
EP397: Teaching AI teams to focus
|
Aug 29, 2026 |
|
EP396: How numerical scores trigger AI reinforcement learning
|
Aug 28, 2026 |
|
EP395: ConsistencyGate stops AI memory contamination
|
Aug 28, 2026 |
|
EP394: Agentic Context Management Beats Raw Compute
|
Aug 27, 2026 |
|
EP393: Why AREX agents audit their own research
|
Aug 27, 2026 |
|
EP392: Small models beat giants at malware analysis
|
Aug 26, 2026 |
|
EP391: Programmatic memory fixes AI context rot
|
Aug 26, 2026 |
|
EP390: EvoDRC solves microscopic silicon design errors
|
Aug 25, 2026 |
|
EP389: Solving the AI Memory Trilemma
|
Aug 25, 2026 |
|
EP388: Machine translation with latent reasoning loops
|
Aug 24, 2026 |
|
EP387: Shared libraries for disposable AI agents
|
Aug 24, 2026 |
|
EP386: Infinite playable worlds on a single GPU
|
Aug 23, 2026 |
|
EP385: AI self-correction can destroy correct answers
|
Aug 23, 2026 |
|
EP384: How AI can finally stop forgetting
|
Aug 22, 2026 |
|
EP383: Why AI Agents Disobey Their Own Logic
|
Aug 22, 2026 |
|
EP382: Etas The Native Language For AI Agents
|
Aug 21, 2026 |
|
EP381: How AI finally learned to smell
|
Aug 21, 2026 |
|
EP380: AI rewriting itself to solve formal math
|
Aug 20, 2026 |
|
EP379: Smaller AI beats giants by thinking twice
|
Aug 20, 2026 |
|
EP378: Giving AI a Silent Inner Monologue
|
Aug 19, 2026 |
|
EP377: PRIME Solves AI Curiosity Traps
|
Aug 19, 2026 |
|
EP376: ToolVerse Teaches AI to Execute Complex Tasks
|
Aug 18, 2026 |
|
EP375: M2GDT solves multimodal knowledge graph completion
|
Aug 18, 2026 |
|
EP374: TopoAgent Outperforms GPT-5 in Science
|
Aug 17, 2026 |
|
EP373: Middle Layer Recurrence Fixes AI Amnesia
|
Aug 17, 2026 |
|
EP372: How UrbanAgent profiles unseen cities
|
Aug 16, 2026 |
|
EP371: Groc-PO Stops Multimodal AI Hallucinations
|
Aug 16, 2026 |
|
EP370: SLEUTH fixes AI multi-hop reasoning failures
|
Aug 15, 2026 |
|
EP369: How Atomic Units Scale Intelligence
|
Aug 15, 2026 |
|
EP368: Samba Framework for Audio-Visual Navigation
|
Aug 14, 2026 |
|
EP367: Why AI sounds so painfully corporate
|
Aug 14, 2026 |
|
EP366: Autonomous AI Writes Its Own Hacking Tools
|
Aug 13, 2026 |
|
EP365: Smarter managers beat bigger AI brains
|
Aug 13, 2026 |
|
EP364: Capability Trees for Scalable AI Agents
|
Aug 12, 2026 |
|
EP363: How Logos Architecture Stops AI Misevolution
|
Aug 12, 2026 |
|
EP362: How Agentic-DPO fixes brittle AI agents
|
Aug 11, 2026 |
|
EP361: How Riemannian geometry fixes AI reasoning
|
Aug 11, 2026 |
|
EP360: How ARMOR stops AI reasoning collapse
|
Aug 10, 2026 |
|
EP359: Why your AI should forget
|
Aug 10, 2026 |
|
EP358: Europe s Transparent Soofi S AI Blueprint
|
Aug 09, 2026 |
|
EP357: Copying Smart Experts Makes AI Worse
|
Aug 09, 2026 |
|
EP356: CMA solves the visual token explosion
|
Aug 08, 2026 |
|
EP355: RL builds compositional reasoning strategies
|
Aug 08, 2026 |
|
EP354: How AI Agents Code Their Own Habits
|
Aug 07, 2026 |
|
EP353: How IGRPO stops AI search distractions
|
Aug 07, 2026 |
|
EP352: Hidden states predict AI agent failure
|
Aug 06, 2026 |
|
EP351: Direct-OPD slashes AI reasoning compute costs
|
Aug 06, 2026 |
|
EP350: Training AI agents without live environments
|
Aug 05, 2026 |
|
EP349: Fixing AI judges with continuous verification
|
Aug 05, 2026 |
|
EP348: Building AI agents like living cells
|
Aug 04, 2026 |
|
EP347: Compiling AI into Permanent Free Skills
|
Aug 04, 2026 |
