activity
20242026
collaborators

14 papers

cs.CL2026

Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs

Zixuan Ren, Jinliang Lu, Junhong Wu +5

Model merging plays a crucial role in consolidating multiple specialized models into a single, unified model, especially in the era of large language models (LLMs). Recent research…

cs.CL2026

HTAM: Hierarchical Transition-Attended Memory for Operator Optimization

Yining Zhang, Mingyang Yi, Chen Wang +5

High-performance GPU kernels are essential for efficient LLM deployment, yet optimizing them remains expertise-intensive. Recent LLM-based code generation makes automatic GPU opera…

cs.AI2026

Listening to the Echo: User-Reaction Aware Policy Optimization via Scalar-Verbal Hybrid Reinforcement Learning

Jing Ye, Xinpei Zhao, Lu Xiang +2

While current emotional support dialogue systems typically rely on expert-defined scalar rewards for alignment, these signals suffer from severe information sparsity. They cannot e…

cs.CV2026

PromptDLA: A Domain-aware Prompt Document Layout Analysis Framework with Descriptive Knowledge as a Cue

Zirui Zhang, Yaping Zhang, Lu Xiang +4

Document Layout Analysis (DLA) is crucial for document artificial intelligence and has recently received increasing attention, resulting in an influx of large-scale public DLA data…

cs.CV2026

ICDAR 2025 Competition on End-to-End Document Image Machine Translation Towards Complex Layouts

Yaping Zhang, Yupu Liang, Zhiyang Zhang +5

Document Image Machine Translation (DIMT) seeks to translate text embedded in document images from one language to another by jointly modeling both textual content and page layout,…

cs.CL2026

EmoHarbor: Evaluating Personalized Emotional Support by Simulating the User's Internal World

Jing Ye, Lu Xiang, Yaping Zhang +1

Current evaluation paradigms for emotional support conversations tend to reward generic empathetic responses, yet they fail to assess whether the support is genuinely personalized…