This is your work, valued
Daejeon
self-distillation-analysis. Codebase for the work “Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?”
73Decision-ConvFormer. [ICLR 2024 Spotlight] Code for the paper "Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making"
12QCS. [NeurIPS 2024] Code for the paper "Adaptive Q-Aid for Conditional Supervised Learning in Offline Reinforcement Learning"
10LESSON. [ICML 2023] Official code repository for LESSON.
7strategic-information-allocation-llm-reasoning. Codebase for the work "Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty"
7 views searches