4 papers
RIMS: Preference Optimization via Smoothed Multi-pair Aggregation for Small-Scale LLM Retrieval-Augmented Generation
Pei Tian, Zihan Dong, Tianci Liu +2
Small-scale language models (SLMs) are attractive for retrieval-augmented generation (RAG) in resource-constrained settings, but their limited capacity makes them highly sensitive…
CogniRoute: Learning to Route Social Evidence in Omni-Modal Models
Yifan Shen, Pei Tian, Xinzhuo Li +8
Omni-modal models can ingest video, audio, and text, but unified access to multiple modalities does not guarantee that a model uses the right evidence. This gap is especially prono…
LLM-based Realistic Safety-Critical Driving Video Generation
Yongjie Fu, Ruijian Zha, Pei Tian +1
Designing diverse and safety-critical driving scenarios is essential for evaluating autonomous driving systems. In this paper, we propose a novel framework that leverages Large Lan…
Agile-VLA: Few-Shot Industrial Pose Rectification via Implicit Affordance Anchoring
Teng Yan, Zhengyang Pei, Chengyu Shi +8
Deploying Vision-Language-Action (VLA) models on resource-constrained edge platforms encounters a fundamental conflict between high-latency semantic inference and the high-frequenc…