collaborators

19 papers

cs.IR2026

Token-Level Credit Assignment Optimization for Generative Document Retrieval

Xinpeng Zhao, Yang Liu, Ran Chen +6

Generative retrieval models perform document retrieval by autoregressively generating document identifiers (DocIDs). This process naturally forms a sequential decision problem, whe…

cs.IR2026

Querit-Reranker: Training Compact Multilingual Rerankers via Efficient Label-Free Distribution Adaptation

Yunfei Zhong, Jun Yang, Wei Huang +7

Deployable multilingual rerankers must generalize across languages, domains, and target ranking tasks while remaining efficient enough for second-stage reranking. However, adapting…

cs.IR2026

Reconstructing Content with Collaborative Attention for Universal Multimodal Representation Learning

Jiahan Chen, Da Li, Hengran Zhang +6

Multimodal embedding models, rooted in multimodal large language models (MLLMs), have yielded significant performance improvements across diverse tasks such as retrieval and classi…

cs.AI2026

Thinking as Compression: Your Reasoning Model is Secretly a Context Compressor

Guoxin Ma, Yibing Liu, Chengzhengxu Li +7

Context compression aims to shorten long context inputs with minimal information loss for LLM inference acceleration. While existing methods have shown promise, they typically rely…

cs.CL2026

ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains

Ziqi Zhao, Xinyu Ma, Liu Yang +6

On-policy self-distillation (OPSD) improves the reasoning performance of large language models (LLMs) by providing dense token-level supervision for on-policy rollouts. However, ex…

cs.CL2026

Large Language Model-Powered Query-Driven Event Timeline Summarization in Industrial Search

Mingyue Wang, Xingyu Xie, Hang Yang +5

Understanding how events evolve over time is essential for search engines handling queries about trending news. We present QDET (Query-Driven Event Timeline Summarization), a produ…