collaborators

7 papers

cs.AI2026

TrafficRAG: A Multimodal RAG Framework for Traffic Accident Liability Determination

Xu Li, Zedong Fu, Xinyi Li +1

Traffic accident liability analysis is a critical yet challenging task in intelligent transportation and legal assistance. Existing methods often suffer from low efficiency, subjec…

cs.IR2026

UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale

Hanyu Li, Yi-Ping Hsu, Aditya Mantha +17

Modern recommendation systems predominantly train retrieval and ranking as separate models despite both increasingly relying on large transformers encoding the same user behavior d…

cs.IR2026

LLMs Need Encoders for Semantic IDs Too

Xiangyi Chen, Zelun Wang, Xinyi Li +3

Multimodal LLMs use dedicated encoders to bridge non-language modalities (vision encoders for images, depth models for audio codec tokens) because raw token embeddings alone cannot…

cs.CL2026

EvoGens: A Population-Based Heuristic Search Framework for Scientific Idea Generation

Xu Li, Hanzhe Tu, Xinyi Li +3

Generating novel research ideas is fundamental to scientific progress. While Large Language Models (LLMs) show promise in assisting this process, existing approaches often exhibit…

cs.SE2026

A Scalable Benchmark for Repository-Oriented Long-Horizon Conversational Context Management

Yang Liu, Li Zhang, Fang Liu +2

In recent years, large language models (LLMs) have advanced rapidly, substantially enhancing their code understanding and generation capabilities and giving rise to powerful code a…

cs.IR2026

Balancing Domestic and Global Perspectives: Evaluating Dual-Calibration and LLM-Generated Nudges for Diverse News Recommendation

Ruixuan Sun, Matthew Zent, Minzhu Zhao +3

In this study, we applied the ``personalized diversity nudge framework'' with the goal of expanding user reading coverage in terms of news locality (i.e., domestic and world news).…