VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
Paper
• 2602.10693 • Published
• 167
floyed shen
floyed
AI & ML interests
None yet
Recent Activity
commented on
a paper
about 17 hours ago
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training submitted
a paper
1 day ago
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training upvoted a paper 1 day ago
DeepEyesV2: Toward Agentic Multimodal Model Organizations
submitted a paper to Daily Papers 1 day ago
authored 4 papers 7 days ago
Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense
Paper
• 2510.01088 • Published
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
Paper
• 2602.10693 • Published
• 167
StressPrompt: Does Stress Impact Large Language Models and Human Performance Similarly?
Paper
• 2409.17167 • Published
Neuro-Vision to Language: Enhancing Visual Reconstruction and Language Interaction through Brain Recordings
Paper
• 2404.19438 • Published