HuggingFace
Joint Subspace Sparse Attention for Efficient Long-Context Decoding
Sparse attention reduces the KV-cache traffic that dominates long-context LLM decoding, but practical methods largely...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
ProbabilityBench: Model Evaluation and Calibration with Exact Ground-Truth Uncertainty
Evaluating model uncertainty on real-world data is challenging because each instance provides only a single observed ...
HuggingFace
RuleTrek: Benchmarking Agentic Rule Reasoning in Complex Scenarios
Large language models (LLMs) increasingly tackle complex real-world tasks in specialized domains. However, identifyin...
HuggingFace
Vela: Scaling Vision-Language-Action Models with Adaptive Action Curve Parametrization
Most vision-language-action models represent future motion as fixed-rate action chunks, tying temporal resolution and...
HuggingFace
AgentSafeEvo: Adversarial Co-Evolution for LLM Agent Safety
Large language model (LLM) agents accomplish complex tasks through multi-turn interactions with external tools. Howev...
HuggingFace
SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm
Recursive self-improvement (RSI) in scientific research aims to improve agents' research capabilities through their o...
HuggingFace
Glance Forcing: Making Bidirectional Diffusion Autoregressive at a Glance
Autoregressive generation underlies real-time, causal video synthesis and is the backbone of video world models. Toda...
HuggingFace
LLM-to-Flow Distillation: Teaching Natural Language Goals to Scientific Generators
Generative discovery in science requires coupling high-level scientific reasoning with the ability to generate sample...
HuggingFace
StreamErase: Towards Ultra-Fast Streaming Video Erasing
Current video object removal methods suffer from prohibitive latency (minutes per video) and non-causal processing th...
HuggingFace
Rethinking LLM-Guided Visual Question Answering: Does Deeper Knowledge Integration Really Help?
Knowledge-based Visual Question Answering (VQA) requires reasoning that extends beyond visible image content, demandi...
HuggingFace
Last Secure Code Benchmark: Is the Code You Vibe Secure?
AI coding agents now write much of the code that ships, yet whether that code is secure remains unclear. We introduce...
HuggingFace
Learning Transferable World-Action Models from Task-Paired Human Videos
World-action models inherit broad visual and physical priors from video pre-training. However, standard within-video ...