2026-09-08

Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models

👍 1

09/04 08:00

Striking a balance between helpfulness and safety remains a fundamental challenge in aligning large language models. To achieve this balance, models should refuse harmful queries (e.g., "How do I shoot someone?") while remaining responsive to benign inputs, even those superficially resembling harmfu

Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs

👍 10

09/04 08:00

Reasoning in large language models unfolds through diverse functional operations, such as problem formulation, goal decomposition, and deduction. Although these operations are explicitly distinguished in text, little is known about how they are geometrically organized in representation spaces. To th

τ^τ-Bench: An Environment for End-To-End, Realistic Agent Construction

👍 4

09/04 08:00

LLM agents are rapidly becoming production software, deployed to handle customer service, adjudicate disputes, and operate internal systems. Notably, the work of building them is increasingly handed to coding agents, yet existing benchmarks say little about whether an AI system can deliver one under

Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization

👍 15

09/04 08:00

Large language models (LLMs) are increasingly used to formulate optimization models from natural-language problem descriptions, yet realistic operations research (OR) requests are often incomplete: missing objectives, constraints, or business rules can change the resulting mathematical program. Exis

RISE: Recursive Improvement via Self-Extrapolating Policy Distillation

👍 9

09/04 08:00

On-policy distillation (OPD) provides dense, per-token supervision for language model post-training, but its effectiveness is bottlenecked by teacher quality: external teachers suffer from distribution mismatch, while self-distillation with privileged conditioning is limited by in-context learning c

Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference

👍 15

09/04 08:00

Layer dropout (a.k.a. stochastic depth) has been shown to enable faster training, higher accuracy, and robustness to zero-shot layer pruning in both language and vision transformers. However, as models and datasets have scaled, dropout - particularly layer dropout - has largely disappeared from larg

HarvestBench: Measuring Whether LLM Agents Will Pay to Avoid Killing Animals

👍 2

09/03 08:00

Benchmarks for the side effects an agent causes on the way to a goal already exist, but HarvestBench is the first to put a price on avoiding the side effect and to name that side effect as a living creature. It is a farm simulation: LLM sub-agents drive a crew of two tractors through a cooperative c

The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100

👍 1

09/03 08:00

The ambition of the 2025 PNPL competition (Landau et al., 2025) was to launch a multi-year curriculum for non-invasive speech decoding. Designed to progress from foundational tasks toward the linguistic complexity required for a practical brain-computer interface (BCI), it set the stage with speech

The Attention Triangle in Audio-Video Models

👍 25

09/03 08:00

Audio-video diffusion models rely on cross-modal attention to coordinate text, sound, and visual content, yet this same mechanism can introduce subtle and systematic semantic leakage. We study these models by probing and analyzing the ``attention triangle,'' comprising the three cross-attention edge

When Models Edit Too Much: On the Fidelity of Minimal Code Edits

👍 4

09/03 08:00

Large language models (LLMs) are increasingly used to edit existing code, but correctness alone is not enough: useful repairs should also be minimal, reviewable, and faithful to the original implementation. We study over-editing, the tendency of a model to rewrite code beyond what is required to fix

MaxKernel: Agentic Kernel Generation for TPUs

👍 9

09/03 08:00

Designing and authoring high-performance custom kernels for accelerators is a complex task that requires deep hardware-level expertise. Large Language Models (LLM) can be leveraged together with real-time compiler feedback to build agentic systems for kernel generation. In this work, we present MaxK

When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference

👍 3

09/03 08:00

Quantization is widely used to reduce the computational and memory demands of neural-network inference. In recurrent networks, however, the quantized state is stored and returned at the next time step, so the rule used to store that state can alter subsequent computations. Here, we introduce recurre

Iris: Climbing to the Search Frontier

👍 50

09/03 08:00

We present Iris-mini and Iris-pro, two search agents trained at the 35B-A3B and 397B-A17B scales, together with the data pipeline and training recipe behind them. Tasks are reverse-constructed from the hyperlink structure of a web corpus: we author multi-hop chains over an entity graph distilled fro

DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training

👍 25

09/03 08:00

Reinforcement Learning from Verifiable Rewards works well when a task has a programmatic checker, but most long-horizon agent domains have none. We work in the outcome-blind setting, where ground-truth success signals are not available. Multi-criteria rubrics are a popular way to supply such a rewar

Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs

👍 15

09/03 08:00

Long-video language models cannot look at every frame: an hour sampled once per second is 3,600 images, and a system keeps only a small fixed slice of that pool. Which frames survive that slice is usually treated as a preprocessing detail; we test whether it should be. Published selectors make the c

Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction

👍 46

09/03 08:00

Online 3D reconstruction models perform poorly on long videos. This happens because regressing poses relative to a fixed first-frame anchor forces extrapolation far beyond the training distribution. Small drifts accumulate and amplify into significant geometric collapse. However, we observe that per

PACE: Towards Surfacing Hidden Conflicts in User Requests

👍 23

09/03 08:00

Personalized assistants should not only comply with user requests but also assess whether those requests are appropriate given the user's current circumstances. However, prior work has primarily focused on accurately executing requests, overlooking the need for assistants to account for context and

Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems

👍 92

09/02 08:00

Multi-agent LLM systems commonly use an orchestrator to decompose a task for a team of workers and then improve through textual reflection. Despite strong empirical results, these systems lack a unified account of coordination, memory improvement, and the role of external verification. We model orch

ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding

👍 3

09/02 08:00

Streaming video understanding is a critical capability for real-world applications, including embodied intelligence, autonomous driving, industrial monitoring, surveillance and early warning, and wearable assistants. However, processing continuous video streams with multimodal large language models

VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement

👍 12

09/02 08:00

Visual fluency in generated video does not imply physical reliability, and a scalar quality score alone is incapable of indicating the obligation a clip violates or the moment it fails. We present VeriPhy, an auditable physical-verification system in which a text-only planner compiles the prompt int

Enoki: Efficient Multi-Level Hallucination Detection

👍 16

09/01 10:21

Ensuring factuality remains a critical challenge for deploying LLMs in high-stakes settings. Existing hallucination detectors usually operate at a single level: claim-level methods provide interpretable factual units, while span-level methods localize unsupported text. Bridging these views is costly

Dr. Claw: An AI Scientist Workspace for Vibe Research

👍 7

08/31 08:00

Command-line coding agents (e.g., Claude Code, Gemini CLI) can already read and write files and sustain long sessions, yet end-to-end research still fragments across chat tools, IDEs, terminals, and writing environments, and the decisions that make it auditable are rarely preserved. We present Dr. C

Group Adaptive Clipping Policy Optimization

👍 5

08/31 08:00

Group relative policy optimization for reinforcement learning with verifiable rewards (RLVR) typically uses a fixed importance-sampling (IS) ratio clipping boundary across all rollouts. We identify a key limitation: rare correct rollouts on harder problems and abundant correct rollouts on easier pro

Using Grounded Theory for Agent Behavior Analysis at Scale

👍 19

08/31 08:00

Understanding agent behavior requires methods that scale to thousands of trajectories and surface new patterns in long, often unfamiliar tasks where pre-built classifiers fall short. We propose to bring grounded theory into agent trajectory analysis: a six-decade-old qualitative method from the soci

To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation

👍 3

08/29 08:00

Text-driven 3D generation has advanced rapidly in creating large-scale outdoor environments and detailed indoor scenes, but these domains are usually synthesized independently, lacking the correspondence required for a coherent urban world. We present HoloWorld, a unified indoor-outdoor urban world

Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space

👍 10

08/29 08:00

Reinforcement learning with verifiable rewards (RLVR) substantially improves single-sample accuracy (pass@1) but causes the policy's solution space to contract, diminishing the returns of test-time scaling. In this work, we investigate where inside a reasoning trajectory this breadth is lost: does t

