activity
20242026
collaborators

6 papers

cs.CV2026

MiMIC: Mitigating Visual Modality Collapse in Universal Multimodal Retrieval While Avoiding Semantic Misalignment

Juan Li, Chuanghao Ding, Xujie Zhang +1

Universal Multimodal Retrieval (UMR) aims to map different modalities (e.g., visual and textual) into a shared embedding space for multi-modal retrieval. Existing UMR methods can b…

cs.LG2025

LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation

Yiqun Shen, Song Yuan, Zhengze Zhang +3

KV Cache is commonly used to accelerate LLM inference with long contexts, yet its high memory demand drives the need for cache compression. Existing compression methods, however, a…

cs.LG2025

daDPO: Distribution-Aware DPO for Distilling Conversational Abilities

Zhengze Zhang, Shiqi Wang, Yiqun Shen +5

Large language models (LLMs) have demonstrated exceptional performance across various applications, but their conversational abilities decline sharply as model size decreases, pres…

cs.CL2025

Momentum Posterior Regularization for Multi-hop Dense Retrieval

Zehua Xia, Yuyang Wu, Yiyun Xia +1

Multi-hop question answering (QA) often requires sequential retrieval (multi-hop retrieval), where each hop retrieves missing knowledge based on information from previous hops. To…

cs.LG2025

Corporate Fraud Detection in Rich-yet-Noisy Financial Graph

Shiqi Wang, Zhibo Zhang, Libing Fang +2

Corporate fraud detection aims to automatically recognize companies that conduct wrongful activities such as fraudulent financial statements or illegal insider trading. Previous le…

cs.CV2024

SynthDoc: Bilingual Documents Synthesis for Visual Document Understanding

Chuanghao Ding, Xuejing Liu, Wei Tang +5

This paper introduces SynthDoc, a novel synthetic document generation pipeline designed to enhance Visual Document Understanding (VDU) by generating high-quality, diverse datasets…