HuggingFace
Self-Improvements in Modern Agentic Systems: A Survey
Self-improving autonomous agents are moving from research prototypes to deployed systems. The primary goal is control...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World
AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide li...
HuggingFace
AffectFlow-DINO: Uncertainty-Aware Multi-Task Affect Estimation via Conditional Rectified Flow
We present AffectFlow-DINO, a multi-task learning system for the 11th ABAW challenge that extends a standard determin...
HuggingFace
Discrete Diffusion Models: A Unified Framework from Tokenization to Generation
Discrete denoising diffusion models (DDMs) have recently emerged as a compelling alternative to autoregressive (AR) m...
HuggingFace
Self in Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence
Autonomous UAV systems increasingly rely on multimodal large language models (MLLMs) to operate in complex real-world...
HuggingFace
SPEAR: A Simulator for Photorealistic Embodied AI Research
Interactive simulators have become powerful tools for training embodied agents and generating synthetic visual data, ...
HuggingFace
Length Penalties Make Chain-of-Thought Less Monitorable
Length-penalized reinforcement learning can shorten chain-of-thought reasoning while hiding an influence that drives ...
HuggingFace
Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code
Languages with rich static semantics, such as Rust, provide stronger guarantees for AI-generated code, but their stri...
arXiv
AIMO Interpretability Challenge
We propose the AIMO Interpretability Challenge, a competition on distinguishing robust from spurious reasoning in fro...
arXiv
Partially Correlated Verifier Cascades in LLM Harnesses: Concave Log-Odds, Polynomial Reliability, and Blind-Spot Ceilings
Serial verification gates are a core reliability primitive in LLM harnesses: a candidate answer is returned only if $...
arXiv
Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code
Languages with rich static semantics, such as Rust, provide stronger guarantees for AI-generated code, but their stri...
arXiv
A Self-Evolving Agent for Longitudinal Personal Health Management
Personal health management unfolds over repeated encounters, yet most health AI systems treat each request in isolati...