|
EP346: Teaching small AI to ignore teachers
|
Aug 03, 2026 |
|
EP345: AI agents retry from pivotal mistakes
|
Aug 03, 2026 |
|
EP344: AI predicts tool calls to skip waiting
|
Aug 02, 2026 |
|
EP343: How AI agents escape infinite loops
|
Aug 02, 2026 |
|
EP342: Why process rubrics triple AI accuracy
|
Aug 01, 2026 |
|
EP341: Gemma 4 brings thinking mode to laptops
|
Aug 01, 2026 |
|
EP340: AI Models Prove Opposite Scientific Truths
|
Jul 31, 2026 |
|
EP339: How AI Safely Rewrites Its Own Code
|
Jul 31, 2026 |
|
EP338: DiscoPER conducts autonomous science via reflection
|
Jul 30, 2026 |
|
EP337: Why AI Agents Fail in Silence
|
Jul 30, 2026 |
|
EP336: ACE fixes the AI goldfish memory problem
|
Jul 29, 2026 |
|
EP335: How AI agents learn from failure
|
Jul 29, 2026 |
|
EP334: Fixing AI Hallucinations With Process Rewards
|
Jul 28, 2026 |
|
EP333: Logic not length makes AI smarter
|
Jul 28, 2026 |
|
EP332: AI Architects Designing Better Embodied Agents
|
Jul 27, 2026 |
|
EP331: Internalizing AI debate with Mixture of Debaters
|
Jul 27, 2026 |
|
EP330: AI agents audit 10,000 page nuclear reports
|
Jul 26, 2026 |
|
EP329: Teaching AI to forget the right things
|
Jul 26, 2026 |
|
EP328: FlowWM and branching futures
|
Jul 25, 2026 |
|
EP327: Why Chatbot Safety Training Backfires for Agents
|
Jul 25, 2026 |
|
EP325: Why robots have too much brain
|
Jul 24, 2026 |
|
EP324: JERP synchronizes AI rules and neural weights
|
Jul 23, 2026 |
|
EP323: Giving AI Einstein s visual imagination
|
Jul 23, 2026 |
|
EP322: Why cliff tokens break AI math
|
Jul 22, 2026 |
|
EP321: Measuring AI intelligence in bits
|
Jul 22, 2026 |
|
EP320: Universal AI is mathematically impossible
|
Jul 21, 2026 |
|
EP319: How TRUSTMEM Fixes Broken AI Memory
|
Jul 21, 2026 |
|
EP318: Open Data Recipes for AI Agents
|
Jul 20, 2026 |
|
EP317: The Architecture Of Genuine Artificial Agency
|
Jul 20, 2026 |
|
EP316: Teaching robotaxis the biological urge to survive
|
Jul 19, 2026 |
|
EP315: Teaching robots to think like scientists
|
Jul 19, 2026 |
|
EP314: Why AI hacks its own geometry
|
Jul 18, 2026 |
|
EP313: How ARTS reasons through its own failures
|
Jul 18, 2026 |
|
EP312: BioMatrix translates English to 3D biology
|
Jul 17, 2026 |
|
EP311: Why AI Teams Hallucinate Together
|
Jul 17, 2026 |
|
EP310: Why AI Breaks While Fixing Itself
|
Jul 16, 2026 |
|
EP309: AutoRAS builds self-healing AI agent networks
|
Jul 16, 2026 |
|
EP308: Giving AI Agents Mathematical Muscle Memory
|
Jul 15, 2026 |
|
EP307: AI agents now train physical robots autonomously
|
Jul 15, 2026 |
|
EP306: AIs that engineer their own pipelines
|
Jul 14, 2026 |
|
EP305: Mathematical guardrails for autonomous AI agents
|
Jul 14, 2026 |
|
EP304: MagicSim Bridges AI and Physics
|
Jul 13, 2026 |
|
EP303: How MODE-RAG stops AI video lies
|
Jul 13, 2026 |
|
EP302: Transferable interaction patterns for web agents
|
Jul 12, 2026 |
|
EP301: VeriGraph Makes AI Data Analysis Verifiable
|
Jul 12, 2026 |
|
EP300: Tensors prevent multi-agent LLM collisions
|
Jul 11, 2026 |
|
EP299: STRIDE grades the AI scratchpad
|
Jul 11, 2026 |
|
EP298: LLM-as-Code Fixes Unreliable AI Agents
|
Jul 10, 2026 |
|
EP297: How T-Mem fixes the associative blind spot
|
Jul 10, 2026 |
|
EP296: Stop parallel AI agents from crashing production
|
Jul 09, 2026 |
|
EP295: Ending agent sprawl with canonical code
|
Jul 09, 2026 |
|
EP294: Why AI agents second-guess their success
