When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation
Paper • 2609.20511 • Published • 109
yurihead
ylzz1997
AI & ML interests
None yet
Recent Activity
liked a model 6 days ago
com-kotobalabs/open-jev-deberta-v3-large liked a model 6 days ago
m-a-p/SheetSage2 upvoted a paper 7 days ago
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy DistillationOrganizations
upvoted a paper 7 days ago
upvoted 3
papers about 1 year ago
FCPE: A Fast Context-based Pitch Estimation Model
Paper • 2509.15140 • Published • 8
VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning
Paper • 2507.22607 • Published • 47
Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy
Paper • 2507.01352 • Published • 61
upvoted 4
papers over 1 year ago
An Empirical Study of GPT-4o Image Generation Capabilities
Paper • 2504.05979 • Published • 64
LightThinker: Thinking Step-by-Step Compression
Paper • 2502.15589 • Published • 31
The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks
Paper • 2502.08235 • Published • 59
Weak-to-Strong Diffusion with Reflection
Paper • 2502.00473 • Published • 24
upvoted an article almost 2 years ago
Article
Fine-tune Llama 2 with DPO
- +1
kashif, ybelkada, lvwerra
• • 70 upvoted a paper about 2 years ago