2026-09-11

The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding

👍 2

09/09 08:00

Non-invasive speech decoding remains constrained by the low signal-to-noise ratio of neural recordings, which makes fine-grained reconstruction of phonemes or individual words difficult. Motivated by neuroscientific evidence that high-level semantic representations are distributed across cortical re

Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs

👍 4

09/09 08:00

Video understanding has rapidly evolved toward video large language models (VideoLLMs): systems that couple video representations with pretrained large language models and condition generation on a textual prompt. Their strong performance on captioning, question answering, retrieval and temporal gro

Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States

👍 1

09/09 08:00

Existing bias auditing methods typically rely on model outputs, requiring costly benchmarks or judge models and potentially missing internal shifts that never appear in generated text. We propose a reference-based method that audits bias in hidden-state representations across related model variants,

RESCUE-BENCH: Towards Relation-Aware Multi-Party Emotional Support Conversation Systems

👍 3

09/09 08:00

Existing emotional support conversation systems mainly focus on one-on-one seeker-supporter interactions and individual emotional states, leaving interpersonal relations in multi-party scenarios underexplored. In this work, we introduce relation-aware emotional support conversation, a new task that

Φ-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?

👍 8

09/09 08:00

Large language models (LLMs) have demonstrated remarkable capabilities in reasoning and code generation, raising the prospect that they could assist in developing and optimizing the very infrastructure that powers them. However, existing benchmarks mainly focus on isolated kernels, predefined operat

Show-Harness: Just a VLM Agent Can Play Robots

👍 115

09/09 08:00

Foundation vision-language models (VLMs) exhibit broad intelligence about the world, yet translating this intelligence into robot control remains challenging. We present Show-Harness, an Embodied Harness that enables VLMs to "play" robots through a compact semantic interface linking intent to action

Programmable World Model

👍 76

09/09 08:00

Recent video world models generate increasingly realistic and interactive visual experiences, yet lack reliable mechanisms for maintaining persistent world state and enforcing programmable rules over extended interactions. We introduce Programmable World Model, a framework that decouples world-state

SchemeArena: Factorized Stress Testing of Scheming in LLM Agents

👍 7

09/08 08:00

We study scheming in LLM agents, in which agents covertly pursue misaligned goals. Our focus is to understand how scheming arises from the interaction of key factors, such as instrumental goals, environmental affordances, oversight conditions, and perceived consequences. Prior work examines only a s

StochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean

👍 6

09/08 08:00

Leading benchmarks for formal theorem proving with large language models are small collections drawn from competition math, such as the IMO and Putnam, that poorly represent field-specific applications. We introduce StochBench, a Lean 4 benchmark of 450 graduate stochastic-processes problems at vary

AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems

👍 78

09/08 08:00

Large language model (LLM)-based multi-agent systems (MAS) achieve strong performance by employing specialized multiple agents, yet their performance depends on the prompt design of each agent. For MAS prompt optimization, textual gradient methods that guide prompt updates using natural-language fee

PlannerForge: LLM Agents for Scenario-Based Testing of Motion Planners in Autonomous Driving

👍 1

09/08 08:00

Ensuring the safety of autonomous driving is a critical challenge. Scenario-based testing is a systematic process used to validate Autonomous Driving Systems (ADSs), but it remains a fragmented modular pipeline in which scenario generation, retrieval, modification, ADS execution, and results analysi

SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents

👍 19

09/08 08:00

SWE-Bench Pro has emerged as a standard benchmark for evaluating software engineering agents on challenging repository-level tasks. However, our analysis work show that its evaluation is undermined by two sources of unreliability: reward hacking, enabled by leakage of gold solutions or hidden evalua

SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators

👍 11

09/08 08:00

World models are increasingly used as policy-in-the-loop imagination environments, where reliable rollouts require fine-grained controllability with respect to low-level robot actions. A key obstacle to scaling such models in robotics is that actions are not a universal language in pixel space: chan

SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?

