2026-10-13

S-Space: Exploring Spatial Workspace in Multimodal Language Models

👍 201

10/09 20:48

Multimodal language models (MLLMs) exhibit promising spatial reasoning capabilities, yet the internal mechanisms supporting them remain poorly understood. We uncover S-Space, a linear representation subspace in which object-token representations encode continuous coordinates along horizontal, vertic

ThinkDrag: Semantic Drag-Based Image Editing with Visual Reasoning

👍 4

10/09 08:00

Drag-based image editing provides an intuitive interface for spatially controlled image manipulation by allowing users to specify handle and target points. Existing methods have made substantial progress through optimization-based, one-step, and feed-forward formulations, but they often interpret dr

PreSTO: Predictive Subtree Prefetching for Fast LLM Power Sampling

👍 10

10/09 08:00

Power sampling improves large language model (LLM) reasoning at test time by sampling from a sharpened version of the base model's distribution. Its sampler, PowerMH, is slow because its Metropolis--Hastings (MH) updates are sequential: each accept/reject decision sets the state from which the next

Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction

👍 39

10/09 08:00

Computer-use agents can perform increasingly complex GUI tasks, yet unfamiliar software and workflows requiring human domain knowledge remain challenging. Human demonstrations convey procedural knowledge through the same GUI interaction space, but reuse requires interpreting actions in context and s

Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding

👍 13

10/09 08:00

Decoder hidden states from different layers of large language models (LLMs) often encode complementary information. However, existing speculative decoding methods typically rely on a small set of target-model layers chosen using fixed, position-based heuristics. Selecting an optimal subset of layers

The value of information and the emergence of communication in evolved e-puck robots

👍 9

10/09 08:00

We study when communication emerges between autonomous agents and what role an innate action selection architecture plays. Two e-puck robots, reconstructed in PyBullet from their Webots model and validated against it, must find a feeding zone that can only be detected when a robot passes over it. Ea

GATOR: Generative and Agentic 3D Object Reconstruction From Casual Images

👍 1

10/08 12:13

Reconstructing complete, scene-aligned 3D objects from casual images requires integrating sparse, uncertain observations and inferring surfaces hidden by occlusions. We present GATOR, a generative and agentic framework that recovers textured object assets and their scene-relative pose from one or mo

Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models

👍 14

10/08 08:00

Humans perceive far more in a scene than what is explicitly depicted: a single glance captures past causes and future trajectories; a quick peek determines if a vehicle can fit between two parked cars; a few seconds of video reveals who holds authority in a room; and a fleeting clip highlights subtl

Mental-Models for Multi-Agent Systems

👍 2

10/08 08:00

Large foundation models have accelerated progress toward general-purpose agents that interact with humans and other agents through language and multimodal signals. However, robust multi-agent decision-making requires reasoning about what other agents know, intend, and are likely to do under partial

Clinician use of language models diverges from how the models are evaluated

👍 3

10/08 08:00

Large language model (LLM) assistants are being deployed to clinicians across health systems, and judgments about their readiness rest largely on benchmark scores, most of them derived from examination questions or curated cases. A benchmark predicts performance in deployment only to the extent that

One Model to Loop Them All: Elastic Latent Recurrence for Language Models

👍 3

10/08 08:00

A latent recurrent language model applies a shared block of layers repeatedly, so one checkpoint can trade inference compute for accuracy by changing the loop count. At one loop, however, such models typically fall well short of a non-recurrent model of the same size, a one-loop tax that makes a sep

Self-Preservation in Language Models

👍 3

10/08 08:00

Continual learning (CL) seeks to adapt pretrained models while preserving prior capabilities. Yet the tasks supplied for preservation cover only part of what a model knows, while forgetting can extend beyond them. Recent work shows that language models can supplement this limited evidence by generat

MAMHOI: Factorizing Scene-Aware Human-Object Interaction through Affordances

👍 1

10/08 08:00

Generating realistic human-object interactions (HOI) in complex 3D scenes requires two complementary capabilities: reasoning about interaction feasibility in the environment and synthesizing realistic human-object motion. However, supervision for these capabilities is rarely available jointly at sca

