1 citations · 4 across the 39 of their papers we have counts for
49 papers
Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language Models
Yuqi Xiong, Chunyi Peng, Zhipeng Xu +5
Reinforcement learning (RL) can elicit specialized visual capabilities in vision-language models (VLMs), yet jointly optimizing heterogeneous objectives often introduces cross-capa…
Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution
Pengcheng Huang, Zhenghao Liu, Shixin Ren +5
Edge-cloud collaboration combines the lower inference overhead and greater data locality of edge-side execution with the stronger capabilities of cloud-hosted models. However, as L…
PVFH-Bench: Benchmarking Premise-Induced Visual Fixation Hallucinations in Vision-Language Models
Xinhao Wang, Junbo Cui, Zhenghao Liu +4
Large Vision-Language Models (LVLMs) have achieved remarkable progress across a wide range of multimodal tasks. However, object hallucination remains a persistent challenge, underm…
ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval
Chunyi Peng, Zhipeng Xu, Yukun Yan +9
Visual document retrieval is a critical component of multimodal retrieval-augmented generation, aiming to identify query-relevant pages from document collections where evidence is…
REFACT: Adaptive Fact Restatement for Compact and Faithful Chain-of-Thought Reasoning
Zhensheng Jin, Xin Dai, Zhenghao Liu +5
Large Language Models (LLMs) increasingly leverage long-form reasoning to solve complex tasks, yet their reasoning processes can deviate from the provided context when evidence is…
HiEviDR-Bench: A Benchmark for Hierarchical Evidence Aggregation in Deep Research
Yubo Sun, Chunyi Peng, Yukun Yan +6
Deep research requires models to retrieve, connect, and synthesize evidence from large-scale heterogeneous sources to answer complex queries and produce analytical reports. Existin…
CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning
Dingling Xu, Ruobing Wang, Qingfei Zhao +8
Reasoning Language Models (RLMs) have significantly improved performance on complex tasks by extending the reasoning chain. However, these chains are prone to containing factual er…
HippoSpark: An On-Demand Experience System for LLM Reasoning
Jingyao Liu, Danling Meng, Chen Huang +5
Distilling historical trajectories into reusable experience to enhance future problem-solving has become a focal point of recent LLM research. However, existing methods predominant…
SPARK: Adaptive Parametric Knowledge Participation for Faithful Retrieval-Augmented Generation
Ruochang Li, Pengcheng Huang, Zhenghao Liu +5
Retrieval-augmented generation (RAG) enhances the faithfulness of large language models (LLMs) by incorporating external knowledge into the generation process. However, conflicts b…
MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering
Qing Yang, Pengcheng Huang, Xinze Li +6
Long-video question answering remains challenging for Vision-Language Models (VLMs), as answer-relevant evidence is often sparse, transient, and temporally dispersed across lengthy…
Memory Shot for Long-Term Dialogue
Chunyi Peng, Haidong Xin, Xuanshuo Sheng +7
Large Language Models (LLMs) have demonstrated strong capabilities in general conversation, instruction following, and complex reasoning. However, in long-term dialogue settings, t…
CC-OCR V2: Fine-Grained Attribution of LMM Failures in Real-World Visual Document Understanding
Chunyi Peng, Zhipeng Xu, Yuqi Xiong +12
Recent Large Multimodal Models (LMMs) have achieved remarkable progress on OCR-centric document understanding and processing tasks. Existing benchmarks primarily evaluate LMMs acro…
ReAlign: Optimizing the Visual Document Retriever with Reasoning-Guided Fine-Grained Alignment
Hao Yang, Yifan Ji, Zhipeng Xu +6
Visual document retrieval aims to retrieve a set of document pages relevant to a query from visually rich collections. Existing methods often employ Vision-Language Models (VLMs) t…
Scientific Knowledge-driven Decoding Constraints Improving the Reliability of LLMs
Maotian Ma, Zheni Zeng, Zhenghao Liu +1
Large language models (LLMs) have shown strong knowledge reserves and task-solving capabilities, but still face the challenge of severe hallucination, hindering their practical app…
Tau-BNO: Brain Neural Operator for Tau Transport Model
Nuutti Barron, Heng Rao, Urmi Saha +6
Mechanistic modeling provides a biophysically grounded framework for studying the spread of pathological tau protein in tauopathies like Alzheimer's disease. Existing approaches ty…
AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research
Yishan Li, Wentong Chen, Yukun Yan +12
Generating deep research reports requires large-scale information acquisition and the synthesis of insight-driven analysis, posing a significant challenge for current language mode…
Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains
Yuqi Xiong, Chunyi Peng, Zhipeng Xu +6
Visual Retrieval-Augmented Generation (VRAG) enhances Vision-Language Models (VLMs) by incorporating external visual documents to address a given query. Existing VRAG frameworks us…
Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models
Hao Chen, Ye He, Yuchun Fan +5
Knowledge augmentation has significantly enhanced the performance of Large Language Models (LLMs) in knowledge-intensive tasks. However, existing methods typically operate on the s…
MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization
Haidong Xin, Xinze Li, Zhenghao Liu +6
Existing memory systems enable Large Language Models (LLMs) to support long-horizon human-LLM interactions by persisting historical interactions beyond limited context windows. How…
UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents
Yifan Ji, Zhipeng Xu, Zhenghao Liu +7
Key Information Extraction (KIE) from real-world documents remains challenging due to substantial variations in layout structures, visual quality, and task-specific information req…
Teaching LLMs to Learn Tool Trialing and Execution through Environment Interaction
Xingjie Gao, Pengcheng Huang, Zhenghao Liu +6
Equipping Large Language Models (LLMs) with external tools enables them to solve complex real-world problems. However, the robustness of existing methods remains a critical challen…
Long-Chain Reasoning Distillation via Adaptive Prefix Alignment
Zhenghao Liu, Zhuoyang Wu, Xinze Li +6
Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities, particularly in solving complex mathematical problems. Recent studies show that distilling long re…
Revealing the Attention Floating Mechanism in Masked Diffusion Models
Xin Dai, Pengcheng Huang, Zhenghao Liu +6
Masked diffusion models (MDMs), which leverage bidirectional attention and a denoising process, are narrowing the performance gap with autoregressive models (ARMs). However, their…
Finding What Matters: Anchoring Context Knowledge with Evolving Indices for Iterative Retrieval
Mingyan Wu, Zhenghao Liu, Xinze Li +7
Retrieval-Augmented Generation (RAG) has become a dominant paradigm for mitigating hallucinations in Large Language Models (LLMs) by incorporating external knowledge. However, exis…