1 citations · 1 across the 27 of their papers we have counts for
28 papers
MEDR: Query-Independent Frame Selection via Multi-Signal Event Modeling and Dynamic Rescoring
Xinlei Pu, Weijie Shi, Wen Yang +6
Frame selection is a fundamental component of multimodal large language models, enabling long videos to be processed under limited visual-token and computational budgets. Uniform s…
DREvo: Distilling Recalibrated Historical Experience for Harness Self-Evolution
Hanghui Guo, Weijie Shi, Zhangze Chen +6
Harness plays a critical role in large language model agent performance, and building a high-performing harness requires substantial expert effort. Therefore, recent research has i…
RippleKV: Cross-Layer KV Cache Allocation via Perturbation Propagation
Dongjie Xu, Kai Qian, Julius +6
Long-context LLM inference is bottlenecked by KV cache memory, yet distributing a limited cache budget across layers remains challenging. Existing methods rely on proxies such as l…
Task Decomposition-Guided Reranking for Adaptive Agent Skill Retrieval
Yanping Chen, Weijie Shi, Wen Yang +1
Skill usage can significantly enhance the ability of modern agent systems to complete complex tasks. However, the growing scale of skill libraries makes accurate skill selection in…
Fighting Numerical Hallucinations via Data-centric Compilation for Online Financial QA
Hao Chen, Xing Tang, Qirui Liu +6
Large Language Models (LLMs) have significantly advanced online data services, particularly in the domain of financial question answering (FinQA). However, such systems remain susc…
SSR3D-LLM: Structured Spatial Reasoning via Latent Steps for Fine-Grained Grounding in Unified 3D-LLMs
Jiawei Li, Ziyi Liu, Weijie Shi +3
3D object grounding localizes referred objects in a 3D scene from natural language. Unified instance-centric 3D-LLMs aim to solve grounding together with dialog, QA, and captioning…
SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting
Weijie Shi, Qiang Xu, Fan Deng +9
Speculative decoding accelerates LLM inference by drafting a tree of candidate continuations and verifying it in one target forward. Existing drafters fall into two camps with oppo…
Cognitive-Uncertainty Guided Knowledge Distillation for Accurate Classification of Student Misconceptions
Qirui Liu, Hao Chen, Weijie Shi +2
Accurately identifying student misconceptions is crucial for personalized education but faces three challenges: (1) data scarcity with long-tail distribution, where authentic stude…
LoopGuard: Breaking Self-Reinforcing Attention Loops via Dynamic KV Cache Intervention
Dongjie Xu, Hao Wu, Weijie Shi +7
Through systematic experiments on long-context generation, we observe a damaging failure mode in which decoding can collapse into persistent repetition loops. We find that this deg…
Decoupling and Regulating Modality Heads for Fake News Detection under Missing Modality
Kai Qian, Dongjie Xu, Weijie Shi +9
Multimodal news often loses its image or text as it spreads across Web platforms. Existing methods treat this as information loss, assuming that the original veracity label remains…
Data-Driven Function Calling Improvements in Large Language Model for Online Financial QA
Xing Tang, Hao Chen, Shiwei Li +7
Large language models (LLMs) have been incorporated into numerous industrial applications. Meanwhile, a vast array of API assets is scattered across various functions in the financ…
ACR: Adaptive Context Refactoring via Context Refactoring Operators for Multi-Turn Dialogue
Jiawei Shen, Jia Zhu, Hanghui Guo +9
Large Language Models (LLMs) have shown remarkable performance in multi-turn dialogue. However, in multi-turn dialogue, models still struggle to stay aligned with what has been est…
DynaGen: Unifying Temporal Knowledge Graph Reasoning with Dynamic Subgraphs and Generative Regularization
Jiawei Shen, Jia Zhu, Hanghui Guo +6
Temporal Knowledge Graph Reasoning (TKGR) aims to complete missing factual elements along the timeline. Depending on the temporal position of the query, the task is categorized int…
RL: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification
Weijie Shi, Yanxi Chen, Zexi Li +5
Reinforcement learning drives recent advances in LLM reasoning and agentic capabilities, yet current approaches struggle with both exploration and exploitation. Exploration suffers…
EduEval: A Hierarchical Cognitive Benchmark for Evaluating Large Language Models in Chinese Education
Guoqing Ma, Jia Zhu, Hanghui Guo +5
Large language models (LLMs) demonstrate significant potential for educational applications. However, their unscrutinized deployment poses risks to educational standards, underscor…
Automatic Failure Attribution and Critical Step Prediction Method for Multi-Agent Systems Based on Causal Inference
Guoqing Ma, Jia Zhu, Hanghui Guo +4
Multi-agent systems (MAS) are critical for automating complex tasks, yet their practical deployment is severely hampered by the challenge of failure attribution. Current diagnostic…
Consistent and Invariant Generalization Learning for Short-video Misinformation Detection
Hanghui Guo, Weijie Shi, Mengze Li +8
Short-video misinformation detection has attracted wide attention in the multi-modal domain, aiming to accurately identify the misinformation in the video format accompanied by the…
E3-Rewrite: Learning to Rewrite SQL for Executability, Equivalence,and Efficiency
Dongjie Xu, Yue Cui, Weijie Shi +9
SQL query rewriting aims to reformulate a query into a more efficient form while preserving equivalence. Most existing methods rely on predefined rewrite rules. However, such rule-…
Zero-Shot Cellular Trajectory Map Matching
Weijie Shi, Yue Cui, Hao Chen +5
Cellular Trajectory Map-Matching (CTMM) aims to align cellular location sequences to road networks, which is a necessary preprocessing in location-based services on web platforms l…
Reading Between the Timelines: RAG for Answering Diachronic Questions
Kwun Hang Lau, Ruiyuan Zhang, Weijie Shi +2
While Retrieval-Augmented Generation (RAG) excels at injecting static, factual knowledge into Large Language Models (LLMs), it exhibits a critical deficit in handling longitudinal…
LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning
Weijie Shi, Han Zhu, Jiaming Ji +7
Legal judgment prediction (LJP) aims to function as a judge by making final rulings based on case claims and facts, which plays a vital role in the judicial domain for supporting c…
Semantic-guided Diverse Decoding for Large Language Model
Weijie Shi, Yue Cui, Yaguang Wu +7
Diverse decoding of large language models is crucial for applications requiring multiple semantically distinct responses, yet existing methods primarily achieve lexical rather than…
Enhancing Tool Learning in Large Language Models with Hierarchical Error Checklists
Yue Cui, Liuyi Yao, Shuchang Tao +4
Large language models (LLMs) have significantly advanced natural language processing, particularly through the integration of external tools and APIs. However, their effectiveness…
DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generation
Hanghui Guo, Jia Zhu, Shimin Di +3
Dynamic Retrieval-augmented Generation (RAG) has shown great success in mitigating hallucinations in large language models (LLMs) during generation. However, existing dynamic RAG m…