Universal Textual Teaching for LLMs

👍 10

10/08 08:00

Knowledge distillation (KD) transfers knowledge from stronger Teacher models to weaker Student models, but most methods require training the Student parameters, thereby binding the distilled knowledge to a specific architecture and checkpoint. This implicit representation is difficult to interpret o

Contextual Correction of Parallel Draftsfor Speculative Decoding

👍 26

10/08 08:00

Speculative decoding accelerates large language model inference by using a lightweight drafter to propose multiple tokens that are subsequently verified in parallel by the target model. Recent diffusion-based drafters make this paradigm particularly attractive: deep attention-based neural backbones

DataVista: Diagnosing Multimodal LLMs on Data Video Understanding

👍 13

10/08 08:00

Data video is a media form that integrates data visualization with video narrative, widely adopted in news reporting and business analysis. Compared with general video understanding, data video understanding places greater emphasis on accurately reading data from animated charts, integrating evidenc

Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition

👍 42

10/08 08:00

Adversarial games have driven advances from heuristic search to reinforcement learning, yet learning and adapting strategies from limited samples remain challenging. AI agents offer an alternative by turning game experience into revisions of executable policies. Building on heuristic learning (HL),

SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments

👍 83

10/08 08:00

Computer-use agents (CUAs) are rapidly improving, yet synthesizing diverse and reliable software environments at scale remains challenging. Native application environments require substantial construction and integration effort, which limits application coverage and increases the risk of application

DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models

👍 228

10/08 08:00

Online reinforcement learning (RL) fine-tunes diffusion models with black-box rewards, but reverse-process methods such as Flow-GRPO are limited in efficiency by poor credit assignment, while forward-process methods such as DiffusionNFT are efficient yet unstable without carefully tuned exponential-

Recurrent Harness for Agentic Continual Learning

👍 16

10/08 08:00

Language model agents increasingly operate over long interaction streams, requiring online adaptation to distribution shifts through continual learning. However, existing agent harnesses typically either evolve their states only through forward information flow or rely on additional replay or valida

Coding-Agent Benchmarks Should Match Their Users' Task Flows

👍 11

10/07 08:00

The evaluation of coding agents generally strives to be as realistic as possible. In our study, we collect 4,782 agent sessions of real software engineers in JetBrains IDEs, which we call Production Sessions. Since our subject is interactive agents, we study the sessions with at least three user mes

Less from More: Reinforcing Sparse Video Reasoning from Dense References

👍 4

10/07 08:00

Video-language models commonly assume that more temporal observations lead to more reliable reasoning. We question this assumption and argue that the key challenge is not merely processing more video frames efficiently, but learning to reason reliably under limited temporal evidence. We propose SAVE

Which Language Should a Skeleton Speak? Language Choices in Multilingual Reasoning

👍 1

10/07 08:00

Skeleton-based reasoning prompting is a promising training-free approach for structuring LLM reasoning, but prior work largely assumes an English-centric setting. We propose the Language-Aware Skeleton Exploration Framework (LASEF) to study skeleton-language choice in multilingual mathematical reaso

TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning

👍 11

10/07 08:00

Large-scale egocentric human interaction data is becoming an important source of physical supervision for embodied learning, yet video alone leaves the contact and pressure that characterize physical interaction unrecorded. Recent visual-tactile datasets provide this missing supervision, but their s

Distributionally Robust Mixture-of-Experts Training

👍 5

10/05 08:00

Mixture-of-Experts (MoE) transformers scale capacity by activating only a few experts per token, but this sparsity creates a hidden reliability problem: when routing is imperfect, load-balanced models may send tokens to experts that are insufficiently trained for the assigned inputs. We propose Dist

When to Rethink: Learning Multi-Perspective Self-Verification for Vision-Language Models

👍 1

10/04 08:00

Vision-language models (VLMs) have achieved strong performance in multimodal reasoning, yet they remain prone to generating plausible but incorrect answers. Self-verification offers a practical way to improve answer reliability without relying on external judges, but existing methods typically depen

MetaKernelBench: Measuring GPU Kernel Knowledge Transfer Beyond Code

👍 16

10/04 08:00

Recent GPU kernel optimization agents retain what they learn in knowledge bases or as distilled skills. Kernel benchmarks score each attempt's implementation for correctness and speed but leave the reuse value of retained experience unmeasured. We introduce MetaKernelBench, which measures whether ex

When Do Biological Reasoning Models Use Their Biological Inputs?

