HuggingFace
On-Policy Self-Distillation in Diffusion Models
Reinforcement learning can align diffusion models with human preferences and task-specific objectives, but endpoint r...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces
LLM agents remain unreliable on long-horizon tasks, where small local failures can compound over extended interaction...
HuggingFace
On-policy Distillation with Verifiable Reward
Reinforcement Learning with Verifiable Rewards (RLVR) and on-policy distillation (OPD) have become two widely adopted...
HuggingFace
Best Practice Critic Optimization
Group-based reinforcement learning methods such as GRPO for large language models avoid training a critic by sampling...
HuggingFace
Length-Adaptive Decoding for Masked Diffusion Machine Translation
Machine translation tests masked diffusion language models (dLLMs) because every source token must be rendered faithf...
HuggingFace
TorchMorph: CUDA-accelerated Morphological Transforms
Morphological transforms are long-standing tools for shape and mask processing, but the de facto reference implementa...
HuggingFace
WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report
Universal multimodal embeddings are becoming a core component of modern AI systems, enabling heterogeneous content to...
HuggingFace
LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training
We present LAION-BVD, a large-scale open video dataset for multimodal learning, which contains 1.3B platform-specific...
HuggingFace
From Seeing to Acting: Smart Glasses as First-Person Intelligence Platforms
Smart glasses are evolving from capture and display accessories into first-person intelligence platforms that connect...
HuggingFace
Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs
Multimodal large language models (MLLMs) have become a prevailing paradigm for unified video perception. However, pos...
HuggingFace
Game2World Engine: Unlocking In-the-Wild Gameplay Videos for World Model Training
Video games provide a scalable source of training data for video world models, offering diverse environments, complex...
HuggingFace
CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild
As large language models (LLMs) continue to advance in coding capabilities, their potential in cybersecurity has draw...