AI Dynamics

Global AI News Aggregator

About

RESEARCH

  • MemFactory: Unified Framework for Trainable Agent Memory Systems
    MemFactory: Unified Framework for Trainable Agent Memory Systems

    By

    @dair_ai

    –

    // Unified Inference and Training Framework for Agent Memory // Most memory-augmented agents are built with duct tape—one system for storage, another for retrieval, a third for training. New research introduces a unified framework that treats agent memory as a first-class, trainable component. MemFactory provides modular, plug-and-play memory components with native GRPO integration for fine-tuning memory management policies through RL. It supports Memory-R1, RMM, and MemAgent paradigms in one framework, with up to 14.8% relative gains over baselines. Why does it matter? As agents move from single-turn tools to persistent assistants, memory becomes the bottleneck. MemFactory gives researchers standardized infrastructure to build, train, and evaluate memory-driven agents without reinventing plumbing for every new approach. Paper: arxiv.org/abs/2603.29493 Learn to build effective AI agents in our academy: academy.dair.ai/

    → View original post on X — @dair_ai, 2026-04-01 14:28 UTC

  • Code-as-Policy Framework for Robot Perception and Control

    By

    @ken_goldberg

    –

    Very excited about the prospect of Code-as-Policy (CaP) for Robotics! Esp with recent rapid advances in agentic coding. CaP has potential to quickly combine VLA models with GOFE primitives into interpretable code, observe experiments, and iterate. Initial results are promising: Max Fu (@letian_fu) Robotics: coding agents’ next frontier. So how good are they? We introduce CaP-X: an open-source framework and benchmark for coding agents, where they write code for robot perception and control, execute it on sim and real robots, observe the outcomes, and iteratively improve code reliability. From @NVIDIA @Berkeley_AI @CMU_Robotics @StanfordAILab capgym.github.io 🧵 — https://nitter.net/letian_fu/status/2039342130565357956#m

    → View original post on X — @ken_goldberg, 2026-04-01 14:25 UTC

  • Neural Network Generates Real-Time Multiplayer Game Engine

    By

    @sallyeaves

    –

    Via @sallyeaves Gordon Wetzstein (@GordonWetzstein) We built a real-time multiplayer game generated entirely by a neural network—and now you can actually play it. In collaboration with @modal, we just launched the live demo for MultiGen, our diffusion-based multiplayer game engine. Grab some friends and try it here 👇 — https://nitter.net/GordonWetzstein/status/2038987059835306043#m

    → View original post on X — @sallyeaves, 2026-04-01 14:01 UTC

  • CaP-X: Open-Source Framework for Coding Agents in Robotics

    By

    @berkeley_ai

    –

    Robotics: coding agents’ next frontier. So how good are they? We introduce CaP-X: an open-source framework and benchmark for coding agents, where they write code for robot perception and control, execute it on sim and real robots, observe the outcomes, and iteratively improve code reliability. From @NVIDIA @Berkeley_AI @CMU_Robotics @StanfordAILab capgym.github.io 🧵

    → View original post on X — @berkeley_ai, 2026-04-01 14:00 UTC

  • Deep Generative Model for Cell ATACseq and RNAseq Profiling

    By

    @gp_pulipaka

    –

    A Deep Generative Model for Profiling of cell ATACseq and RNAseq. #BigData #Analytics #DataScience #AI #MachineLearning #IoT #IIoT #Python #RStats #TensorFlow #JavaScript #ReactJS #Serverless #DataScientist #Linux #Programming #Coding #100DaysofCode https://
    geni.us/Gen-RNASeq

    → View original post on X — @gp_pulipaka

  • SIGReg and LeWM Experiments: Challenges with Value Function Generalization

    By

    @id_aa_carmack

    –

    Adding a little bit of SIGReg to prefinal activations did coerce them into independent Gaussian, but it hurt generalization on value functions. Training a full LeWM ahead of time also resulted in worse value function estimation. I’m not giving up yet, but my first few attempts

    → View original post on X — @id_aa_carmack

  • Tri-System Theory: AI’s Impact on Human Reasoning and Cognitive Autonomy
    Tri-System Theory: AI’s Impact on Human Reasoning and Cognitive Autonomy

    By

    @sallyeaves

    –

    Thinking—Fast, Slow, and Artificial: How AI is Reshaping Human Reasoning and the Rise of Cognitive Surrender papers.ssrn.com/sol3/papers.… ✍️Steven D. Shaw & Gideon Nave via @SSRN @Wharton 👉 "We introduce Tri-System Theory, extending dual-process accounts of reasoning by positing System 3: artificial cognition that operates outside the brain" 👉 "System 3 can supplement or supplant internal processes, introducing novel cognitive pathways" 👉 "Across studies, participants with higher trust in AI and lower need for cognition and fluid intelligence showed greater surrender to System 3" 💡 "Tri-System Theory thus characterizes a triadic cognitive ecology, revealing how System 3 reframes human reasoning and may reshape autonomy and accountability in the age of AI" @Corix_JC @ahier @sim010101 @maponi @sallyeaves @CEO_AISOMA @dinisguarda @JagersbergKnut @FernandaKellner @PVynckier @EstelaMandela @sulefati7 @ChuckDBrooks @SusanHayes_ @theomitsa @TarakRindani @FrRonconi @Nicochan33 @JoannMoretti @Khulood_Almani @TheAIObserverX @pchamard @mikeflache @TysonLester @smaksked @amalmerzouk @Analytics_699 @MaryRich78 @NathaliaLeHen @sminaev2015 @WillyRayNick @RLDI_Lamy

    → View original post on X — @sallyeaves, 2026-04-01 13:52 UTC

  • Simple Battle-Tested Algorithms Outperform AI Systems
    Simple Battle-Tested Algorithms Outperform AI Systems

    By

    @sallyeaves

    –

    Simple, Battle-Tested Algorithms Still Outperform #AI buff.ly/UejRET3 @Hackernoon by Jose Crespo PhD Cc @jblefevre60 @Fabriziobustama @HaroldSinnott @gezgintrk @sallyeaves @SpirosMargaris @efipm

    → View original post on X — @sallyeaves, 2026-04-01 13:30 UTC

  • LeCun Apologizes to AI Researchers in April Fools Joke

    By

    @garymarcus

    –

    Hey, you are never gonna believe it! @ylecun organized a group phone call with me and @SchmidhuberAI and some of the other people he has ripped off over the years, and *apologized*. He’s a much more mature human being than I had ever realized. Oh wait… April Fool’s!

    → View original post on X — @garymarcus

  • Build a Large Language Model from Scratch Repository
    Build a Large Language Model from Scratch Repository

    By

    @sumanth_077

    –

    If you found it useful, reshare it with your network Follow me → @Sumanth_077 for more insights and tutorials on AI Engineering! nitter.net/Sumanth_077/status/203… Sumanth (@Sumanth_077) Build a Large Language Model from scratch! This repository contains the code examples for developing, pretraining, and finetuning a LLM from scratch. It is the official codebase for the book Build a Large Language Model (From Scratch). Notebook examples are included for each chapter: Chapter 1: Understanding Large Language Models Chapter 2: Working with Text Data Chapter 3: Coding Attention Mechanisms Chapter 4: Implementing a GPT Model from Scratch Chapter 5: Pretraining on Unlabeled Data Chapter 6: Finetuning for Text Classification Chapter 7: Finetuning to Follow Instructions Link to the repo in the comments! — https://nitter.net/Sumanth_077/status/2039332313910383043#m

    → View original post on X — @sumanth_077, 2026-04-01 13:22 UTC