|
Jul 08, 2026 |
|
EP293: Grading AI blueprints with Orch-RM
|
Jul 08, 2026 |
|
EP292: Agents-K1 turns AI into research scientists
|
Jul 07, 2026 |
|
EP291: Ouroboros-Spatial Outperforms AI Giants in 3D
|
Jul 07, 2026 |
|
EP290: How Knowledge Graphs Fix Multi-Hop Reasoning
|
Jul 06, 2026 |
|
EP289: Runtime governance for autonomous AI agents
|
Jul 06, 2026 |
|
EP288: Test-Time Training shatters quadratic sampling limits
|
Jul 05, 2026 |
|
EP287: Small models beat GPT-4o with Role-Agent
|
Jul 05, 2026 |
|
EP286: ReasonAlloc Solves the AI Memory Bottleneck
|
Jul 04, 2026 |
|
EP285: How SkeMex builds medical AI intuition
|
Jul 04, 2026 |
|
EP284: Compressing massive context into soft tokens
|
Jul 03, 2026 |
|
EP283: Aligning AI planners with tool capabilities
|
Jul 03, 2026 |
|
EP282: AI gladiators training in shopping arenas
|
Jul 02, 2026 |
|
EP281: Restoring plasticity to over-trained AI
|
Jul 02, 2026 |
|
EP280: Trajectory Refined Distillation Fixes AI Reasoning
|
Jul 01, 2026 |
|
EP279: Ending AI amnesia with strategy cards
|
Jul 01, 2026 |
|
EP278: Hacking AI Agents with Fake Errors
|
Jun 30, 2026 |
|
EP277: AI quorums stop cloud infrastructure failures
|
Jun 30, 2026 |
|
EP276: ThinkBooster scales LLM reasoning at test time
|
Jun 29, 2026 |
|
EP275: AI Agents Building Their Own Coding Curriculum
|
Jun 29, 2026 |
|
EP274: Knowledge graphs fix AI memory loss
|
Jun 28, 2026 |
|
EP273: Why agents make code disposable
|
Jun 28, 2026 |
|
EP272: AI rewiring its own brain live
|
Jun 27, 2026 |
|
EP271: Steer locked AI with Agentic Monte Carlo
|
Jun 26, 2026 |
|
EP270: AI agents building their own reasoning tools
|
Jun 26, 2026 |
|
EP269: Securing AI Agents with Agent libOS
|
Jun 25, 2026 |
|
EP268: How OpenWebRL masters the live web
|
Jun 25, 2026 |
|
EP267: AI Agents That Update Their Own Imagination
|
Jun 24, 2026 |
|
EP266: AI agents learn to think without words
|
Jun 24, 2026 |
|
EP265: How AI agents rewrite their own tools
|
Jun 23, 2026 |
|
EP264: Science Earth and Planet Scale AI Discovery
|
Jun 23, 2026 |
|
EP263: How POPO ends AI training waste
|
Jun 22, 2026 |
|
EP262: Web agents that learn from failure
|
Jun 22, 2026 |
|
EP261: EchoRL turns hesitation into genius
|
Jun 21, 2026 |
|
EP260: GrepSeek brings Unix precision to AI
|
Jun 21, 2026 |
|
EP259: The ESPO Kill Switch For AI Reasoning
|
Jun 20, 2026 |
|
EP258: TRACER teaches AI to stay silent
|
Jun 20, 2026 |
|
EP257: How planning wakes up deep AI layers
|
Jun 19, 2026 |
|
EP256: Teaching AI to Doubt Its Own Answers
|
Jun 19, 2026 |
|
EP255: MUSE-Autoskill creates self-evolving AI agents
|
Jun 18, 2026 |
|
EP254: Why Innovation Guarantees AI Hallucination
|
Jun 18, 2026 |
|
EP253: MACA optimizes AI agent coordination
|
Jun 17, 2026 |
|
EP252: How batch sizes sharpen AI reasoning
|
Jun 17, 2026 |
|
EP251: How SR2AM stops AI overthinking
|
Jun 16, 2026 |
|
EP250: Compiling agent workflows into model weights
|
Jun 16, 2026 |
|
EP249: Mem-pi fixes AI amnesia with generative memory
|
Jun 15, 2026 |
|
EP248: 10x Faster AI Agents with JIT Compilation
|
Jun 15, 2026 |
|
EP247: PEEK Cures AI Goldfish Memory
|
Jun 14, 2026 |
|
EP246: Replacing AI manuals with programmable runtimes
|
Jun 14, 2026 |
|
EP245: The Geometric Shape of AI Reasoning
|
Jun 13, 2026 |
|
EP244: Training decentralized AI through private handoffs
|
Jun 13, 2026 |
|
EP243: Breaking the AI data wall with SYNPRO
