2026-10-09

RoboJEPA: Scaling Robotic Latent World Models

👍 1

10/07 08:00

Latent world models have shown a remarkable ability to predict future states and to plan in the real world. In practice, however, we lack a principled way to estimate how their capabilities scale with model size, data, and compute, an open problem that slows progress in the field. In this work we pr

MIMESIS: Learning User Simulators as Training Environments for Interactive Agents

👍 10

10/07 08:00

Training and evaluating interactive language agents typically requires rich user interactions, yet collecting human feedback is expensive and difficult to scale. Simulated users offer a scalable alternative, but they must both resemble real user behavior and provide useful learning experiences for a

System Switch: When Should a Fast Decision Model Stop and Think?

👍 1

10/07 08:00

Dual-process agents pair a fast policy with a slow deliberative model. In real-time settings the slow model usually runs continuously; in turn-based agents and robot planners it is invoked on events such as uncertainty or a detected failure. We study a fast learned actor that takes every decision an

Q-Learning with Scalar Adjoint Matching

👍 15

10/07 08:00

Flow policies capture rich and diverse action distributions, and fine-tuning them with off-policy RL to improve beyond the demonstrations has drawn growing interest. However, fine-tuning a flow policy against a learned value function is not trivial, because the policy generates its action over many

UniSkill: Learning Actor-Aligned Skill Proposals for an Evolving Policy

👍 5

10/07 08:00

Large language model agents can improve across tasks by retaining reusable skills distilled from prior interactions. Recent work jointly optimizes task execution and skill extraction, enabling the policy and skillbank to co-evolve. However, as the actor continues learning, rewarding skill proposals

EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory

👍 4

10/07 08:00

Conditional memory architectures such as DeepSeek Engram use input n-grams to look up learned embeddings, expanding the capacity of large language models (LLMs) with limited additional computation. Beyond model scaling, this architecture has demonstrated the potential to decouple factual knowledge s

From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery

👍 16

10/07 08:00

Test-time scaling (TTS) improves the reasoning capabilities of large language models by allocating additional inference computation. Existing approaches to improving TTS efficiency largely optimize accuracy against one resource dimension at a time, advancing either the accuracy--cost or accuracy--la

QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation

👍 12

10/07 08:00

We introduce QuadTok, a novel framework for visual tokenization and autoregressive image generation. Compared to traditional approaches using 2D grids or 1D token sequences, we propose a hierarchical quadtree structure, bridging the gap between 2D spatial binding and 1D sequence-level flexibility. T

SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles

👍 7

10/07 08:00

Memory-augmented reinforcement learning strengthens LLM agents' ability to solve complex long-horizon tasks. Skills are one such form of memory, pairing instructions with an applicability condition over task types. However, retaining every skill indiscriminately as the policy improves lets obsolete

SWE-Game: Can Coding Agents Build the Games We Want?

👍 25

10/07 08:00

We introduce SWE-Game, a benchmark of 247 tasks grounded in 41 executable reference Godot games spanning 13 gameplay categories in 2D and 3D. Five task types cover development from a brief, implementation from a game design document, skeleton completion, repair of 83 injected-fault cases, and Godot-

RunningTab: Direct Workspace Interaction with Environment-Side Tabs

👍 34

10/07 08:00

Much knowledge work produces new deliverables from files a workspace already holds, and LLM agents are beginning to take such work over. Through direct corpus interaction, an agent can search and read any of those files from a terminal with no indexing, and producing a deliverable from many of them

Agent Plasticity: Measuring Self-Improvement Through Experience

👍 1

10/06 08:00

AI agents increasingly operate in environments where they can diagnose failures and improve through experience, yet existing evaluations largely measure what an agent can do at a fixed point in time rather than how effectively it learns. Evaluating self-improvement requires answering three questions

A self-learning scientific agent for X-ray diffraction

👍 9

10/06 08:00

A central challenge for scientific agents is to turn analytical experience into reusable expertise grounded in physical evidence. Here we introduce Gan Jiang, a self-learning agent for powder X-ray diffraction built on a diffraction-analysis ecosystem we developed: XMatcher, XQueryer, XDecomposer an

CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use

👍 9

10/06 08:00

Reconstructing an editable CAD model from a 3D shape remains a challenging engineering task. Existing methods can propose CAD operations, but no single source of proposals works equally well across different part geometries and stages of reconstruction. We introduce CADFather, an autonomous agentic

PhysEvo: Astra Can Act, Let It

👍 26

10/06 08:00

Astra can act, yet reliable manipulation depends on the system through which it observes and controls the world. We introduce PhysEvo, a framework for physical recursive self-improvement (RSI) around a single frozen model. A task agent executes robot tasks; a meta-agent uses the resulting trajectori

Co-Evolving Robot Orchestrators and Policies through Deployment

👍 1

10/06 08:00

Vision-language-action (VLA) policies trained on large datasets are capable within their training domains, yet they still fail to generalize to the variety of situations a robot meets in real-world deployment. Agentic robot systems complement the policy with a vision-language model (VLM) orchestrato

DLoop: Looped Speculative Decoding

👍 11

10/06 08:00

Speculative decoding accelerates autoregressive generation in large language models. In each drafting stage, a lightweight draft model proposes tokens that the target model subsequently verifies. With increasingly capable draft models, we find that the target model frequently accepts all tokens prod

Lineage-Aware Memory Governance: A Derivation-Gated Framework for Privacy-Preserving Column-Level Access Control in Enterprise AI Agents

👍 1

10/05 08:00

Enterprise AI agents that share a memory store face two unaddressed risks: sensitive data can leak through legitimately computed results the requester could not derive, and departments can silently compute a same-named key performance indicator (KPI) through conflicting logic. Existing agent-memory

TIDES: Implicit Time-Awareness in Selective State Space Models

👍 1

10/05 08:00

Selective state space models (SSMs), such as Mamba, achieve strong per-token expressivity by making the time discretization step TildeΔ a learned function of the input. However, in doing so, TildeΔ no longer equals the physical time gap Δ between consecutive observations, limiting the ability of the

Internalizing Agent Experience into Diffusion Model Weights via On-Policy Context Distillation

👍 10

10/05 08:00

Wrapping an image generation model in an agentic harness can effectively boost Text-to-Image task performance: the harness can leverage memory, skills, workflow orchestration, result verification, and iterative refinement to continually construct and revise prompts, thereby eliciting better images.

How corner is a corner case? Percentile control for highway scenario generation

👍 1

10/04 08:00

Generating corner-case scenarios with appropriate adversity in a simulation environment is critical for testing an autonomous vehicle (AV) software stack's safety performance before deployment. Existing autonomous-driving scenario generators can enforce specific behavior, adversity, or feasibility c

SheetSage2: Coherent Lead-Sheet Transcription with Synthetic Supervision

👍 7

10/04 08:00

Transcribing music into a human-readable score requires a coherent understanding of rhythm, harmony, melody, and form. Two obstacles limit this goal: annotated recordings are scarce, and accurate local predictions can still produce inconsistent musical sequences. We present SheetSage2, a unified mus

NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis

👍 19

10/03 08:00

Sparse-view novel view synthesis is a central problem in 3D content creation, but diffusion-based approaches remain limited by iterative denoising, making multi-view generation expensive at inference time. We introduce NAMVIS, a diffusion-free framework that reformulates multi-view image synthesis a

Beyond the Parameter Monolith: Reconstructive Memories, Executable Skills, and Residual Assembly for Language Models

👍 1

10/02 08:00

Language-model systems can separate contextual computation, persistent storage, and exact execution instead of updating all capabilities through one shared parameter system. We investigate FEM-ASM, a finite-element-method-inspired organization in which independently constructed document states and d

FastOPD: On-Policy Distillation for Lightweight VLA Deployment

👍 2

10/02 08:00

Vision-Language-Action (VLA) foundation models have scaled rapidly to enhance manipulation performance and generalizability, but this scaling incurs high computational costs that render real-world deployment increasingly challenging. Existing approaches typically mitigate this issue by designing sma

Inherit-MAS: Test-Time Evolution of Multi-Agent Systems through Workflow and Execution Inheritance

