HuggingFace
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution
Frontier open-weight models are increasingly available, but serving them still largely assumes datacenter infrastruct...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Personalized Auto-Research: Towards a True AI Co-Scientist
AI co-scientists that generate hypotheses, retrieve related work, design experiments, execute code, and draft full pa...
HuggingFace
Unifying Graph Neural Networks Through a Common Layer Equation
Graph neural networks are commonly described through family-specific equations whose notation obscures shared computa...
HuggingFace
HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety
Large language models are increasingly deployed through agent harnesses that manage tools, extensions, persistent sta...
HuggingFace
Agent Lightning v1.0: Towards Harnessed Agentic RL
Modern agents operate inside agent harnesses that manage tools, context, and control flow, making the harness a criti...
HuggingFace
MathForm: Scaling Mathematical Autoformalization with Knowledge Retrieval and Verification-Guided Refinement
Autoformalization is commonly framed as translating natural-language mathematical statements into machine-verifiable ...
HuggingFace
CoinVE-200K: A Large-Scale High-Quality Dataset for Compositional Instruction-Guided Video Editing
The quality and diversity of instruction-based video editing datasets are steadily improving, yet existing datasets m...
HuggingFace
EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing
High-resolution image editing is increasingly demanded in professional workflows, yet existing diffusion-based models...
HuggingFace
Cross-Model Memory Transfer via Target-Side Reader Adaptation
Methods for improving knowledge use in large language models typically fall into two regimes. Non-parametric retrieva...
HuggingFace
Demystifying Agent Skills: Why They Work-Until They Don't
Skills have emerged as a practical and effective approach for enhancing LLM agents at inference time through structur...
HuggingFace
MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding
Vision encoders are a critical component of vision-language models, and scaling their capacity effectively improves p...
HuggingFace
PixRestore: Unified Image Restoration via Pixel Diffusion Transformer
Unified image restoration (UIR) aims to recover high-quality (HQ) content from low-quality (LQ) images with different...