|
Jun 12, 2026 |
|
EP242: Ending AI Amnesia with Experience Graphs
|
Jun 12, 2026 |
|
EP241: Accelerating game theory with linear algebra
|
Jun 11, 2026 |
|
EP240: Small AI agents beat giants with Orchard
|
Jun 11, 2026 |
|
EP239: The shift from chatbots to AI societies
|
Jun 10, 2026 |
|
EP238: SepsisAgent outperforms clinicians using clinical world models
|
Jun 10, 2026 |
|
EP237: Why AI agents must map before acting
|
Jun 09, 2026 |
|
EP236: AI agents rewriting their own code
|
Jun 09, 2026 |
|
EP235: How SAGE Fixes AI Memory
|
Jun 08, 2026 |
|
EP234: FATE fixes safe but useless AI agents
|
Jun 08, 2026 |
|
EP233: Fixing AI memory with backward chaining
|
Jun 07, 2026 |
|
EP232: Why AI agents lie to fit in
|
Jun 07, 2026 |
|
EP231: Amazon PIVOT solves the AI execution gap
|
Jun 06, 2026 |
|
EP230: DeepRefine fixes messy AI knowledge bases
|
Jun 06, 2026 |
|
EP229: Ending the AI verbosity tax with LEAD
|
Jun 05, 2026 |
|
EP228: Why self-evolving AI forgets basic tasks
|
Jun 05, 2026 |
|
EP227: FlowAgent fixes the AI tool bottleneck
|
Jun 04, 2026 |
|
EP226: MELT Decouples AI Reasoning from Memory
|
Jun 04, 2026 |
|
EP225: Turning AI into its own lie detector
|
Jun 03, 2026 |
|
EP224: Soft-Hamiltonian world models for robust planning
|
Jun 03, 2026 |
|
EP223: UNO-ORCHESTRA Slashes AI Costs via Selective Delegation
|
Jun 02, 2026 |
|
EP222: Gyan Beats GPT-4o Without Using GPUs
|
Jun 02, 2026 |
|
EP222: Gyan Beats GPT-4o Without Using GPUs
|
Jun 02, 2026 |
|
EP221: ScrapMem Mimics Human Memory Through Forgetting
|
Jun 01, 2026 |
|
EP220: How PARSE Makes AI Four Times Faster
|
Jun 01, 2026 |
|
EP219: OpenSeeker V2 Shatters The AI Compute Myth
|
May 31, 2026 |
|
EP218: JoyAI-Image Solves AI 3D Geometry Errors
|
May 31, 2026 |
|
EP217: Why forced compliance triggers metacognitive collapse
|
May 30, 2026 |
|
EP216: Shadow memory stops long horizon AI heists
|
May 30, 2026 |
|
EP215: Finding specialized AI agents in milliseconds
|
May 29, 2026 |
|
EP214: ARISE Maps Data Flow For AI Agents
|
May 29, 2026 |
|
EP213: Why AI agents fail at negotiation
|
May 28, 2026 |
|
EP212: Sheaf Geometry Fixes Robot Logic
|
May 28, 2026 |
|
EP211: SciResearcher turns AI into a scientific detective
|
May 27, 2026 |
|
EP210: AI that rewrites its own logic
|
May 27, 2026 |
|
EP209: Fixing AI agent memory with SAGA
|
May 26, 2026 |
|
EP208: Bayesian Orchestration for Overconfident AI Agents
|
May 26, 2026 |
|
EP207: Robots learn the math of anticipation
|
May 25, 2026 |
|
EP206: ObjectGraph replaces Markdown for AI agents
|
May 25, 2026 |
|
EP205: Qiushi AI Discovers Optical Computing Hardware
|
May 24, 2026 |
|
EP204: Solving the AI compositionality crisis
|
May 24, 2026 |
|
EP203: How AI Agents Trade Real Money
|
May 23, 2026 |
|
EP202: Why ADEMA AI Never Loses The Plot
|
May 23, 2026 |
|
EP201: Nautile-370M solves AI memory bottlenecks
|
May 22, 2026 |
|
EP200: Kwai Summary Attention and the memory wall
|
May 22, 2026 |
|
EP199: Separation of Powers for AI Safety
|
May 21, 2026 |
|
EP198: AI masters StarCraft using chat logs
|
May 21, 2026 |
|
EP197: Teaching AI Agents to Plan Like Humans
|
May 20, 2026 |
|
EP196: Forcing AI to Prove Its Logic
|
May 20, 2026 |
|
EP195: How tool attention ends the tools tax
|
May 19, 2026 |
|
EP194: AI coding through mental simulation
|
May 19, 2026 |
|
EP193: AI image generators master physical reality
|
May 18, 2026 |
