DAPD: Dual-Anchored Policy Distillation
Paper • 2608.01735 • Published • 158
山下颯太
thomas-taylor
AI & ML interests
None yet
Recent Activity
liked a model 12 days ago
TokenRhythm/NeoHorse-1-9B liked a model 14 days ago
Navin-Models/Qwen3.8-Flash-Next-Uncensored-AD-4.27-GGUF liked a model 14 days ago
TokenRhythm/NeoHorse-1-4BOrganizations
None yet
upvoted 2
papers about 2 months ago
upvoted 3
papers 2 months ago
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs
Paper • 2607.17423 • Published • 98
Latent-Identity Tuning in Text-to-Image Personalization Models
Paper • 2607.11885 • Published • 8
ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation
Paper • 2607.13124 • Published • 16
upvoted 8
papers 4 months ago
ABot-Earth 0.5: Generative 3D Earth Model
Paper • 2606.09967 • Published • 178
Kwai Keye-VL-2.0 Technical Report
Paper • 2606.10651 • Published • 103
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
Paper • 2605.28816 • Published • 149
DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards
Paper • 2605.21467 • Published • 86
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
Paper • 2605.20025 • Published • 90
Segment Anything with Motion, Geometry, and Semantic Adaptation for Complex Nonlinear Visual Object Tracking
Paper • 2605.22538 • Published • 6
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
Paper • 2605.11609 • Published • 49
Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation
Paper • 2605.11739 • Published • 19
upvoted a paper 5 months ago