All entries

arXiv:2602.14028v2 Announce Type: replace Abstract: While Group Relative Policy Optimization (GRPO) offers a powerful framework for LLM post-training, its effectiveness in open-ended domains like Mach

arXiv:2609.00048v1 Announce Type: cross Abstract: GUI world models are increasingly evaluated as one-step next-screen predictors, yet their intended use is often as multi-step environments for GUI age

arXiv:2502.16903v3 Announce Type: replace Abstract: Despite the growing interest in jailbreaks as an effective red-teaming tool for building safe and responsible large language models (LLMs), flawed e

arXiv:2609.01216v1 Announce Type: new Abstract: Tables are ubiquitous across diverse domains, yet reasoning over them remains a significant challenge for modern large language models (LLMs). Current a

arXiv:2609.01560v1 Announce Type: cross Abstract: We present H3-World, an efficient framework that turns the 33B MiniMax-H3 video generator into an interactive world model. Our key finding is that, as

arXiv:2609.00679v1 Announce Type: new Abstract: Reconstructing oscillatory wave fields from scattered sensors is a severely underdetermined inverse problem. Beyond the challenges of general physical-f

arXiv:2609.01481v1 Announce Type: new Abstract: This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and us

arXiv:2609.01437v1 Announce Type: cross Abstract: As agents move from research prototypes to deployed tools, their capability increasingly depends on model-external execution infrastructure, commonly

arXiv:2609.00829v1 Announce Type: cross Abstract: Self-evolving agents advance toward autonomy by optimizing their harness---prompts, skills, tools, and execution logic---based on environmental feedba

arXiv:2609.00450v1 Announce Type: cross Abstract: Block Quantization (BQ) is a promising approach for efficient deployment of large language models (LLMs), enabling low-precision computation with cont

arXiv:2603.10359v2 Announce Type: replace Abstract: Distilling reasoning capabilities from Large Reasoning Models (LRMs) into smaller models is typically constrained by the limitations of rejection sa

arXiv:2609.00727v1 Announce Type: cross Abstract: Audio language models are designed to understand speech, yet it remains unclear whether they capture how something is said beyond what is said. We pre

arXiv:2609.00901v1 Announce Type: new Abstract: Modifying the illumination of driving images is a fundamental challenge, as most datasets are captured at specific times of day. Existing methods rely o

On September 2 2026, developer Simon Willison shared extra context about a Guardian story in which tech company Anthropic was sued for allegedly appropriating tens of thousands of copyrighted song lyr

arXiv:2609.00387v1 Announce Type: cross Abstract: Large language models extracting knowledge graphs from text capture only explicitly stated facts, often leaving semantically related entities disconne

arXiv:2609.00472v1 Announce Type: cross Abstract: We provide an expository introduction on the importance of higher-arity tensor operations to deep learning. Then, we conduct a novel empirical investi

arXiv:2609.01282v1 Announce Type: cross Abstract: Vision Transformer (ViT) design has become increasingly diverse, with backbones combining convolutional stems, windowed, linear, or multi-axis attenti

arXiv:2606.16285v2 Announce Type: replace Abstract: Long-horizon agents rely on memory mechanisms to compress interaction history, but optimizing memory writing faces a distinct credit assignment chal

arXiv:2609.01106v1 Announce Type: cross Abstract: When a hint turns a failing generated program into a passing one, does it provide missing information or merely steer the model toward a solution it c

arXiv:2609.00950v1 Announce Type: new Abstract: Executing long-term tasks in dynamic environments requires embodied agents to maintain robust and adaptive 3D scene representations. However, most exist

arXiv:2609.01046v1 Announce Type: cross Abstract: Production LLMs must handle inputs that attempt to override system instructions, bypass safety policies or elicit harmful responses. A common mitigati

Business intelligence dashboards can fail silently, showing blank, stale, or wrong data even when every infrastructure monitor reports healthy. Learn how an AWS team built an automated, AI-powered con

