7 papers
Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization
Jiashu Yao, Heyan Huang, Daiqing Wu +2
To encourage diverse exploration in reinforcement learning (RL) for large language models (LLMs) without compromising accuracy, we propose Policy Split, a novel paradigm that bifur…
Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning
Daiqing Wu, Xuan Zhang, Dongbao Yang +7
The maturation of Large Audio Language Models (LALMs) has raised growing expectations for them to comprehend complex audio much like humans. Current efforts primarily replicate tex…
SIFThinker: Spatially-Aware Image Focus for Visual Reasoning
Zhangquan Chen, Ruihui Zhao, Chuwei Luo +4
Current multimodal large language models (MLLMs) still face significant challenges in complex visual tasks (e.g., spatial understanding, fine-grained perception). Prior methods hav…
Incorporating Self-Rewriting into Large Language Model Reasoning Reinforcement
Jiashu Yao, Heyan Huang, Shuang Zeng +6
Through reinforcement learning (RL) with outcome correctness rewards, large reasoning models (LRMs) with scaled inference computation have demonstrated substantial success on compl…
MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models
Jiacheng Ruan, Dan Jiang, Xian Gao +3
Recently, multimodal large language models (MLLMs) have achieved significant advancements across various domains, and corresponding evaluation benchmarks have been continuously ref…
Efficient and Accurate Prompt Optimization: the Benefit of Memory in Exemplar-Guided Reflection
Cilin Yan, Jingyun Wang, Lin Zhang +6
Automatic prompt engineering aims to enhance the generation quality of large language models (LLMs). Recent works utilize feedbacks generated from erroneous cases to guide the prom…