👍 16

09/08 08:00

While research on recursive self-improvement (RSI) has predominantly automated model training pipelines, reliable autonomous development demands a missing pillar: post-hoc monitoring and auditing to understand what models learn and ensure safe alignment. Mechanistic interpretability tools are essent

Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails

👍 4

09/08 08:00

Agent harnesses (the system prompt, tool set, execution hooks, and context-management scaffolding around a model) are a critical determinant of agentic task success. Automated harness evolution can enable smaller models to perform well on domain-specific tasks at a fraction of frontier-model cost. S

Difficulty-Adaptive Tree-Structured Policy Optimization for Expanding Reasoning Coverage in RLVR

👍 2

09/08 08:00

Reinforcement Learning with Verifiable Rewards (RLVR) has been central to the recent success of Large Reasoning Models. However, while RLVR significantly improves single-sample accuracy, it often fails to expand the model's intrinsic reasoning coverage (pass@k) due to limited exploration during trai

Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents

👍 15

09/07 08:00

AI research agents combine prior knowledge, public sources, and experimental feedback to produce useful results. The Discovery Certification Protocol (DCP) turns claims about these results into executable recovery and feedback tests. Gate 1 validates useful improvement on sealed evaluation. Gate 2 g

Revisiting Complete Reasoning Traces for Post-Training

👍 8

09/07 08:00

Large language models (LLMs) are often post-trained on pre-collected reasoning trajectories to improve their reasoning capability. Such trajectories tend to be long due to complex, interwoven paths, which often include detours on the path toward the answer. However, it has been underexplored whether

PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents

👍 4

09/06 08:00

Sequential memory agents process long documents by reading chunks one after another while maintaining a compact memory state, coupling document traversal to reasoning depth. This coupling introduces sensitivity to evidence placement and ties inference latency linearly to document length. We introduc

OracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super Resolution

👍 4

09/06 08:00

Recursive Super-Resolution (SR) extends fixed-scale SR to extreme magnification by repeatedly feeding predictions back into the same model, analogous to zooming an image repeatedly. However, ground truth availability at every scale, especially at depth, remains challenging as the required source res

DianShi-RxnDB: A Large-Scale, Fine-Grained Organic Reaction Data Platform Built via a Fully Automated Pipeline for Researchers and AI Agents

👍 9

09/06 08:00

High-quality structured organic reaction data are essential for developing artificial intelligence for chemistry (AI4Chem), yet much of this knowledge remains dispersed across patent text, images, and reaction schemes. We present DianShi-RxnDB, a large-scale, fine-grained organic reaction data platf

Diffs vs. Whole Files: An Empirical Comparison of Iterative Edit-Based and Direct Generation for Flutter/Dart Code Models

👍 4

09/05 08:00

Large language models used for code editing can be trained and deployed in at least two output regimes: direct generation, where the model emits the entire modified file in one shot, and iterative diff-based generation ("steps"), where the model emits a sequence of localized search/replace edits app

VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification

👍 30

09/05 08:00

Multimodal Large Language Models (MLLMs) perform strongly on general visual understanding tasks such as visual question answering, yet they often struggle with a basic comparative skill: identifying what has changed between two similar images. We introduce VDiff-Bench, a challenging multiple-choice

WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data

👍 28

09/04 08:00

Recent advances in wearable sensing enable continuous monitoring of physiological and behavioral signals, yet existing benchmarks rarely evaluate whether AI systems can reason over a real user's longitudinal wearable record. We introduce WearableQA, a benchmark comprising 4,084 10-option multiple-ch

RenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitives

👍 2

09/04 08:00

We present 'RenderFormer-V2', a unified learned transformer-based neural rendering model, complementary to modern physics-based rendering systems, that can handle diverse light-transport effects such as caustics, volumetric scattering, environment lighting, textured and displaced surfaces and out-of

EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness?

👍 5

09/03 08:00

Modern LLM-based agents operate through a harness of tools, reusable skills, and specialist agents that shapes what they observe and what they can do. In practice, this harness continually evolves as new capabilities are added. We introduce EVOHARNESSBENCH, a benchmark for evaluating agents under co

From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution

👍 2

09/02 08:00

Training data attribution (TDA) aims to identify training examples that shape model behavior, but its intervention value depends on both which examples are selected and how they are modified. Influence functions (IF) estimate behavioral changes under infinitesimal reweighting, yet IF-selected exampl

MasterControl Seventeen Every Time

👍 1

09/02 08:00

We study a governed approach to enterprise analytics: a language model interprets the question, while deterministic policy selects and runs a pre-approved analytical program that returns both results and evidence. We show that this restriction can remain expressive within a defined analytical class,

AgenticGen: Reward-Guided Agentic Video Generation for Advertising

👍 7

08/31 08:00

Advertising video generation is not only a video synthesis task, but also a product-conditioned reasoning problem whose success is measured by online business metrics. Recent video foundation models can generate realistic clips from multimodal conditions, yet they do not optimize how a product shoul

A Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware

👍 5

08/12 08:00

AI-powered search products such as ChatGPT search, Google's AI Overviews, and Perplexity provide LLM-synthesized answers grounded in live web results. We developed OreoLook (formerly lixSearch), an open-source answer engine using automated browser agents and provider-routed LLM inference. Its local

10 Ways People Are Making Money With GPT-6 Astra

@sairahul1 · 143.5K 粉丝 · 1.5M 阅 · 561 赞 · 53 转

09/09 18:08

Someone gave GPT-6 Astra $52. 13 hours later: $11,345.95. Someone else gave it $43.47 and one instruction. It turned that into $41,495 overnight. Someone went to sleep. Woke up to $200 in their

中文介绍 分享使用GPT-6 Astra赚钱的10种方式，包括案例分享和收益展示。

What Happens When AI Starts Improving AI?

@apexin_ai · 395 粉丝 · 281.6K 阅 · 500 赞 · 84 转

09/08 12:23

Astra shows how far AI has come. What takes it further? The continued progress of today’s most capable models depends on smarter decisions before training, better strategies during training, and more

中文介绍 探讨AI提升AI能力的进展，强调训练前、训练中、训练后的决策和策略。

How to use ChatGPT Astra for UGC so well it feels illegal

@lucaspatiri_ · 5.8K 粉丝 · 275.5K 阅 · 506 赞 · 41 转

09/09 00:12

openai shipped its most capable model on september 3. i wasn't going to write this. we've generated 2.6 billion organic views across 62 campaigns, managed 590 creators, and produced 22,504 tracked

中文介绍 介绍如何利用ChatGPT Astra进行UGC，实现非法般的效果，分享成功案例。

From GPT-5.6 Sol to GPT-6 Astra: Why Am I Repeating Myself?

@BradGroux · 6.6K 粉丝 · 229.0K 阅 · 561 赞 · 118 转

09/10 06:47

I've been using GPT-6 Astra with the workflow I developed around GPT-5.6: documented task scope, repository context, standard operating procedures, and verification before delivery. In my testing,

中文介绍 对比GPT-5.6 Sol和GPT-6 Astra，分享个人使用GPT-6 Astra的体验和工作流程。

How to design brand mascots with AI (krea). No experience needed

@semochkin_alex · 1.5K 粉丝 · 191.5K 阅 · 507 赞 · 44 转

09/09 20:34

Hi, I'm Alex, cofounder at @relate_studio. In this tutorial, I'll walk you through how we design brand mascots with AI: finding first concepts in Krea, refining the best direction in Nano Banana 2,

中文介绍 教程：使用AI设计品牌吉祥物，无需经验，分享设计流程。

Pushing Local AI Forward

@MiaAI_lab · 27.4K 粉丝 · 180.6K 阅 · 505 赞 · 58 转

09/09 21:45

For the past three months I’ve been building and shipping local AI recipes, mostly for NVIDIA DGX Spark systems. What started as a personal project has grown far beyond what I expected. My GitHub

中文介绍 分享个人构建和发布本地AI食谱的经历，展示项目成长过程。

Reducing cost and improving performance with Claude Platform

@ClaudeDevs · 683.4K 粉丝 · 106.4K 阅 · 1.3K 赞 · 70 转

09/09 01:01

Tuning prompt caching, instructions, and effort can reduce Claude's cost without sacrificing application performance. Performance and cost are often viewed as a trade-off: to spend less, you accept

中文介绍 介绍如何通过调整提示、指令和努力来降低Claude的成本，同时保持应用性能。

How to Use GPT-6 Astra to Find Profitable Trading Strategies 24/7

@RohOnChain · 68.8K 粉丝 · 102.3K 阅 · 524 赞 · 48 转

09/08 20:39

I will break down exactly how to build an AI agent like hedge funds that finds profitable trading strategies from the markets 24/7 with GPT-6 Astra. Let's get straight to it. Bookmark This - I'm

中文介绍 教程：使用GPT-6 Astra构建24/7寻找有利可图交易策略的AI代理。

Personal statement on joining the OpenAI board

@paulfchristiano · 5.3K 粉丝 · 70.7K 阅 · 654 赞 · 96 转

09/10 01:05

I am excited to be joining the OpenAI nonprofit board, serving on the Safety and Security Committee to support safety oversight. Based on the recent trajectory of capabilities and the continued

