50 citations · 196 across the 45 of their papers we have counts for
50 papers
ARCANA: A Benchmark for Abstraction and Analogical Reasoning
Ruqi Chen, Zilei Wang, Wei Wang
Analogical reasoning is widely considered a fundamental component of human intelligence. Few benchmarks are designed to explicitly test far analogical reasoning - reasoning between…
On the Vulnerability of Parameter-Level Defenses to Model Merging
Kuangpu Guo, Qingyan Zheng, Jian Liang +4
The training-free integration of expert models via model merging has exposed significant security risks, enabling free-riders to combine specialized models without authorization. R…
GAPD: Gold-Action Policy Distillation for Agentic Reinforcement Learning in Knowledge Base Question Answering
Xin Sun, Jianan Xie, Zhongqi Chen +6
Reinforcement learning (RL) is a natural fit for agentic knowledge base question answering (KBQA), where a model must issue executable actions, observe knowledge-base feedback, and…
Beyond Static Personas: Situational Personality Steering for Large Language Models
Zesheng Wei, Mengxiang Li, Zilei Wang +1
Personalized Large Language Models (LLMs) facilitate more natural, human-like interactions in human-centric applications. However, existing personalization methods are constrained…
Do All Vision Transformers Need Registers? A Cross-Architectural Reassessment
Spiros Baxevanakis, Platon Karageorgis, Ioannis Dravilas +1
Training Vision Transformers (ViTs) presents significant challenges, one of which is the emergence of artifacts in attention maps, hindering their interpretability. Darcet et al. (…
Taming Momentum: Rethinking Optimizer States Through Low-Rank Approximation
Zhengbo Wang, Jian Liang, Ran He +2
Modern optimizers like Adam and Muon are central to training large language models, but their reliance on first- and second-order momenta introduces significant memory overhead, wh…
Evaluating and Achieving Controllable Code Completion in Code LLM
Jiajun Zhang, Zeyu Cui, Lei Zhang +7
Code completion has become a central task, gaining significant attention with the rise of large language model (LLM)-based tools in software engineering. Although recent advances h…
From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning
Jiajun Zhang, Zeyu Cui, Jiaxi Yang +9
The dominant Fill-in-the-Middle (FIM) paradigm for code completion is constrained by its rigid inability to correct contextual errors and reliance on unaligned, insecure Base model…
Predict the Retrieval! Test time adaptation for Retrieval Augmented Generation
Xin Sun, Zhongqi Chen, Qiang Liu +5
Retrieval-Augmented Generation (RAG) has emerged as a powerful approach for enhancing large language models' question-answering capabilities through the integration of external kno…
KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering
Xin Sun, Zhongqi Chen, Xing Zheng +6
Knowledge Base Question Answering (KBQA) challenges models to bridge the gap between natural language and strict knowledge graph schemas by generating executable logical forms. Whi…
Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging
Kuangpu Guo, Aijing Yu, Jian Liang +4
Model merging has emerged as a promising paradigm for enabling multi-task capabilities without additional training. However, traditional basic merging methods often experience perf…
PlotCraft: Pushing the Limits of LLMs for Complex and Interactive Data Visualization
Jiajun Zhang, Jianke Zhang, Zeyu Cui +7
Recent Large Language Models (LLMs) have demonstrated remarkable proficiency in code generation. However, their ability to create complex visualizations for scaled and structured d…
Cooperative Pseudo Labeling for Unsupervised Federated Classification
Kuangpu Guo, Lijun Sheng, Yongcan Yu +3
Unsupervised Federated Learning (UFL) aims to collaboratively train a global model across distributed clients without sharing data or accessing label information. Previous UFL work…
Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation
Weinan He, Zilei Wang, Yixin Zhang
Universal Domain Adaptation (UniDA) focuses on transferring source domain knowledge to the target domain under both domain shift and unknown category shift. Its main challenge lies…
The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models
Lijun Sheng, Jian Liang, Ran He +2
Test-time adaptation (TTA) methods have gained significant attention for enhancing the performance of vision-language models (VLMs) such as CLIP during inference, without requiring…
Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG
Xin Sun, Jianan Xie, Zhongqi Chen +7
Large language models (LLMs) augmented with retrieval systems have significantly advanced natural language processing tasks by integrating external knowledge sources, enabling more…
R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning
Lijun Sheng, Jian Liang, Zilei Wang +1
Vision-language models (VLMs), such as CLIP, have gained significant popularity as foundation models, with numerous fine-tuning methods developed to enhance performance on downstre…
The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs?
Hao Yin, Guangzong Si, Zilei Wang
Contrastive decoding strategies are widely used to reduce object hallucinations in multimodal large language models (MLLMs). These methods work by constructing contrastive samples…
Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference
Hao Yin, Guangzong Si, Zilei Wang
Multimodal large language models (MLLMs) improve performance on vision-language tasks by integrating visual features from pre-trained vision encoders into large language models (LL…
ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Models
Hao Yin, Guangzong Si, Zilei Wang
Contrastive decoding strategies are widely used to mitigate object hallucinations in multimodal large language models (MLLMs). By reducing over-reliance on language priors, these s…
Towards Compatible Fine-tuning for Vision-Language Model Updates
Zhengbo Wang, Jian Liang, Lijun Sheng +3
So far, efficient fine-tuning has become a popular strategy for enhancing the capabilities of foundation models on downstream tasks by learning plug-and-play modules. However, exis…
Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment
Ziang Yan, Zhilin Li, Yinan He +9
Current multimodal large language models (MLLMs) struggle with fine-grained or precise understanding of visuals although they give comprehensive perception and reasoning in a spect…
DIVE: Subgraph Disagreement for Graph Out-of-Distribution Generalization
Xin Sun, Liang Wang, Qiang Liu +2
This paper addresses the challenge of out-of-distribution (OOD) generalization in graph machine learning, a field rapidly advancing yet grappling with the discrepancy between sourc…
LoRA-Pro: Are Low-Rank Adapters Properly Optimized?
Zhengbo Wang, Jian Liang, Ran He +2
Low-rank adaptation, also known as LoRA, has emerged as a prominent method for parameter-efficient fine-tuning of foundation models. Despite its computational efficiency, LoRA stil…