7 papers
ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference
Xiongwei Zhu, Xiaojian Liao, Tianyang Jiang +3
Fine-grained Mixture-of-Experts (MoE) models sparsely activate only a subset of experts per token, reducing activated computation while maintaining high model capacity. However, in…
Multi-Paradigm Agent Interaction in Practice:A Systematic Analysis of Generator-Evaluator, ReAct Loop,and Adversarial Evaluation in the buddyMe Framework
Xiaohua Wang, Chao Han, Kai Yu +2
The rapid evolution of Large Language Model (LLM) agents has produced diverse interaction paradigms, yet few production systems integrate multiple paradigms within a unified archit…
RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation
Jiajun Zhang, Yuying Li, Zhixun Li +13
Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains. However, their ability to replicate complex, multi-panel visualiz…
SCAN: Sparse Circuit Anchor Interpretable Neuron for Lifelong Knowledge Editing
Yuhuan Liu, Haitian Zhong, Xinyuan Xia +3
Large Language Models (LLMs) often suffer from catastrophic forgetting and collapse during sequential knowledge editing. This vulnerability stems from the prevailing dense editing…
Learning to Draft: Adaptive Speculative Decoding with Reinforcement Learning
Jiebin Zhang, Zhenghan Yu, Liang Wang +8
Speculative decoding accelerates large language model (LLM) inference by using a small draft model to generate candidate tokens for a larger target model to verify. The efficacy of…
Multimodal Adaptive Retrieval Augmented Generation through Internal Representation Learning
Ruoshuang Du, Xin Sun, Qiang Liu +4
Visual Question Answering systems face reliability issues due to hallucinations, where models generate answers misaligned with visual input or factual knowledge. While Retrieval Au…