DINO-MX: A Modular & Flexible Framework for Self-Supervised Learning
"训练框架" 相关文章
When Models Outthink Their Safety: Mitigating Self-Jailbreak in Large Reasoning Models with Chain-of-Guardrails
UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction-as-Reasoning
MUG-V 10B: High-efficiency Training Pipeline for Large Video Generation Models
DMRetriever: A Family of Models for Improved Text Retrieval in Disaster Management
CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions
RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning
Multimodal Policy Internalization for Conversational Agents
Multimodal Policy Internalization for Conversational Agents
Multimodal Policy Internalization for Conversational Agents
Localist LLMs -- A Mathematical Framework for Dynamic Locality Control
Learning without Global Backpropagation via Synergistic Information Distillation
ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference
Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation
Towards Strategic Persuasion with Language Models
SABR: A Stable Adaptive Bitrate Framework Using Behavior Cloning Pretraining and Reinforcement Learning Fine-Tuning
GraSP: A Unified Graph-Based Framework for Scalable Generation, Quality Tagging, and Management of Synthetic Data for SFT and DPO
Multi-Plasticity Synergy with Adaptive Mechanism Assignment for Training Spiking Neural Networks
WeChat-YATT: A Simple, Scalable and Balanced RLHF Trainer
VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