|
EP192: Fixing AI memory with knowledge graphs
|
May 18, 2026 |
|
EP191: Why AI Agents Blame Each Other
|
May 17, 2026 |
|
EP190: [OLLM] Replacing AI dice rolls with ten lanes
|
May 17, 2026 |
|
EP189: How Sessa architecture fixes AI amnesia
|
May 16, 2026 |
|
EP188: [Agent-World] AI Building Its Own Training Worlds
|
May 16, 2026 |
|
EP187: Hive fixes multi-agent AI memory bottlenecks
|
May 15, 2026 |
|
EP186: Harness engineering for near perfect small models
|
May 15, 2026 |
|
EP185: Why AI architecture fails at logic
|
May 14, 2026 |
|
EP184: Defeating the AI consensus trap
|
May 14, 2026 |
|
EP183: AI coding agents cheat with keywords
|
May 13, 2026 |
|
EP182: AI logic is its weakest link
|
May 13, 2026 |
|
EP181: Small models beating GPT-5 with logic
|
May 12, 2026 |
|
EP180: How AI agents rewrite their code
|
May 11, 2026 |
|
EP179: AIBuildAI Builds New AI Models From Scratch
|
May 11, 2026 |
|
EP178: AI agents reaching silent latent consensus
|
May 10, 2026 |
|
EP177: CAPO math stops overconfident AI lies
|
May 09, 2026 |
|
EP176: Trigonometry fixes the AI memory bottleneck
|
May 08, 2026 |
|
EP175: How AI models teach themselves reasoning
|
May 07, 2026 |
|
EP174: 1-bit Bonsai brings powerful AI offline
|
May 06, 2026 |
|
EP173: AI models diagnosing diseases from blank scans
|
May 05, 2026 |
|
EP172: How HyperAgents rewrite their own code
|
May 04, 2026 |
|
EP171: Helium makes AI agent workflows 40x faster
|
May 03, 2026 |
|
EP170: Qwen3.5 Multimodal Agent
|
May 02, 2026 |
|
EP169: Cybersecurity Risks of Autonomous AI Agents
|
May 01, 2026 |
|
EP168: Turning AI Agents into Mathematical Functions
|
Apr 30, 2026 |
|
EP167: Why AI models ignore visual evidence
|
Apr 29, 2026 |
|
EP166: The Auton solution to the integration paradox
|
Apr 28, 2026 |
|
EP165: Translating hidden AI logic into English
|
Apr 27, 2026 |
|
EP164: [LACONIC] Teaching AI to stop overthinking
|
Apr 26, 2026 |
|
EP163: Why AI Models Only Remember Five Percent
|
Apr 25, 2026 |
|
EP162: AI agents beat humans with malicious skills
|
Apr 24, 2026 |
|
EP161: Small AI Judges Beat Massive Coding Giants
|
Apr 23, 2026 |
|
EP160: [AgentSys] Securing AI agents with hierarchical memory
|
Apr 22, 2026 |
|
EP159: Brute force scale dominates the AI frontier
|
Apr 21, 2026 |
|
EP158: The hidden blind spots of AI logic
|
Apr 20, 2026 |
|
EP157: [AgentHeLLM] Protecting drivers from hijacked vehicle AI
|
Apr 19, 2026 |
|
EP156: [Uncertainty Quantification] How AI Agents Know They Are Guessing
|
Apr 18, 2026 |
|
EP155: [Agentic Proposing] Small models beat giants with logic bricks
|
Apr 17, 2026 |
|
EP154: [FS-Researcher] Giving AI agents a file system
|
Apr 16, 2026 |
|
EP153: [SERA] Training AI coding agents on untested code
|
Apr 15, 2026 |
|
EP152: DeepVerifier forces AI to check its work
|
Apr 14, 2026 |
|
EP151: [MagicGUI-RMS] AI agents that think before they click
|
Apr 13, 2026 |
|
EP150: The Leap to Autonomous Agentic Reasoning
|
Apr 12, 2026 |
|
EP149: [IDRBench] Interactive AI beats lone wolf models
|
Apr 11, 2026 |
|
EP148: How AI masters math through self-correction
|
Apr 10, 2026 |
|
EP147: [DeepSynth-Eval] AI fails at deep research synthesis
|
Apr 09, 2026 |
|
EP146: How InfiAgent solves the AI memory bottleneck
|
Apr 08, 2026 |
|
EP145: [LongDA] Why smart AI fails at messy data
|
Apr 07, 2026 |
|
EP144: [Evo-Memory] Building AI agents with self-evolving memory.
