Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
Paper • 2605.11609 • Published • 116
Dongcheng Zhao
XduSponge
·
AI & ML interests
None yet
Recent Activity
authored a paper about 21 hours ago
Neuro-Vision to Language: Enhancing Visual Reconstruction and Language
Interaction through Brain Recordings authored a paper about 21 hours ago
Astrocyte-Enabled Advancements in Spiking Neural Networks for Large
Language Modeling authored a paper about 21 hours ago
Harnessing Task Overload for Scalable Jailbreak Attacks on Large
Language ModelsOrganizations
upvoted 2
papers 1 day ago