ReSPO: Reshaped Sequence Policy Optimization for Gradient Starvation in Off-Policy Learning
Paper • 2609.35433 • Published • 12
董家愷
Snooow1029
·
AI & ML interests
None yet
Recent Activity
updated a model 2 days ago
Snooow1029/hyeyeon published a model 2 days ago
Snooow1029/hyeyeon updated a dataset 8 days ago
Snooow1029/cloak_deltasOrganizations
upvoted 4
papers about 1 month ago
Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards
Paper • 2610.02967 • Published • 30
Rethinking Automated Voice Similarity by Shifting from EER to Embedding Geometry
Paper • 2609.33999 • Published • 6
ReCAST: Reward Credit Assignment across Timesteps for Online Diffusion Reinforcement
Paper • 2609.13425 • Published • 11
upvoted a paper 4 months ago
upvoted an article 8 months ago
Article
Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective
LinkedIn
• • 82 upvoted an article 10 months ago
Article
ChatML vs Harmony: Understanding the new Format from OpenAI 🔍
kuotient
• • 58 upvoted an article 12 months ago
Article
Welcome GPT OSS, the new open-source model family from OpenAI!
- +10
reach-vb, pcuenq, lewtun, clem, Rocketknight1, clefourrier, celinah, Wauplin, marcsun13, pagezyhf, ahadnagy, joaogante
• • 514 upvoted a paper about 1 year ago