activity
20242026
collaborators

7 papers

cs.CV2026

RL-RIG: A Generative Spatial Reasoner via Intrinsic Reflection

Tianyu Wang, Zhiyuan Ma, Qian Wang +3

Recent advancements in image generation have achieved impressive results in producing high-quality images. However, existing image generation models still generally struggle with a…

cs.CL2025

Investigating the Impact of Rationales for LLMs on Natural Language Understanding

Wenhang Shi, Shuqing Bian, Yiren Chen +5

Chain-of-thought (CoT) rationales, which provide step-by-step reasoning to derive final answers, benefit LLMs in both inference and training. Incorporating rationales, either by ge…

cs.CL2025

No Loss, No Gain: Gated Refinement and Adaptive Compression for Prompt Optimization

Wenhang Shi, Yiren Chen, Shuqing Bian +6

Prompt engineering is crucial for leveraging the full potential of large language models (LLMs). While automatic prompt optimization offers a scalable alternative to costly manual…

cs.LG2025

FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning

Liang Hu, Jianpeng Jiao, Jiashuo Liu +20

Search has emerged as core infrastructure for LLM-based agents and is widely viewed as critical on the path toward more general intelligence. Finance is a particularly demanding pr…

cs.AI2025

ST-Raptor: LLM-Powered Semi-Structured Table Question Answering

Zirui Tang, Boyu Niu, Xuanhe Zhou +6

Semi-structured tables, widely used in real-world applications (e.g., financial reports, medical records, transactional orders), often involve flexible and complex layouts (e.g., h…

cs.AI2025

Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts

Zhenghao Liu, Xingsheng Zhu, Tianshuo Zhou +5

With the rapid advancement of Multi-modal Large Language Models (MLLMs), their capability in understanding both images and text has greatly improved. However, their potential for l…