👍 4

10/01 08:00

Multi-agent systems (MAS) built from large language models coordinate specialized agents to tackle complex tasks, but effective workflows are difficult to design in advance. Test-time evolution refines workflows using execution feedback, yet broad revisions can disturb useful components, while re-ex

StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search

👍 4

10/01 08:00

Recovering executable CAD programs from 3D meshes is challenging due to the compositional nature of CAD construction and the interaction between discrete modeling choices and continuous parameters. Many learning-based methods predict complete programs in a single pass and rely predominantly on sketc

Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation

👍 4

10/01 08:00

Long-horizon compositional manipulation has become increasingly important for real-world robot deployment, where a single task involves multiple coordinated subtasks. Existing world-action models (WAMs) jointly predict short-horizon visual futures and actions, but typically lack explicit subtask-lev

PAMI: Part Anchored Motion for Text to Human-Object Interaction Generation

👍 1

09/29 08:00

Text-conditioned full-body human-object interaction (HOI) generation requires synthesizing human motion and object trajectories that match the input text while remaining precisely coordinated over time. Most methods represent the human and object as separate trajectories and predict the global human

Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation

👍 2

09/29 08:00

Few-step streaming audio--video generation requires both causal modeling and step distillation, yet standard training recipes face two context-related challenges. Teacher forcing pairs clean history with a noisy target, but supervises predictive contextual representations only indirectly through vel

How to scale your app with an AI UGC Army (Full Workflow)

@jakecastilloooo · 18.7K 粉丝 · 141.1K 阅 · 507 赞 · 40 转

10/08 00:38

AI UGC (when done correctly) is one of the greatest hacks for finding and scaling winning videos for organic and paid social. (FYI I’m giving away 13 prompts throughout this article AND a AI UGC skill

中文介绍 分享如何使用AI UGC Army扩大应用规模的全流程，提供13个prompt和AI UGC技能分享。

AI won't take your job anytime soon. In 10 yrs, only 5% of what humans do will be replaced by AI

@mustafasuleyman · 1.2M 粉丝 · 99.2K 阅 · 587 赞 · 104 转

10/06 22:16

This is the prediction Nobel laureate Daron Acemoglu makes in the first issue of The Humanist Review, our new magazine exploring the future of AI, published by MAI. He argues we need to stop

中文介绍 诺贝尔奖得主Daron Acemoglu预测，未来10年内AI将取代人类工作的比例仅为5%。

The Infinite SaaS Factory

@satyanadella · 9.6M 粉丝 · 82.6K 阅 · 587 赞 · 73 转

10/08 23:09

So much of what we do at work is still spent working around software. We switch between apps, rebuild context each time, and translate what we want to do into the steps each system expects. AI is

中文介绍 Satya Nadella探讨如何通过AI解决工作中的软件问题，提高工作效率。

how to use AI agents to run your marketing team (the playbook)

@aashatwt · 16.5K 粉丝 · 24.8K 阅 · 513 赞 · 43 转

10/07 20:05

i haven’t built a million-dollar app yet. but i’ve worked with many of the top AI companies over the last six months, and one thing is obvious: they move so fucking fast. here’s what that speed can

中文介绍 介绍如何利用AI代理运行营销团队，分享与顶级AI公司合作的经验。

If you have too many interests, build this AI system in 1 hour

@Hesamation · 90.6K 粉丝 · 21.4K 阅 · 618 赞 · 51 转

10/06 17:46

if you have an ADHD brain, you probably have six different goals, you get overwhelmed, and you miss days without working on any one of them. that's me. I love agents, harnesses, RL, LLM architecture,

中文介绍 针对多兴趣人士，分享构建AI系统的快速方法，涉及agents、RL、LLM架构等。

Synthesis Superintelligence: from Semiconductors to Superconductors — Periodic Labs’ Liam Fedus and Ekin Dogus Cubuk

Latent Space · 10/09 00:27

A special Science pod and Engineering pod crossover.. with Forward Deployed Engineering kicker!