中文介绍 保罗·克里斯蒂亚诺加入OpenAI董事会，关注安全和安全委员会。

Exactly how I edit videos with Astra

@ForwardEditor · 10.0K 粉丝 · 61.4K 阅 · 512 赞 · 36 转

09/08 08:54

This weekend, I watched a movie with my daughter while my computer worked on a video I would have normally spent most of a day editing. The video was a favor for someone in my personal life. I'm a

中文介绍 分享使用Astra编辑视频的技巧，实现高效视频制作。

LLM-as-Judge Architectures: Putting Evals Into Your Agent Runtime

@JoshARosen · 1.3K 粉丝 · 47.0K 阅 · 510 赞 · 49 转

09/08 22:00

LLM-as-judge is already a common part of building AI applications. Run your application against a dataset, have another model grade the results, and use the scores to figure out whether the latest

中文介绍 介绍LLM-as-judge架构，如何在AI应用中实现评估。

Software Engineer to AI Engineer: Best Move 2026

@TechWithTimm · 16.2K 粉丝 · 40.2K 阅 · 506 赞 · 79 转

09/09 22:57

A lot of software engineers see AI engineering as a completely different career. But it’s not. I have a friend who works as an AI engineer and makes around $200,000 to $300,000 a year. When I asked

中文介绍 探讨软件工程师转向AI工程师的趋势，分享同行收入案例。

AlphaGenome Atlas: A High-Resolution Map of Human DNA Accelerating Biological Discovery

@GoogleAI · 2.5M 粉丝 · 37.4K 阅 · 643 赞 · 90 转

09/08 22:41

Today, we’re introducing AlphaGenome Atlas 🧬 an interactive platform for genomics discovery. In 2025, @GoogleDeepMind released AlphaGenome to help decode the complex language of our DNA — but

中文介绍 介绍AlphaGenome Atlas，一个用于基因组发现的交互式平台。

My Son Had Six Weeks to Learn Two Years of Saxon Math. We Used AI.

@DataRepublican · 957.2K 粉丝 · 37.3K 阅 · 846 赞 · 155 转

09/10 10:21

NYC and LA are restricting student AI. We used it to expose what school missed—and repair two years of gaps in six weeks. Part 1 of 3 in a series. Between my husband and I, three of our parents were

中文介绍 分享使用AI帮助儿子在六周内学习两年数学的经历。

The Complete Guide to pstack Pt. 2

@poteto · 92.6K 粉丝 · 23.3K 阅 · 822 赞 · 60 转

09/10 01:02

In my last post, I showed you why verification is the foundation of everything I do with agents, and how to get started creating your own verification skills. The key lesson was that if an agent can't

中文介绍 教程：pstack完全指南第二部分，强调验证是构建代理的基础。

The Physical World Does Not Hand You a State Vector

@jhMITgunship · 1.5K 粉丝 · 18.3K 阅 · 1.4K 赞 · 1 转

09/09 01:23

What superintelligence needs to operate in the physical world For much of the work we give models from OpenAI, Anthropic and the other frontier labs, the world has already been turned into context.

中文介绍 探讨超智能在物理世界操作的需求，强调将世界转化为上下文的重要性。

Alaya AI: Mastering Multimodal Sensor Synchronization for Next-Gen Autonomous Systems

@Alaya_AI · 321.1K 粉丝 · 10.6K 阅 · 504 赞 · 450 转

09/10 18:15

As autonomous vehicles, robotics, and spatial computing platforms evolve, AI model training is shifting away from isolated 2D image annotation toward complex multimodal sensor fusion. Today’s frontier

中文介绍 介绍Alaya AI在多模态传感器同步方面的进展，为下一代自主系统奠定基础。

How a researcher uses Codex and ChatGPT to search for new antimicrobial molecules

OpenAI News · 09/11 00:00

César de la Fuente’s lab uses Codex and ChatGPT to search living and extinct genomes for antimicrobial candidates to fight drug-resistant infections.

中文介绍 César de la Fuente的实验室利用Codex和ChatGPT在生活与灭绝生物的基因组中寻找抗微生物候选分子，以对抗耐药感染。

Now everyone can put data to work

OpenAI News · 09/10 23:00

Meet the Data agent in ChatGPT Work. Connect company data, uncover insights, and build interactive dashboards with AI using natural language.