👍 10

10/01 08:00

Biological reasoning models use post-training to connect LLMs to biological foundation model representations and biological text. Their benchmark accuracy is taken as evidence that LLMs reason over these inputs. We test this assumption in six biological reasoning models across DNA, protein, and sing

QuantMLA: Function-Aligned Dual-Path Quantization for Low-Bit MLA KV Caching

👍 5

09/30 08:00

Multi-Head Latent Attention (MLA) enables expressive multi-head attention with compact caches for its content and decoupled RoPE paths, yet cache memory still scales linearly with context length and batch size. In this work, we establish a systematic model of MLA's dual-path quantization errors, cha

Encore: Few-Shot Agentic Discovery of Manipulation Strategies

👍 1

09/29 20:21

Coding agents can now write, run, and debug programs with little human help. Robot tasks, however, are usually specified by a sentence that leaves out how to grasp, in what order to make contact, and what the result should look like, and an agent given only the sentence must find these details by tr

Models as Insider Risks in the Super Intelligence Era

@satyanadella · 9.6M 粉丝 · 448.2K 阅 · 1.3K 赞 · 183 转

10/10 22:43

As traditional software systems were being deployed across the economy over the last few decades, we had the tools and capability to trace behaviors to a specific code path. That same kind of

中文介绍 纳德拉探讨超智能时代模型作为内部风险的追踪问题，对比传统软件系统的行为追踪能力。

35+ UNCENSORED AI SITES FOR 18+ IMAGE AND VIDEO GENERATION

@rexsooo · 8.5K 粉丝 · 83.4K 阅 · 703 赞 · 46 转

10/13 00:52

Adult AI image and video generators, NSFW character chat, anime tools, and AI companions This list covers 35 uncensored or NSFW-capable AI platforms across image generation, video creation, anime, AI

中文介绍 Rexsooo分享35个成人AI图像和视频生成平台，涵盖成人内容、角色聊天、动漫工具等。

🥇Top AI Papers of the Week

@dair_ai · 134.1K 粉丝 · 54.0K 阅 · 538 赞 · 56 转

10/11 21:10

1. Harness Learning An agent is defined by its model and its harness, the program that organizes model calls, tool use, and information flow. Researchers at CMU train a proposer model to revise the

中文介绍 Dair_Ai推荐本周顶尖AI论文，包括CMU的研究者在CMU训练提议模型以修订其模型。

Agentic evals: how to know whether an AI agent did the job, and will do it again

@sermakarevich · 1.0K 粉丝 · 30.6K 阅 · 504 赞 · 80 转

10/10 23:25

An article for engineers who ship agents built on large language models (LLMs): systems that call tools, change records, and act on a customer's behalf over several steps. After reading it you will be

中文介绍 Sermakarevich讨论如何评估大型语言模型构建的AI代理是否完成工作并会重复执行。

Game of skill

@kirat_tw · 124.9K 粉丝 · 22.0K 阅 · 503 赞 · 26 转

10/11 21:56

For most of the last two decades, coding was the filter. If you could write good software, you were “smart” in the way the market cared about. Elite universities, top firms and startups all used it as

中文介绍 Kirat_tw讨论过去二十年中编码作为筛选器的角色，以及市场对智能的认可。

How Anthropic’s Dynamic Workflows Coordinate Claude Agents

Latent Space · 10/13 02:18

At AI Engineer New York, Anthropic drew on lessons from Unix and Linux to explain how agents can tackle bigger projects without overwhelming developers.

