collaborators

5 papers

cs.CL2026

DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing

Jinyu Guo, Zhihan Zhang, Jiehui Xie +7

The quadratic computational complexity of the standard attention mechanism constitutes a fundamental bottleneck for large language models in long-context inference. While existing…

cs.CL2026

Aligned Multi-View Scripts for Universal Chart-to-Code Generation

Zhihan Zhang, Lizi Liao

Chart-to-code generation converts a chart image into an executable plotting script, enabling faithful reproduction and editable visualizations. Existing methods are largely Python-…

cs.CL2026

Prioritizing the Best: Incentivizing Reliable Multimodal Reasoning by Rewarding Beyond Answer Correctness

Mengzhao Jia, Zhihan Zhang, Meng Jiang

Reinforcement Learning with Verifiable Rewards (RLVR) improves multimodal reasoning by rewarding verifiable final answers. Yet answer-correct trajectories may still rely on incompl…

cs.CL2025

XFinBench: Benchmarking LLMs in Complex Financial Problem Solving and Reasoning

Zhihan Zhang, Yixin Cao, Lizi Liao

Solving financial problems demands complex reasoning, multimodal data processing, and a broad technical understanding, presenting unique challenges for current large language model…

cs.CL2025

Boosting Chart-to-Code Generation in MLLM via Dual Preference-Guided Refinement

Zhihan Zhang, Yixin Cao, Lizi Liao

Translating chart images into executable plotting scripts-referred to as the chart-to-code generation task-requires Multimodal Large Language Models (MLLMs) to perform fine-grained…