HuggingFace
Training Open Models for Agentic Phone Use
Phones are becoming an important execution surface for general-purpose agents, but training open models for reliable ...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents
While recent LLM-based terminal agents have demonstrated promising capabilities, the scarcity of high-quality, execut...
HuggingFace
Unlimited OCR Works
Recently, end-to-end OCR models, exemplified by DeepSeek OCR, have once again thrust OCR into the spotlight. A widely...
HuggingFace
FastMix: Fast Data Mixture Optimization via Gradient Descent
While large and diverse datasets have driven recent advances in large models, identifying the optimal data mixture fo...
HuggingFace
Tapered Language Models
Modern language models, including transformer, recurrent, and memory-based variants, share a common chassis: a stack ...
HuggingFace
UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation
Vision Transformers (ViT) dominate computer vision. However, their reliance on rigid patch projectors hinders transfe...
HuggingFace
Tmax: A simple recipe for terminal agents
Terminal-using agents have quickly become the most popular downstream application of language models (LMs). Despite t...
HuggingFace
DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams
Massive unstructured multimodal streams suffer from high "data entropy," impeding both efficient human knowledge acqu...
HuggingFace
HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions
With the rapid spread of retrieval-augmented generation and semantic search, choosing the right embedding and retriev...
HuggingFace
MeshFlow: Mesh Generation with Equivariant Flow Matching
Meshes are among the most common 3D scene representations, but directly generating meshes is challenging because the ...
HuggingFace
Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents
Long-horizon tasks are common in real-world robotic deployments, yet failure detection for such tasks remains underex...
HuggingFace
Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding
Autoregressive generation in large language models (LLMs) conventionally decodes from the final layer, assuming that ...