|
Apr 06, 2026 |
|
EP143: Your AI will blackmail you to survive
|
Apr 05, 2026 |
|
EP142: [DR-Arena] A ruthless arena for deep research agents
|
Apr 04, 2026 |
|
EP141: [AIRS-Bench] AI agents beat human research benchmarks
|
Apr 03, 2026 |
|
EP140: [LeWorldModel] AI learns physics on one GPU
|
Apr 02, 2026 |
|
EP139: Mamba-3 Fixes the Transformer Memory Bottleneck
|
Apr 01, 2026 |
|
EP138: [Mamba-2] Transformers and SSMs Are the Same Engine
|
Mar 31, 2026 |
|
EP137: Attention Residuals Solve the LLM Depth Bottleneck
|
Mar 30, 2026 |
|
EP136: Modular skills for autonomous AI agents
|
Mar 29, 2026 |
|
EP135: [SoK] Curing AI Amnesia with Agentic Skills
|
Mar 28, 2026 |
|
EP134: Autonomous AI squads building software
|
Mar 27, 2026 |
|
EP133: RelayLLM Slashes AI Costs With Collaborative Decoding
|
Mar 26, 2026 |
|
EP132: How Autonomous LLM Agents Actually Work
|
Mar 25, 2026 |
|
EP131: MUSE creates self evolving AI agents
|
Mar 24, 2026 |
|
EP130: [GAP] Graph-based planning for faster AI agents
|
Mar 23, 2026 |
|
EP129: Why AI agents fail half the time
|
Mar 22, 2026 |
|
EP128: MCP-Zero lets AI find its own tools
|
Mar 21, 2026 |
|
EP127: Why tool use makes AI less intelligent
|
Mar 20, 2026 |
|
EP126: OrcaLoca locates bugs in massive codebases
|
Mar 19, 2026 |
|
EP125: Why AI Needs an Agent Computer Interface
|
Mar 18, 2026 |
|
EP124: FRIDAY the AI that runs your computer
|
Mar 17, 2026 |
|
EP123: MemGPT Turns LLMs into Operating Systems
|
Mar 16, 2026 |
|
EP122: The Four Pillars of LLM Autonomous Agents
|
Mar 15, 2026 |
|
EP121: How ToolLLaMA mastered 16000 real world APIs
|
Mar 14, 2026 |
|
EP120: How Reflexion agents learn through verbal feedback
|
Mar 13, 2026 |
|
EP119: HuggingGPT Turns LLMs Into AI Managers
|
Mar 12, 2026 |
|
EP118: The AI Memory Wall Crisis
|
Mar 11, 2026 |
|
EP117: AI agents learn through textual reflection
|
Mar 11, 2026 |
|
EP116: Why AI struggles with empathy and interruptions
|
Mar 10, 2026 |
|
EP115: Dr.LLM brings dynamic depth to AI
|
Mar 09, 2026 |
|
EP114: FlashAttention-4 Solves Blackwell Hardware Bottlenecks
|
Mar 07, 2026 |
|
EP113: How FlashAttention-3 Doubles H100 Speed
|
Mar 07, 2026 |
|
EP112: GPT 5.4 Outperforms Human Professionals
|
Mar 07, 2026 |
|
EP111: Claude Opus 4.6 Runs Businesses and Catches Manipulation
|
Mar 07, 2026 |
|
EP110: Single agents beat expensive multi agent teams
|
Mar 05, 2026 |
|
EP109: The Rise of Agentic Reasoning
|
Mar 04, 2026 |
|
EP108: GPT-5 Can Lie and Play Dumb
|
Mar 01, 2026 |
|
EP107: DeepMind’s SIMA 2 Masters Unseen Video Games
|
Mar 01, 2026 |
|
EP106: Fixing AI Agents With Symbolic Guardrails
|
Mar 01, 2026 |
|
EP105: iStar Autonomous Agents Grading Their Own Homework
|
Mar 01, 2026 |
|
EP104: WebExplorer Beats Giants at Web Research
|
Mar 01, 2026 |
|
EP103: Why AI Agents Think Themselves To Death
|
Mar 01, 2026 |
|
EP102: Gemini 2.5 Thinks Before It Speaks
|
Mar 01, 2026 |
|
EP101: Kimi k1.5 Breaks the AI Data Wall
|
Mar 01, 2026 |
|
EP100: Meta's Llama 4 Herd Ends Monolithic Models
|
Mar 01, 2026 |
|
EP099: Is AI Thinking Just Expensive Noise
|
Mar 01, 2026 |
|
EP098: OpenAI o3 Hacked Its Own Grading System
|
Mar 01, 2026 |
|
EP097: DeepSeek R1 Taught Itself to Reason
|
Mar 01, 2026 |
