Training LLM Judges from Language Feedback via Position-Selective Self-Distillation
Paper • 2609.38792 • Published • 6
GPUおじさん
gpu-oji
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 9 days ago
Training LLM Judges from Language Feedback via Position-Selective Self-Distillation upvoted a paper 9 days ago
Overcoming Scaling Limits in On-Policy Self-Distillation for LLM ReasoningOrganizations
None yet
upvoted 4
papers 9 days ago
Overcoming Scaling Limits in On-Policy Self-Distillation for LLM Reasoning
Paper • 2609.37915 • Published • 9
Beyond the Remembered World: Predictive 4D Belief for Persistent Navigation in Evolving Worlds
Paper • 2609.39166 • Published • 6
Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence
Paper • 2609.34563 • Published • 219