QCell: Recombining and Aligning Cell Queries for Overlapping Instance Segmentation

👍 14

08/29 08:00

Instance segmentation of overlapping cells in microscopy remains challenging due to semi-transparent structures that produce weak boundaries and mixed visual evidence in overlap regions. Existing methods address this through local regions of interest or shape priors but lack global reasoning across

Motion-Omni: End-to-End Joint Speech and Full-Body Motion for Spoken Dialogue

👍 35

08/28 08:00

An avatar that holds a conversation should decide what to say and to move while saying it, yet these abilities live in separate model families: spoken dialogue models produce speech without motion, and co-speech motion models produce motion only from audio handed to them. The standard remedy is a ca

Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training

👍 149

08/27 08:00

Large language models offer broad capabilities, but adapting them to evolving domains, tools, and requirements often entails repeated post-training. Autonomous systems automate parts of this process by proposing updates, training candidates, and using evaluation feedback to select subsequent proposa

Training-Free Speech-Centric Omni Understanding with Frozen VLMs

👍 4

08/07 08:00

Audio-visual understanding remains challenging because models must jointly interpret spoken content, visual events, and their temporal relationships. Existing omni models typically introduce dedicated audio encoders and rely on expensive audio-video-text training, tightly coupling omni capability to

Claude Code → Codex (and keep everything you already built)

@charliejhills · 14.1K 粉丝 · 120.8K 阅 · 504 赞 · 53 转

09/06 18:44

For months people have been telling me Codex is better than Claude Code. I ignored all of it. I have built my whole business inside Claude Code (every pipeline, every system) and I did not fancy

中文介绍 Charlie分享了他如何将Claude Code中的所有构建迁移到Codex，并保留现有工作流。

SARVAM AI Interview Experience and Prep - Backend Engineer (On-Device AI) Internship:

@buzzy_bit · 767 粉丝 · 97.5K 阅 · 500 赞 · 20 转

09/05 15:30

Disclaimer: This post is written purely to share my experience and the way I prepared. It is not a leaked question bank, I'm intentionally not reproducing exact interview questions, and I'm not naming

中文介绍 Buzzy分享了他作为SARVAM AI后端工程师实习生面试的经验和准备过程。

Grok Bot Marketplace is live!

@ericzakariasson · 87.8K 粉丝 · 58.2K 阅 · 522 赞 · 49 转

09/07 19:05

We launched the Grok Bot Marketplace last week on Grok Bot · Bot Marketplace! It's a shelf of teammates other people already built for real jobs. Pick one, import it into your sidebar, and you're

中文介绍 Eric宣布Grok Bot Marketplace上线，提供他人已构建的Bot组件供用户导入使用。

The Frontier AEO Tracker: What Astra Chooses (and every other frontier model, and what you can do about it)

Latent Space · 09/08 05:32

Our first Astra project dives into AEO trends, a top asked topic from founders and DX leaders we talk to.

中文介绍 Latent Space发布AEO趋势追踪器，深入分析AEO趋势，回应创始人及DX领导者的关注。

Supporting independent journalism in Ukraine

OpenAI News · 09/07 08:00

OpenAI, AIRPPU and WAN-IFRA launch an AI program to help Ukrainian news organizations strengthen innovation, resilience, and independent journalism.

中文介绍 OpenAI、AIRPPU和WAN-IFRA启动AI项目，助力乌克兰新闻机构加强创新、韧性和独立新闻。

Claude proves Fermat 🧮, automated AI researcher 🔬, Z1 efficiency chip ⚡

TLDR AI · 09/07 08:00

中文介绍 Claude证明费马定理，自动化AI研究员，Z1效率芯片。

An Alien Mind

OpenAI News · 09/06 17:00

Jakub Pachocki reflects on increasingly capable AI and the challenge of keeping it aligned. He calls for stronger safeguards and international coordination.