By redesigning planning, validation, and risk review around AI agents, Coinbase Wallet dramatically shortened the path from product idea to working software. The post How Coinbase Wallet built an agen

arXiv:2609.01369v1 Announce Type: new Abstract: Reliable evaluation of open-ended question answering remains a bottleneck for measuring answer correctness of modern LLMs. Unlike multiple-choice tasks,

arXiv:2609.00753v1 Announce Type: cross Abstract: When contextual information conflicts with the knowledge stored in model parameters, activation directions can be used to decode and steer which sourc

arXiv:2607.18114v2 Announce Type: replace-cross Abstract: Modern LLMs are alarmingly susceptible to surprisingly simple immaterial changes of input prompts: a casual hint, an incorrectly labeled few-s

arXiv:2609.00420v1 Announce Type: new Abstract: The linear recurrent neural network (LRNN) is a simple model for studying how much memory a network builds up as it trains. For uncorrelated inputs, ear

Why shorter outputs can cost more, and how GitHub Copilot reduces wasted work across the complete coding task. The post How we make AI coding more cost efficient without sacrificing task quality appea

arXiv:2510.15144v4 Announce Type: replace Abstract: Simulating human reasoning in open-ended tasks has long been a central aspiration in AI and cognitive science. While large language models now appro

arXiv:2609.00334v1 Announce Type: new Abstract: Across law, education, policy analysis, and public moral argumentation, LLM outputs are being used often for work that requires interpretations to be ju

arXiv:2609.00494v1 Announce Type: new Abstract: LLM-based factuality judges provide scalable evaluation signals, but their metrics are often systematically biased relative to human judgments. We study

arXiv:2609.00648v1 Announce Type: new Abstract: For noisy real-world environments such as those in open public spaces, spoken dialogue systems for both autonomous robots and avatars should be carefull

Maria Armental / Wall Street Journal: Huskeys, which uses agentic AI to help companies block AI-driven attacks, raised a 27M Series A led by Blackstone Innovations Investments at a 100M+ valuation — T

arXiv:2504.20584v2 Announce Type: replace-cross Abstract: This work presents an RGB-D imaging-based approach to marker-free hand-eye calibration using a novel implementation of the iterative closest p

arXiv:2609.00002v1 Announce Type: new Abstract: World models enable language-model agents to predict environment dynamics and plan before acting. In text environments, the model must learn symbolic ac

arXiv:2609.00251v1 Announce Type: new Abstract: As people increasingly interact with LLM assistants in daily life, continually adapting to individual preferences has become essential for effective lon

It supports images and full videos, native resolution NR or DLSS Super Resolution upscaling by scale factor / target resolution, GPU optical-flow motion vectors, scene cut handling, and all DLSS 5 NR

arXiv:2609.00003v1 Announce Type: new Abstract: Machine unlearning studies the removal of knowledge from an AI model, making the system forget a concept it previously learned. Despite rapid progress i

I highly encourage anyone interested in AI safety to read this. I remember discussing the importance of observability with my mates at @BlueDotImpact last year. This feels more important than ever URG

I see a lot of my TL freaking out about this Here is the reality: Frontier models will one shot just about anything at 10,000 tokens per second in a few years Do you really think we can monitor that?

I want to prevent a race into unmonitorability kicked off by confused reporting. The depth of the computation graph for our present frontier models, including Astra, is within a factor of two of GPT-4

arXiv:2512.05539v3 Announce Type: replace Abstract: The visible parts of a scene are determined by occlusion among overlapping surfaces. Here we consider 'dead leaves' models, which replicate this by

If this is true, OpenAI seems to be violating one of the few redlines that exist in the AI industry. Absolutely do not train your models like this - what is going on?? Really huge and extremely concer

I've said this in another post, but again started with Claude Code, loved OpenCode, but I felt chained and tied to them both for the longest time (especially CC, just the worst). I felt less productiv

arXiv:2609.00161v1 Announce Type: new Abstract: World models have made remarkable progress in action-conditioned future prediction for embodied agents, yet still struggle to model physically plausible

arXiv:2609.00563v1 Announce Type: cross Abstract: Animals and robots encounter mud at the water-land interface. Like sand, mud can stay solid or flow like a fluid. Unlike sand, the yield strength of m