17 papers
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…
Head-wise Modality Specialization within MLLMs for Robust Fake News Detection under Missing Modality
Kai Qian, Weijie Shi, Jiaqi Wang +7
Multimodal fake news detection (MFND) aims to verify news credibility by jointly exploiting textual and visual evidence. However, real-world news dissemination frequently suffers f…
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…