papers

Publications (8)

cs.CL2026

dCache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching

Yuchu Jiang, Yue Cai, Xiangzhong Luo +4

Diffusion-based large language models (dLLMs), despite their promising performance, still suffer from inferior inference efficiency. This is because dLLMs rely on bidirectional att…

cs.LG2025

Mimic In-Context Learning for Multimodal Tasks

Yuchu Jiang, Jiale Fu, Chenduo Hao +4

Recently, In-context Learning (ICL) has become a significant inference paradigm in Large Multimodal Models (LMMs), utilizing a few in-context demonstrations (ICDs) to prompt LMMs f…

cs.AI2025

GraphIC: A Graph-Based In-Context Example Retrieval Model for Multi-Step Reasoning

Jiale Fu, Yaqing Wang, Simeng Han +2

In-context learning (ICL) enhances large language models (LLMs) by incorporating demonstration examples, yet its effectiveness heavily depends on the quality of selected examples.…

cs.CR2022

An Input-Aware Mimic Defense Theory and its Practice

Jiale Fu, Yali Yuan, Jiajun He +3

The current security problems in cyberspace are characterized by strong and complex threats. Defenders face numerous problems such as lack of prior knowledge, various threats, and…

cs.CL2026

Flatter Tokens are More Valuable for Speculative Draft Model Training

Jiaming Fan, Daming Cao, Xiangzhong Luo +3

Speculative Decoding (SD) is a key technique for accelerating Large Language Model (LLM) inference, but it typically requires training a draft model on a large dataset. We approach…

cs.CV2025

Object Retrieval for Visual Question Answering with Outside Knowledge

Shichao Kan, Yuhai Deng, Jiale Fu +5

Retrieval-augmented generation (RAG) with large language models (LLMs) plays a crucial role in question answering, as LLMs possess limited knowledge and are not updated with contin…

cs.CL2025

Fast Large Language Model Collaborative Decoding via Speculation

Jiale Fu, Yuchu Jiang, Junkai Chen +3

Large Language Model (LLM) collaborative decoding techniques improve output quality by combining the outputs of multiple models at each generation step, but they incur high computa…

cs.LG2026

Rethinking LLM Ensembling from the Perspective of Mixture Models

Jiale Fu, Yuchu Jiang, Peijun Wu +3

Model ensembling is a well-established technique for improving the performance of machine learning models. Conventionally, this involves averaging the output distributions of multi…