HuggingFace
EnvHarness: Awakening Static Worlds for Agent Learning
LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agen...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
WithEveryone: Unified Planning and Identity Grounding for Group Image Generation
Identity-preserving image generation becomes increasingly unreliable when a scene must contain many specified people....
HuggingFace
ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Models
Action-conditioned video world models require low-latency causal generation and reliable responses to game-native con...
HuggingFace
MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use
Memory has become a key component of large language models, enabling them to retain information and learn from long-t...
HuggingFace
4DAnyone: Create Anyone in 4D from a Casual Monocular Video
We present 4DAnyone, a framework for reconstructing 4D humans from an uncalibrated monocular video by generating reco...
HuggingFace
Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization
Large language models often fail to answer questions about a bounded document collection when the source documents ar...
HuggingFace
Repo0: Design-Driven Zero-to-All Code Generation
Large language model agents have made substantial progress in code generation, yet most existing systems assume a pre...
HuggingFace
SkillEvo: Self-Renewing Evolution Gradients from Multi-Turn Interaction Feedback
Agent Skills are today either hand-authored or produced in a single LLM generation pass, and consequently possess no ...
HuggingFace
FlashPrefill V2: Block-Sparse Prefill Attention for Long-Context LLM Serving
Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention re...
HuggingFace
Chain-of-Experience for Continual LLM Improvement
Humans continuously learn from experience, whereas conventional large language model (LLM) evaluations ignore the mod...
HuggingFace
SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?
Software increasingly functions as part of the scientific instrument itself, making failures in scientific code capab...
HuggingFace
Towards Quantifying Benchmark Optimization in ASR Models
Public benchmarks are important measures of Automatic Speech Recognition (ASR) model capabilities. However, by nature...