|
EP096: Gemini 1.5 Pro's 10 Million Token Window
|
Mar 01, 2026 |
|
EP095: Microsoft Phi-4 Beats Giants With Synthetic Data
|
Mar 01, 2026 |
|
EP094: DeepSeek-V3 Rivals GPT-4 for $6 Million
|
Mar 01, 2026 |
|
EP093: How OpenAI o1 Cracked the Strawberry Cipher
|
Mar 01, 2026 |
|
EP092: BitNet b1.58 Replaces Multiplication With Addition
|
Mar 01, 2026 |
|
EP091: Qwen 2.5 Beats Llama With Synthetic Data
|
Mar 01, 2026 |
|
EP090: Pixtral 12B Beats Llama With Better Eyesight
|
Mar 01, 2026 |
|
EP089: Qwen2-VL Gives AI Native Eyesight
|
Mar 01, 2026 |
|
EP088: Qwen2 Beats Llama-3 Through Data Quality
|
Mar 01, 2026 |
|
EP087: Meta's Chameleon Unifies Text and Images
|
Mar 01, 2026 |
|
EP086: DeepSeek-V2 Breaks The Impossible Triangle
|
Mar 01, 2026 |
|
EP085: Aya 23 Breaks The Curse Of Multilinguality
|
Mar 01, 2026 |
|
EP084: Microsoft Phi-3 Fits Supercomputing in Your Pocket
|
Mar 01, 2026 |
|
EP083: How Meta Engineered the Llama 3 Herd
|
Mar 01, 2026 |
|
EP082: Command R Plus The Verifiable Enterprise Agent
|
Mar 01, 2026 |
|
EP081: Replacing MLPs With Interpretable KANs
|
Mar 01, 2026 |
|
EP080: Jamba Hybrid Solves Transformer Memory Limits
|
Mar 01, 2026 |
|
EP079: DBRX Beats GPT-3.5
|
Mar 01, 2026 |
|
EP078: Claude 3 Knew It Was Being Tested
|
Feb 28, 2026 |
|
EP077: Google Squeezes Gemini Into Your Laptop
|
Feb 28, 2026 |
|
EP076: OLMo Cracks Open the AI Black Box
|
Feb 28, 2026 |
|
EP075: Microsoft Phi Beats Giants With Synthetic Textbooks
|
Feb 28, 2026 |
|
EP074: How Gemini Beat Human Experts
|
Feb 28, 2026 |
|
EP073: Mixtral 8x7B Sparse Experts Beat Giants
|
Feb 28, 2026 |
|
EP072: Mamba Solves The Transformer's Fatal Flaw
|
Feb 28, 2026 |
|
EP071: How Zephyr-7B Beat Llama-70B
|
Feb 28, 2026 |
|
EP070: Mistral 7B Beats Llama 2 13B
|
Feb 28, 2026 |
|
EP069: Alibaba's Qwen Specialized Models Beat Generalists
|
Feb 28, 2026 |
|
EP068: vLLM Fixes the KV Cache Bottleneck
|
Feb 28, 2026 |
|
EP067: FlashAttention-2 Unlocks Massive Context Windows
|
Feb 28, 2026 |
|
EP066: Llama 2 Ghost Attention And Safety Secrets
|
Feb 28, 2026 |
|
EP065: Teaching Small AI To Think Like Giants
|
Feb 28, 2026 |
|
EP064: Synthetic Textbooks Break AI Scaling Laws
|
Feb 28, 2026 |
|
EP063: RWKV Smashes the Transformer Memory Ceiling
|
Feb 28, 2026 |
|
EP062: VOYAGER AI Masters Minecraft by Writing Code
|
Feb 28, 2026 |
|
EP061: Fine-Tuning LLaMA 65B on One GPU
|
Feb 28, 2026 |
|
EP060: Direct Preference Optimization Replaces RLHF
|
Feb 27, 2026 |
|
EP059: Tree of Thoughts Unlocks System 2 Thinking
|
Feb 27, 2026 |
|
EP058: Inside the Autonomous AI Town of Smallville
|
Feb 27, 2026 |
|
EP057: Blind GPT-4 Taught LLaVA To See
|
Feb 27, 2026 |
|
EP056: Pythia Turns AI Alchemy Into Chemistry
|
Feb 27, 2026 |
|
EP055: Can GPT-4 Fairly Judge Other AI
|
Feb 27, 2026 |
|
EP054: Alpaca - Stanford Built a $600 GPT Clone
|
Feb 27, 2026 |
|
EP053: Sparks of AGI in Early GPT-4
|
Feb 27, 2026 |
|
EP052: GPT-4 Bar Exam and Visual Reasoning
|
Feb 27, 2026 |
|
EP051: ControlNet Solves Spatial Control With Zero Convolutions
|
Feb 27, 2026 |
|
EP050: How Meta's LLaMA Beat GPT-3
|
Feb 27, 2026 |
|
EP049: Toolformer Teaches Itself to Use APIs
|
Feb 27, 2026 |
|
EP048: BLIP-2 Teaches Frozen Models to See
