6 citations · 14 across the 33 of their papers we have counts for
41 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…
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…
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…
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…
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…
DIAL-KG: Schema-Free Incremental Knowledge Graph Construction via Dynamic Schema Induction and Evolution-Intent Assessment
Weidong Bao, Yilin Wang, Ruyu Gao +3
Knowledge Graphs (KGs) are foundational to applications such as search, question answering, and recommendation. Conventional knowledge graph construction methods are predominantly…
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…
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…
SEEK: Steering LLM Reasoning for RAG via Internal Reasoning Sketches
Xinze Li, Yuqing Lan, Zhenghao Liu +7
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external knowledge into the generation process. Benefiting from the reasoning capabiliti…
Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling
Shuliang Liu, Zhipeng Xu, Zhenghao Liu +6
Large Language Models (LLMs) as automatic evaluators, commonly referred to as LLM-as-a-Judge, have also attracted growing attention. This approach plays a vital role in aligning LL…
Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization
Shaohua Duan, Pengcheng Huang, Xinze Li +7
Long-context modeling is critical for a wide range of real-world tasks, including long-context question answering, summarization, and complex reasoning tasks. Recent studies have e…
Legal: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain
Xin Dai, Buqiang Xu, Zhenghao Liu +5
Legal Artificial Intelligence (LegalAI) has achieved notable advances in automating judicial decision-making with the support of Large Language Models (LLMs). However, existing leg…
ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization
Zhensheng Jin, Xinze Li, Yifan Ji +7
Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of Large Language Models (LLMs). However, these methods often suffer from…
Enhancing Long-Chain Reasoning Distillation through Error-Aware Self-Reflection
Zhuoyang Wu, Xinze Li, Zhenghao Liu +7
Large Language Models (LLMs) have exhibited strong reasoning capabilities and achieved remarkable performance in mathematical problem-solving tasks. Recently, distilling reasoning…
LISRec: Modeling User Preferences with Learned Item Shortcuts for Sequential Recommendation
Haidong Xin, Zhenghao Liu, Sen Mei +7
User-item interaction histories are pivotal for sequential recommendation systems but often include noise, such as unintended clicks or actions that fail to reflect genuine user pr…
Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation
Chunyi Peng, Zhipeng Xu, Zhenghao Liu +7
Multimodal Retrieval-Augmented Generation (MRAG) has shown promise in mitigating hallucinations in Multimodal Large Language Models (MLLMs) by incorporating external knowledge. How…
Enhancing the Patent Matching Capability of Large Language Models via the Memory Graph
Qiushi Xiong, Zhipeng Xu, Zhenghao Liu +6
Intellectual Property (IP) management involves strategically protecting and utilizing intellectual assets to enhance organizational innovation, competitiveness, and value creation.…
Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models
Shuliang Liu, Xinze Li, Zhenghao Liu +6
Retrieval-Augmented Generation (RAG) has proven its effectiveness in alleviating hallucinations for Large Language Models (LLMs). However, existing automated evaluation metrics can…