37 citations · 42 across the 17 of their papers we have counts for
19 papers
Gradient-free Task-Conditioned Retrieval for On-Device In-Context Learning
Xinyu Luo, Hui Liu, Yihua Shao +3
On-device in-context learning (ICL) relies on pre-inference retrieval to select demonstrations for useful context before downstream model inference. This retrieval must exploit tas…
Unbiased Alignment for Large Language Models with Noisy Preferences
Jialiang Wang, Xianming Liu, Xiong Zhou +2
The alignment of large language models with human preferences is commonly achieved through Reinforcement Learning from Human Feedback or Direct Preference Optimization. However, th…
Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios
Hui Liu, Bin Zou, Kecheng Chen +3
Large language models (LLMs) exhibit substantial variability in performance and computational cost across tasks and queries, motivating routing systems that select models to meet u…
Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition
Hui Liu, Kecheng Chen, Jialiang Wang +3
Vision-Language Models (VLMs), such as CLIP, have significantly advanced zero-shot image recognition. However, their performance remains limited by suboptimal prompt engineering an…
Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models
Kecheng Chen, Ziru Liu, Xijia Tao +7
Diffusion Language Models (DLMs) have recently achieved significant success due to their any-order generation capabilities. However, existing inference methods typically rely on lo…
Hybrid Retrieval-Augmented Generation Agent for Trustworthy Legal Question Answering in Judicial Forensics
Yueqing Xi, Yifan Bai, Huasen Luo +3
As artificial intelligence permeates judicial forensics, ensuring the veracity and traceability of legal question answering (QA) has become critical. Conventional large language mo…
Unveiling Modality Bias: Automated Sample-Specific Analysis for Multimodal Misinformation Benchmarks
Hehai Lin, Hui Liu, Shilei Cao +3
Numerous multimodal misinformation benchmarks exhibit bias toward specific modalities, allowing detectors to make predictions based solely on one modality. While previous research…
Domain-Specific Data Generation Framework for RAG Adaptation
Chris Xing Tian, Weihao Xie, Zhen Chen +5
Retrieval-Augmented Generation (RAG) combines the language understanding and reasoning power of large language models (LLMs) with external retrieval to enable domain-grounded respo…
Propose and Rectify: A Forensics-Driven MLLM Framework for Image Manipulation Localization
Keyang Zhang, Chenqi Kong, Hui Liu +3
The increasing sophistication of image manipulation techniques demands robust forensic solutions that can both reliably detect alterations and precisely localize tampered regions.…
Disentangling Instruction Influence in Diffusion Transformers for Parallel Multi-Instruction-Guided Image Editing
Hui Liu, Bin Zou, Suiyun Zhang +3
Instruction-guided image editing enables users to specify modifications using natural language, offering more flexibility and control. Among existing frameworks, Diffusion Transfor…
Test-time Adaptation for Foundation Medical Segmentation Model without Parametric Updates
Kecheng Chen, Xinyu Luo, Tiexin Qin +5
Foundation medical segmentation models, with MedSAM being the most popular, have achieved promising performance across organs and lesions. However, MedSAM still suffers from compro…
Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidance
Hui Liu, Wenya Wang, Kecheng Chen +6
In zero-shot image recognition tasks, humans demonstrate remarkable flexibility in classifying unseen categories by composing known simpler concepts. However, existing vision-langu…
Q-PART: Quasi-Periodic Adaptive Regression with Test-time Training for Pediatric Left Ventricular Ejection Fraction Regression
Jie Liu, Tiexin Qin, Hui Liu +5
In this work, we address the challenge of adaptive pediatric Left Ventricular Ejection Fraction (LVEF) assessment. While Test-time Training (TTT) approaches show promise for this t…
Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You Need
Kecheng Chen, Pingping Zhang, Hui Liu +6
We have recently witnessed that ``Intelligence" and `` Compression" are the two sides of the same coin, where the language large model (LLM) with unprecedented intelligence is a ge…
Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning
Hui Liu, Wenya Wang, Hao Sun +4
Large Language Models (LLMs) have demonstrated impressive in-context learning (ICL) capabilities from few-shot demonstration exemplars. While recent learning-based demonstration se…
TELLER: A Trustworthy Framework for Explainable, Generalizable and Controllable Fake News Detection
Hui Liu, Wenya Wang, Haoru Li +1
The proliferation of fake news has emerged as a severe societal problem, raising significant interest from industry and academia. While existing deep-learning based methods have ma…
Robust Domain Misinformation Detection via Multi-modal Feature Alignment
Hui Liu, Wenya Wang, Hao Sun +2
Social media misinformation harms individuals and societies and is potentialized by fast-growing multi-modal content (i.e., texts and images), which accounts for higher "credibilit…
Interpretable Multimodal Misinformation Detection with Logic Reasoning
Hui Liu, Wenya Wang, Haoliang Li
Multimodal misinformation on online social platforms is becoming a critical concern due to increasing credibility and easier dissemination brought by multimedia content, compared t…
Towards Multi-Modal Sarcasm Detection via Hierarchical Congruity Modeling with Knowledge Enhancement
Hui Liu, Wenya Wang, Haoliang Li
Sarcasm is a linguistic phenomenon indicating a discrepancy between literal meanings and implied intentions. Due to its sophisticated nature, it is usually challenging to be detect…