-
Provable Benefits of In-Tool Learning for Large Language Models
Paper • 2508.20755 • Published • 11 -
CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning
Paper • 2508.15868 • Published • 3 -
Gated Delta Networks: Improving Mamba2 with Delta Rule
Paper • 2412.06464 • Published • 14
Yuantian Huang
hyuantian
AI & ML interests
None yet
Organizations
None yet
-
Provable Benefits of In-Tool Learning for Large Language Models
Paper • 2508.20755 • Published • 11 -
CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning
Paper • 2508.15868 • Published • 3 -
Gated Delta Networks: Improving Mamba2 with Delta Rule
Paper • 2412.06464 • Published • 14
datasets
0
None public yet