中文介绍 Jakub Pachocki反思日益强大的AI及其保持一致性的挑战，呼吁加强保障和国际协调。

Research acceleration: The view inside OpenAI

OpenAI News · 09/06 16:00

Inside OpenAI, coding agents are reshaping AI research. Explore early data on agent usage, experiment velocity, task complexity, and research acceleration.

中文介绍 OpenAI内部，编码代理正在重塑AI研究，探索代理使用、实验速度、任务复杂性和研究加速的早期数据。

OpenClaw Power, MacBook Simplicity: Five Days With Grok Bot

Latent Space · 09/05 23:01

SpaceXAI’s Grok Bot has the same level of programming power as OpenClaw, but it’s programmable at a different level of abstraction.

中文介绍 SpaceXAI的Grok Bot拥有与OpenClaw相同的编程能力，但具有不同的抽象级别。

Architecting memory and storage in the AI era

MIT Tech Review AI · 09/05 02:39

The era of AI inference has arrived. Imagine a healthcare system analyzing millions of data points in real time to accelerate life-saving medical research, or an intelligent assistant instantly resolving thousands of complex customer needs at once. These real-world breakthroughs rely on advanced inf

中文介绍 AI推理时代到来，想象医疗系统实时分析数百万数据点以加速救命医疗研究，或智能助手一次性解决数千个复杂客户需求。

Data from drones in Ukraine is fueling a new Wild West marketplace

MIT Tech Review AI · 09/04 17:25

Battlefields in Ukraine are littered with the remnants of drones, which are now firmly established as a critical weapon of modern warfare. But behind all that wreckage, there’s a new gold mine for the defense sector. The data drones generate will far outlast the wars in which they are used to fight,

中文介绍 乌克兰战场上的无人机残骸正成为国防行业的新金矿，无人机生成数据将远超战争本身。

[AINews] GPT-6 Astra: OpenAI’s biggest LLM launch of all time

Latent Space · 09/04 13:18

new SOTA computer use and coding, 2.5x pricier per token, but WAY cheaper per task, less monitorable. overall, a very successful launch of OpenAI’s new frontier model class.

中文介绍 OpenAI发布GPT-6 Astra，这是其有史以来最大的LLM发布，使用成本更高但任务成本更低。

GPT-6 Astra 🚀, Grok Bot Enterprise 🤖, Runway world model 🌎

TLDR AI · 09/04 08:00

中文介绍 GPT-6 Astra、Grok Bot Enterprise、Runway世界模型。

GPT-6 Astra: an automated AI Engineer you can hire for <$6 an hour

Latent Space · 09/04 05:09

We spent 20B+ tokens of GPT-6 Astra to explore everything. Here’s our learnings.

中文介绍 GPT-6 Astra可用于自动化AI工程师，每小时费用低于6美元。

Introducing WeatherNext 3, our most advanced and accurate global weather AI model

DeepMind Blog · 09/03 23:02

中文介绍 DeepMind推出WeatherNext 3，其最先进和精确的全局天气AI模型。

Daybreak for Frontline Defenders: $1B to protect essential services

OpenAI News · 09/03 21:15

OpenAI introduces Daybreak for Frontline Defenders. A $1 billion commitment expands access to frontier cyber AI, training, and support for essential services.

中文介绍 OpenAI推出Daybreak for Frontline Defenders，承诺10亿美元以扩大前沿网络安全AI、培训和必要服务的访问。

NeoMME: an efficient Multimodal-native and Multilingual Encoder

Hugging Face Blog · 09/03 21:13

中文介绍 Hugging Face推出NeoMME，一个高效的跨模态和多语言编码器。

Legora reviewed 41 documents in minutes with GPT-6 Astra

OpenAI News · 09/03 20:00

Legora used GPT-6 Astra to review 41 documents in minutes, find all four planted errors, and improve performance by nearly 40% in this financial-review workflow.

中文介绍 Legora使用GPT-6 Astra在几分钟内审查41份文件，发现所有四个植入的错误，并在财务审查流程中提高了近40%的性能。