HuggingFace
Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules
Coding agents such as Claude Code also follow text files that developers write for them: a project file, skills the a...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation
Diffusion language models (DLMs) offer parallel sampling for faster generation than autoregressive models, an increas...
HuggingFace
Drive3R: Block-wise Streaming Geometric Foundation Models for Autonomous Driving
High-fidelity closed-loop simulation for autonomous driving increasingly relies on dense multi-view 3D reconstruction...
HuggingFace
PreciseCoder: Faithful and Generalizable Debugging Beyond Unit-Test Rewards
Reinforcement learning (RL) from unit tests is the common recipe for post-training code models, but a unit test only ...
HuggingFace
When Left Is Right? Camera-Motion Understanding beyond Screen
Can a vision-language model tell left from right? Modern VLMs solve visual puzzles and follow hour-long videos, yet w...
HuggingFace
Looking Complete Is Not Being Grounded: Evaluating LLM Sitreps Against Human-Authored Situation Reports
Evaluation for automatic crisis reporting should measure what practitioners need, not what is convenient to compare. ...
HuggingFace
Lluna: Collaborative Unimodal Models for Missing-Modality Inference
Pretrained unimodal models offer a flexible route to multimodal prediction through collaboration, but this collaborat...
HuggingFace
Unlocking Structured Pruning for Reasoning Language Models via Attention-Preserving MLP Trimming
Structured pruning reduces LLM inference costs by removing model components to produce smaller dense models. However,...
HuggingFace
FreeSolo: Linear-time Sparse Attention with Zero-Shot Length Extrapolation
Linear-time sequence models typically store long-context information in a recurrent state. A fixed-size state limits ...
HuggingFace
Speculative Sampling in Interactive Video Generation
Interactive video generation commonly relies on small bidirectional chunks to reduce response latency. Yet our prelim...
HuggingFace
CoTranslator: Reverse to Forward Chain-of-Thought Translator for Reasoning Distillation
Reasoning distillation requires chain-of-thought (CoT) data with correct answers, but obtaining such data efficiently...
arXiv
PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis
Multimodal code intelligence connects the symbolic world of programs with the visual world their execution creates. I...