中文介绍 Latent Space发布科技与工程融合项目，涵盖半导体到超导体的合成超级智能研究。

How Oracle turns days of work into minutes with ChatGPT and Codex

OpenAI News · 10/09 00:00

Across recruiting, engineering, and operations, Oracle turns specialist knowledge into fast, repeatable workflows with ChatGPT Work and Codex.

中文介绍 OpenAI推出ChatGPT和Codex，将专业知识转化为快速可复制的流程，应用于招聘、工程和运营。

Pollo AI turns creative ideas into campaigns with OpenAI

OpenAI News · 10/08 20:00

With GPT-5.6, GPT-6 Astra, and GPT‑Image‑2.5, Pollo AI helps creators turn bold ideas into detailed images and cinematic video ads.

中文介绍 Pollo AI利用GPT-5.6等模型，帮助创作者将创意转化为详细图像和视频广告。

AI breakthroughs in robotics won’t change your life any time soon

MIT Tech Review AI · 10/08 17:00

The story is a collaboration between MIT Technology Review and Aventine, a non-profit research foundation that creates and supports content about how technology and science are changing the way we live. A robot shaped like a human—white with a black head and torso—has been popping up on video feeds.

中文介绍 MIT Tech Review AI指出，机器人领域的AI突破不会立即改变人们的生活。

Building a safer path to autonomous industrial AI

MIT Tech Review AI · 10/08 16:17

Industrial AI is entering a new phase. After decades of predictive analytics and other specialized applications, advances in foundation models, physical AI, and agentic AI are making it possible to automate more complex tasks across industrial environments. But unlike AI that operates purely in the

中文介绍 MIT Tech Review AI探讨工业AI安全发展路径，自动化复杂任务成为可能。

[AINews] Claude Haiku 5.5 — better than GPT-6 Luna at the same pricing

Latent Space · 10/08 15:27

yay small models

中文介绍 Latent Space发布Claude Haiku 5.5模型，性能优于GPT-6 Luna，价格相同。

Disrupting AI-enabled “false front” operations

OpenAI News · 10/08 08:00

OpenAI disrupted two AI-enabled influence operations that used false-front journalists and a think tank to spread geopolitical messaging.

中文介绍 OpenAI打击利用虚假记者和智库传播地缘政治信息的AI影响力操作。

The model that didn't exist, so you made it yourself

Hugging Face Blog · 10/08 08:00

中文介绍 Hugging Face Blog介绍使用机器学习构建模型的过程。

ChatGPT Intelligent UI 🧠, Claude Haiku 5.5 ⚡, Grok Bot 3rd party models 🤖

TLDR AI · 10/08 08:00

中文介绍 TLDR AI介绍ChatGPT、Claude Haiku 5.5和Grok Bot等AI工具。

Multimodal open d1 decision models for the edge

Hugging Face Blog · 10/08 00:54

中文介绍 Hugging Face Blog介绍多模态边缘决策模型open d1。

Can a Cloud-Native Harness Make Agents Reliable Beyond the Desktop?

Latent Space · 10/07 22:10

Kubernetes co-creators Craig McLuckie and Joe Beda aim to bring agent harnesses fully into the cloud.

中文介绍 Kubernetes共同创造者推出云原生工具Stacklok，提升桌面以外的代理可靠性。

Introducing Falcon ASR

Hugging Face Blog · 10/07 21:21

中文介绍 Hugging Face Blog介绍Falcon ASR语音识别模型。

One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO

Hugging Face Blog · 10/07 20:45

中文介绍 Hugging Face Blog介绍Nvidia Nemotron模型在IOI和IMO比赛中的卓越表现。

Helping teens learn, plan, and shape the future of AI

OpenAI News · 10/07 20:00

College Planner is coming to ChatGPT for Teens to help students manage college applications, alongside new flashcards, quizzes, and a teen AI council.

中文介绍 OpenAI为青少年推出College Planner，辅助大学申请和AI未来规划。

Radisson Hotel Group brings hotel discovery into ChatGPT

OpenAI News · 10/07 15:00

Radisson partnered with Accenture to build a ChatGPT plugin using OpenAI technology, helping travelers find, compare, and book hotels while planning their trips.

中文介绍 Radisson酒店集团与Accenture合作，在ChatGPT中推出酒店发现插件。