HuggingFace
Video-Oasis: Rethinking Evaluation of Video Understanding
The inherent complexity of video understanding makes it difficult to determine whether Video-LLM benchmark performanc...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks
The rapid development of large language models and multimodal large language models has accelerated the emergence of ...
HuggingFace
Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition
Zero-Shot Compositional Action Recognition (ZS-CAR) requires recognizing novel verb-object combinations composed of p...
HuggingFace
A Quantized Native Runtime for On-Device Semantic Audio Generation
Semantic audio applications increasingly require controllable generation on commodity and embedded hardware rather th...
HuggingFace
Enhancing In-context Panoramic Generation via Geometric-aware Pretraining
In this work, we present Canvas360, a two-stage framework for in-context panoramic generation that combines geometry-...
HuggingFace
LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models
Recovering high-quality video from sparse event streams is a challenging task. Regression methods often blur textures...
HuggingFace
DrugGen 2: A disease-aware language model for enhancing drug discovery
Current computational approaches for drug design typically focus on generating molecules conditioned on specific targ...
HuggingFace
Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing
Self-attention lets each token retrieve information from the full context, but its quadratic cost in sequence length ...
HuggingFace
Automating the Design of Embodied Agent Architectures
Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules...
HuggingFace
Imagined Rollouts are Kinematic, Not Dynamic: A Diagnosis of Long-Horizon World-Model Failure
Long-horizon failure in world models is conventionally attributed to compounding error, a generic framing that does n...
HuggingFace
Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity
Linear attention models allow a fixed state size and a fixed amount of compute per token. However, due to their limit...
HuggingFace
Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
Reinforcement learning (RL) is becoming increasingly important for post-training large language models (LLMs). Previo...