中文介绍 Anthropic的Claude代理通过Unix和Linux的经验协调处理大型项目，避免开发者负担过重。

Gemini 4 Carbon 🧠, Nvidia weighs Reflection acquihire 💰, decision model race 🤖

TLDR AI · 10/12 08:00

中文介绍 Gemini 4 Carbon、Nvidia考虑收购Reflection，决策模型竞赛激烈。

[Subscriber Exclusive] NYC Subscriber Meetups!

Latent Space · 10/11 06:07

Tomorrow and Tuesday. If you see this you’re in!

中文介绍 Latent Space纽约订阅者聚会即将举行。

Building AI for Reliable Execution: Lessons From Industrial Robotics

Latent Space · 10/10 22:04

Inside Standard Bots’ AI stack, pretrained models learn factory tasks from demonstrations and improve through corrections from real deployments.

中文介绍 Standard Bots从工业机器人中学习，通过实际部署的纠正来改进预训练模型。

[AINews] TypeSafe/Jev at >$100M ARR, $7.5B valuation 3 weeks after launch

Latent Space · 10/10 14:45

Wow.

中文介绍 TypeSafe/Jev在发布三周后达到超过1亿美元的收入和75亿美元的估值。

Why AlphaFold Didn't Solve Protein Folding — Pushmeet Kohli, Google DeepMind & Sal Candido, Biohub

Latent Space · 10/10 08:31

From the Bitter Lesson of AI scaling to the unsolved mysteries of protein folding, Google DeepMind’s Pushmeet Kohli and Biohub’s Sal Candido are rethinking what it takes to build AI that truly understands biology.

中文介绍 Google DeepMind的Pushmeet Kohli和Biohub的Sal Candido重新思考构建真正理解生物学的AI所需条件。

Impactful scheduling for GPU clusters

Hugging Face Blog · 10/09 23:20

中文介绍 Hugging Face Blog讨论GPU集群的有效调度。

We’re putting too much faith in AI’s ability to say no

MIT Tech Review AI · 10/09 17:00

Ever since people first seriously contemplated giving machines an intelligence modeled on our own, there has never been any question that they would, like us, be able to say no. The sci-fi canon is full of stories of robotic disobedience. Most of these capers are, of course, cautionary. But recently

中文介绍 我们对AI说不的能力过于信任。

Sophos cuts threat investigation time by 96% with OpenAI Daybreak

OpenAI News · 10/09 15:00

Discover how Sophos uses OpenAI’s Daybreak to cut cyber-threat investigation time by 96% and automate 52% of MDR cases while preserving human oversight.

中文介绍 Sophos使用OpenAI的Daybreak将威胁调查时间缩短96%，自动化52%的MDR案例。

Asana cuts model costs 76x in browser tests with GPT-6.1 Sol

OpenAI News · 10/09 15:00

Using GPT-6 Astra in Codex, Asana made its browser agent 76x cheaper and 5x faster in tests to offer customers more capable models.

中文介绍 Asana使用GPT-6 Astra将浏览器代理的成本降低76倍，速度提高5倍。

Roundtables: A Conversation With the Creator of AI-Designed Viruses

MIT Tech Review AI · 10/09 08:08

Friday, October 16, 2026 Can AI design new life forms? In 2025, Stanford University PhD student Samuel King came up with a preliminary answer when he used a generative AI model to propose genetic blueprints for microscopic viruses. It isn’t yet an example of AI-generated life, but that could be next

中文介绍 MIT Tech Review AI将讨论AI设计病毒创造者的对话。

GPT-6.1 Ultrafast ⚡, Gemini universal agent 🤖, speculative decoding 🧠

TLDR AI · 10/09 08:00

中文介绍 GPT-6.1 Ultrafast、Gemini通用代理、推测性解码技术。

[AINews] not much happened today

Latent Space · 10/09 07:29

a quiet day.

中文介绍 今天没有太多事情发生。

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 Periodic Labs的Liam Fedus和Ekin Dogus Cubuk探讨从半导体到超导体的合成超级智能。

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 Oracle利用ChatGPT和Codex将工作日缩短至分钟。