14 papers
Harness-Search: Guiding Long-Horizon Search through Multi-Agent Coordination
Shanyong Wang, Zhenwen Ji, Lei Jin +7
Long-horizon search requires agents to gather evidence across multiple steps and synthesize it into well-supported answers. The recent agent harnesses provide a natural and promisi…
Momentum-Coupled Rubric Adaptation for Detailed Image Captioning
Zhenwen Ji, Lei Jin, Shanyong Wang +6
Detailed image captioning requires accurate and comprehensive descriptions of fine-grained visual content, yet caption quality spans factual accuracy, information coverage, and cla…
From Glance to Scrutiny: Progressive Distortion Reasoning for Fine-Grained Image Quality Assessment
Aoting Zhang, Mingze Gao, Dongbao Yang +5
Multi-modal large language models (MLLMs) have demonstrated significant potential in image quality assessment (IQA) by bridging visual perception with descriptive evaluations. Howe…
Multi-Image Visual Token Pruning in Large Visual Language Models
Rongyang Zhang, Chengqiang Lu, Cong Li +9
With the growing demand for processing multiple image sequences in real-world applications, various visual token pruning methods have emerged to mitigate the computational and cont…
RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge Injection
Shicheng Xu, Liang Pang, Liyi Chen +7
Retrieval-augmented generation (RAG) improves factuality but adds latency and engineering overhead at serving time. We propose RING (Retrieval-Internalized Generation), a holistic…
EditCaption: Human-Refined SFT and HAE-DPO for Image Editing Instruction Synthesis
Xiangyuan Wang, Honghao Cai, Yunhao Bai +9
High-quality source-target image pairs with precise editing instructions are essential for instruction-guided image editing, yet constructing such training triplets at scale remain…
Knowledge-Graph Paths as Intermediate Supervision for Self-Evolving Search Agents
Huyu Wu, Jun Liu, Xiaochi Wei +3
Self-evolving search agents reduce reliance on human-written training questions by generating and solving their own search tasks. We build on Search Self-Play (SSP), a representati…
MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality
Panqi Yang, Haodong Jing, Jiahao Chao +5
Unified visual tokenization faces a fundamental trade-off between high-fidelity pixel reconstruction (spatial equivariance) and semantic abstraction (conceptual invariance). We att…
SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility
Xuyang Zhi, Peilun zhou, Chengqiang Lu +10
The evolution of Large Language Models (LLMs) is shifting the focus from single, verifiable tasks toward complex, open-ended real-world scenarios, imposing significant challenges o…
Aligning Large Language Models with Searcher Preferences
Wei Wu, Peilun Zhou, Liyi Chen +6
The paradigm shift from item-centric ranking to answer-centric synthesis is redefining the role of search engines. While recent industrial progress has applied generative technique…
Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models
Wei Wu, Liyi Chen, Congxi Xiao +7
Large reasoning models enhanced by reinforcement learning with verifiable rewards have achieved significant performance gains by extending their chain-of-thought. However, this par…
RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering
Rongyang Zhang, Yuqing Huang, Chengqiang Lu +8
In real-world scenarios, providing user queries with visually enhanced responses can considerably benefit understanding and memory, underscoring the great value of interleaved imag…
RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios
Fei Zhao, Chengqiang Lu, Yufan Shen +9
While various multimodal multi-image evaluation datasets have been emerged, but these datasets are primarily based on English, and there has yet to be a Chinese multi-image dataset…
SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment
Yuqing Huang, Rongyang Zhang, Qimeng Wang +9
Recent advancements in large language models (LLMs) have revolutionized natural language processing through their remarkable capabilities in understanding and executing diverse tas…