3 papers
cs.AI2025
TongSIM: A General Platform for Simulating Intelligent Machines
Zhe Sun, Kunlun Wu, Chuanjian Fu +24
As artificial intelligence (AI) rapidly advances, especially in multimodal large language models (MLLMs), research focus is shifting from single-modality text processing to the mor…
cs.CL2025
Reasoning with Exploration: An Entropy Perspective
Daixuan Cheng, Shaohan Huang, Xuekai Zhu +4
Balancing exploration and exploitation is a central goal in reinforcement learning (RL). Despite recent advances in enhancing large language model (LLM) reasoning, most methods lea…
cs.CL2024
On Domain-Adaptive Post-Training for Multimodal Large Language Models
Daixuan Cheng, Shaohan Huang, Ziyu Zhu +5
Adapting general multimodal large language models (MLLMs) to specific domains, such as scientific and industrial fields, is highly significant in promoting their practical applicat…