arXiv
AI-Driven Reproducibility and Analytical Robustness in Scientific Discovery
Reproducible and analytically robust research findings are essential to scientific progress, but evaluating these pro...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Behavioral Couplings: From Formation to Behavioral Emergence in Language Models
Fine-tuning large language models (LLMs) can induce behaviors beyond those explicitly targeted. For example, training...
arXiv
Rethinking the design space of Vanilla Pixel Diffusion Transformers
Pixel-space diffusion models have recently re-emerged as a compelling alternative to latent diffusion, avoiding the l...
HuggingFace
PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews
Peer review is under strain from the growth of submissions, and review comments written by humans or AI can misstate ...
HuggingFace
Stuck on Shuffle: On Attribute-Object Binding in Vision-Language Models
Retrieval is a fundamental task in multimodal systems: given an image or text query, the goal is to find the most rel...
HuggingFace
BridgeWAM: Bridging Video and Action Experts via Latent Bridge Queries
World Action Models (WAMs) commonly couple video and action experts through dense, layer-wise Mixture-of-Transformers...
HuggingFace
MorphAct: Robot Policies Morphing with the Worlds They Act In
Progress toward general intelligence in the physical world requires scaling robot learning across diverse environment...
HuggingFace
FC-SWE: Failure-Conditioned RL for Long-Horizon Software Engineering Agents
Repository-level software engineering (SWE) is a challenging long-horizon setting: agents must reason over extended i...
HuggingFace
SciΠvot: Benchmarking Principal-Investigator Judgment at Pivotal Moments of Scientific AutoResearch Agents
Large language model (LLM) agents can keep scientific experiments running for months with little human supervision, b...
HuggingFace
OfficeTown: Generative Organizations for Evolving Agent Intelligence
AI agents increasingly use files and software tools to produce professional deliverables. Such work draws on material...
HuggingFace
Dream2Discern: Learning from Hard Latent Variants for Runtime Failure Prediction in Multi-Agent Systems
Reliable deployment of LLM-based multi-agent systems calls for runtime auditors that predict terminal outcomes from o...
HuggingFace
Learning to Think and Explore in 3D World
We study how vision-language models (VLMs) can learn to think and actively explore in 3D space. Instead of providing ...