中文介绍 ChatGPT Work推出数据代理功能，可连接公司数据，用自然语言挖掘洞察力并构建交互式仪表板。

Powering AI is an architecture problem

MIT Tech Review AI · 09/10 19:00

On July 22, 2026, a transmission line fault in Ashburn, Virginia—the heart of the world’s largest data center cluster—knocked more than 3 gigawatts of load off the grid in seconds. And it wasn’t the first time. Two years earlier, a single failed surge arrester dropped roughly 60 Virginia facilities

中文介绍 弗吉尼亚阿什本地区一次传输线故障导致3GW负荷瞬间断电，再次突显了为AI供电的架构问题。

Introducing ChatGPT for Financial Services

OpenAI News · 09/10 15:00

Introducing ChatGPT for Financial Services, combining built-in financial data and GPT-6 Astra for research, modeling, and client-ready materials.

中文介绍 OpenAI推出针对金融服务领域的ChatGPT，结合内置金融数据和GPT-6 Astra进行研究和建模。

Expanding AI access and cyber defense for federal, state, local, and tribal governments

OpenAI News · 09/10 15:00

OpenAI and GSA will offer eligible federal, state, local, and tribal governments $0 license fees, 50% off usage, and expanded cyber defense support.

中文介绍 OpenAI与GSA合作，为符合条件的政府机构提供免费许可、50%使用费折扣和扩展的网络安全支持。

[AINews] not much happened today

Latent Space · 09/10 11:33

a quiet day

中文介绍 今日AI领域平静无大新闻。

Introducing the Agents API

OpenAI News · 09/10 08:00

Build and launch cloud agents with the Agents API, a managed service powered by the Codex harness for orchestration, long-running sessions, and tool use.

中文介绍 OpenAI推出Agents API，可通过Codex harness构建和部署云代理。

Build more natural voice experiences with GPT‑Live‑1 in the API

OpenAI News · 09/10 08:00

GPT‑Live‑1 brings natural, full-duplex voice conversations to the API, with stronger instruction following, custom voices, and telephony support.

中文介绍 GPT-Live-1 API提供自然、全双工语音对话，增强指令遵循、定制声音和电话支持。

Rebuilding AUTOMATIC1111 with Gradio Workflow

Hugging Face Blog · 09/10 08:00

中文介绍 使用Gradio Workflow重建AUTOMATIC1111。

DeepSeek Flash v4.1 🤖, Siri AI 📱, Anthropic AI economics 📈

TLDR AI · 09/10 08:00

中文介绍 DeepSeek Flash v4.1、Siri AI和Anthropic AI经济学等AI新闻概述。

Paul Christiano joins OpenAI Foundation Board

OpenAI News · 09/10 01:00

Paul Christiano joins the OpenAI Foundation Board and its Safety and Security Committee, bringing experience in AI alignment, safety, and standards.

中文介绍 Paul Christiano加入OpenAI基金会董事会和安全与标准委员会。

IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license

Hugging Face Blog · 09/09 23:36

中文介绍 IBM发布SOTA Granite Time Series PatchTST-FM-r2模型，具有商业友好型许可。

The AI policy window is open. We need to act.

OpenAI News · 09/09 21:00

Chris Lehane argues that stronger AI capabilities require stronger safety evidence, shared standards, and durable policy action while the policy window remains open.

中文介绍 Chris Lehane认为，在政策窗口期，需要更强大的安全证据、共享标准和持久政策行动。

GPT-6 Astra: The next generation in intelligence for work

OpenAI News · 09/09 19:00

Meet GPT-6 Astra, OpenAI’s most capable model for business, with advanced reasoning, computer use, and stronger writing and design judgment.

中文介绍 GPT-6 Astra是OpenAI最强大的企业级模型，具有高级推理、计算机使用能力，以及更强的写作和设计判断。

[AINews] OpenAI reports Navier-Stokes singularity find in 88 hours using Astra-next, roughly 10,000 agents and 130B tokens (>$40M), a contender for second ever Millennium Prize awarded

Latent Space · 09/09 13:04

Overshadowing Cognition's $48B Series E, Mistral's $24B Series D, Meta's Muse agent, and GPT Image 2.5. The most jam packed, feel the AGI day in the history of AI.

中文介绍 OpenAI使用Astra-next在88小时内报告发现Navier-Stokes奇点，使用约10,000个代理和1300亿个标记（价值超过4000万美元），是第二个千禧年奖的有力竞争者。