Submitted by CodeGoat24 10 Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning · 7 authors 1
Submitted by shiyi0408 2 FlexiAct: Towards Flexible Action Control in Heterogeneous Scenarios · 5 authors 1
Submitted by iofu728 2 RetroInfer: A Vector-Storage Approach for Scalable Long-Context LLM Inference · 18 authors 1
Submitted by Robot2050 1 Invoke Interfaces Only When Needed: Adaptive Invocation for Large Language Models in Question Answering · 3 authors 1