5 papers
AMBER: Multi-View Adaptive Budget Allocation for Listwise Vision-Language Reranking
Wenteng Chen, Jiachen Zhu, Rong Shan +10
Vision-language models (VLMs) are powerful listwise rerankers for multimodal retrieval, but high inference costs restrict them to evaluating small local candidate views. Existing m…
Weaving Visual Narratives: Agentic Image Bundle Composition Beyond Atomic Visual Matching
Rong Shan, Tianyi Xu, Congmin Zheng +9
Image retrieval has traditionally been formulated as a point-wise matching problem, where each candidate image is scored in isolation. However, this atomic paradigm fails to captur…
OThink-SRR1: Search, Refine and Reasoning with Reinforced Learning for Large Language Models
Haijian Liang, Zenghao Niu, Junjie Wu +3
Retrieval-Augmented Generation (RAG) expands the knowledge of Large Language Models (LLMs), yet current static retrieval methods struggle with complex, multi-hop problems. While re…
PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval
Tianyi Xu, Rong Shan, Junjie Wu +11
Personal photo albums are not merely collections of static images but living, ecological archives defined by temporal continuity, social entanglement, and rich metadata, which make…
Proof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents
Shengjie Ma, SHengjie Ma, Chenlong Deng +6
While reinforcement learning (RL) enhances their ability to plan and reason across retrieval steps, we identify a critical failure mode in this setting: Tool-Call Hacking. Unlike e…