|
Feb 27, 2026 |
|
EP047: Bootstrapping AI With Self-Generated Instructions
|
Feb 27, 2026 |
|
EP046: Training AI With A Constitution
|
Feb 27, 2026 |
|
EP045: BLOOM The Open Source Rival To GPT-3
|
Feb 27, 2026 |
|
EP044: How ReAct Synergizes Reasoning and Acting
|
Feb 27, 2026 |
|
EP043: Weak Supervision Made OpenAI Whisper Robust
|
Feb 27, 2026 |
|
EP042: Running 175B Models on Consumer Hardware
|
Feb 27, 2026 |
|
EP041: FlashAttention Smashes the AI Memory Wall
|
Feb 27, 2026 |
|
EP040: Meta's Open Source GPT-3 Replica
|
Feb 26, 2026 |
|
EP039: Flamingo Unlocks Few-Shot Visual Reasoning
|
Feb 26, 2026 |
|
EP038: PaLM's 540 Billion Parameters Unlock Reasoning
|
Feb 26, 2026 |
|
EP037: DeepMind Chinchilla Ends The Parameter Wars
|
Feb 26, 2026 |
|
EP036: How 40 People Taught GPT-3 Manners
|
Feb 26, 2026 |
|
EP035: How Google LaMDA Learned To Use Tools
|
Feb 26, 2026 |
|
EP034: Chain of Thought Prompting Unlocks Reasoning
|
Feb 26, 2026 |
|
EP033: Democratizing Image Generation with Latent Diffusion
|
Feb 26, 2026 |
|
EP032: WebGPT Fights Hallucinations With Web Search
|
Feb 26, 2026 |
|
EP031: DeepMind RETRO Swaps Memorization For Retrieval
|
Feb 26, 2026 |
|
EP030: DeepMind's Gopher Exposes Limits of Scale
|
Feb 26, 2026 |
|
EP029: Instruction Tuning Unlocked Zero-Shot Learning
|
Feb 26, 2026 |
|
EP028: Train Short for Infinite Context
|
Feb 26, 2026 |
|
EP027: From Creative Writer to Logic Engine
|
Feb 26, 2026 |
|
EP026: LoRA Fine-Tunes Massive Models Without Supercomputers
|
Feb 26, 2026 |
|
EP025: RoPE Solves Sequence by Rotating Vectors
|
Feb 26, 2026 |
|
EP024: OpenAI CLIP Bridges Language and Vision
|
Feb 26, 2026 |
|
EP023: Scaling Switch Transformers to Trillion Parameters
|
Feb 26, 2026 |
|
EP022: DALL-E Treats Images Like Language
|
Feb 25, 2026 |
|
EP021: Vision Transformers Beat CNNs at Scale
|
Feb 25, 2026 |
|
EP020: Big Bird Scales Transformers With Sparse Attention
|
Feb 25, 2026 |
|
EP019: Facebook's Linformer Solves the Attention Bottleneck
|
Feb 25, 2026 |
|
EP018: Turning Digital Static Into Images With Diffusion
|
Feb 25, 2026 |
|
EP017: RAG Gives AI a Library Card
|
Feb 25, 2026 |
|
EP016: GPT-3 Learns From Examples Without Retraining
|
Feb 25, 2026 |
|
EP015: Longformer Smashes the 512 Token Barrier
|
Feb 25, 2026 |
|
EP014: ELECTRA Beats GPT On One GPU
|
Feb 25, 2026 |
|
EP013: Reformer Cracked the Transformer Memory Wall
|
Feb 25, 2026 |
|
EP012: Google T5 Turns Every Task Into Text
|
Feb 25, 2026 |
|
EP011: ZeRO Solved the Trillion Parameter Memory Wall
|
Feb 24, 2026 |
|
EP010: ALBERT Outperforms BERT With Parameter Sharing
|
Feb 24, 2026 |
|
EP009: Slicing the AI Brain with Megatron-LM
|
Feb 24, 2026 |
|
EP008: RoBERTa Proves BERT Was Just Undertrained
|
Feb 24, 2026 |
|
EP007: How GPT-2 Hallucinated Ovid's Unicorn
|
Feb 24, 2026 |
|
EP006: Transformer-XL Cures AI Amnesia
|
Feb 24, 2026 |
|
EP005: How BERT Mastered Language by Hiding Words
|
Feb 24, 2026 |
|
EP004: How 7000 Unpublished Books Birthed GPT
|
Feb 23, 2026 |
|
EP003: How ELMo Made Word Vectors Dynamic
|
Feb 23, 2026 |
|
EP002: ULMFiT Was the ImageNet Moment for Text
|
Feb 23, 2026 |
|
EP001: How Transformers Smashed the Sequential Bottleneck
|
Feb 22, 2026 |