8 papers
Learn from the Gap: Differential-Aware Advantage Pruning with Adaptive Rollout Sampling for GRPO
Jiahua Yang, Zhiwei Yang, Xianpeng Zhang +7
Recently, Group Relative Policy Optimization (GRPO) and its variants have been developed for policy optimization and demonstrated notable performance gains. However, these methods…
MMLDSum-LLM: Multimodal Long-Document Summarization with Visual-Alignment and Keyword-Aware
Xianpeng Zhang, Jiahua Yang, Dongyu Chen +7
Multimodal long documents are core carriers of professional knowledge, where critical evidence is sparsely distributed across paragraphs and modalities. This easily causes key info…
QuantEval: A Benchmark for Financial Quantitative Tasks in Large Language Models
Zhaolu Kang, Junhao Gong, Wenqing Hu +15
Large Language Models (LLMs) have shown strong capabilities in finance-oriented question answering, yet their evaluation on professional quantitative workflows remains fragmented a…
Learning from Prompt itself: the Hierarchical Attribution Prompt Optimization
Dongyu Chen, Jian Ma, Xianpeng Zhang +5
Optimization is fundamental across numerous disciplines, typically following an iterative process of refining an initial solution to enhance performance. This principle is equally…
Easy Adaptation: An Efficient Task-Specific Knowledge Injection Method for Large Models in Resource-Constrained Environments
Dong Chen, Zhengqing Hu, Shixing Zhao +1
While the enormous parameter scale endows Large Models (LMs) with unparalleled performance, it also limits their adaptability across specific tasks. Parameter-Efficient Fine-Tuning…
MIMO: A medical vision language model with visual referring multimodal input and pixel grounding multimodal output
Yanyuan Chen, Dexuan Xu, Yu Huang +6
Currently, medical vision language models are widely used in medical vision question answering tasks. However, existing models are confronted with two issues: for input, the model…
TeLL-Drive: Enhancing Autonomous Driving with Teacher LLM-Guided Deep Reinforcement Learning
Chengkai Xu, Jiaqi Liu, Shiyu Fang +4
Although Deep Reinforcement Learning (DRL) and Large Language Models (LLMs) each show promise in addressing decision-making challenges in autonomous driving, DRL often suffers from…
The Critical Canvas--How to regain information autonomy in the AI era
Dong Chen
In the era of AI, recommendation algorithms and generative AI challenge information autonomy by creating echo chambers and blurring the line between authentic and fabricated conten…