38 citations · 54 across the 27 of their papers we have counts for
36 papers
MedSTP: Preserving Subspace and Transition Evidence for Medical VQA Token Pruning
Mengchen Fan, Qizhen Lan, Xi Xiao +6
Medical vision-language models (VLMs) for visual question answering (VQA) often pass long visual-token sequences to the language model, making visual-token pruning attractive but r…
Posterior Flow Matching
Chenrui Ma, Xi Xiao, Lin Zhao +4
Flow matching learns how to transport noise toward data, but its mean prediction does not directly report the endpoint uncertainty remaining at an intermediate state. This paper in…
Dynamic Hub-and-Spoke Memory for Streaming Video Understanding
Xinru Jiang, Lin Zhao, Xi Xiao +7
Streaming video understanding requires answering questions at arbitrary times over a continuously growing visual stream. The central challenge is to compactly remember long-range h…
Rethinking Layer-Wise Information Allocation for Vision Foundation Model Adaptation
Yuqi Li, Xi Xiao, Yunbei Zhang +6
Vision foundation models are increasingly reused as frozen backbones for downstream visual recognition, making parameter-efficient adaptation a central problem. Prompt-based adapta…
Less Tokens, Better Forecasts: Sparse Residual Routing for Efficient Weather Prediction
Janet Wang, Yunbei Zhang, Lin Zhao +3
Existing ViT-based weather forecasting models apply uniform computation across all spatial tokens, even though nearby atmospheric grid points often contain similar values and large…
Not All Directions Matter: Towards Structured and Task-Aware Low-Rank Model Adaptation
Xi Xiao, Chenrui Ma, Yunbei Zhang +7
Low-Rank Adaptation (LoRA) has become a cornerstone of parameter-efficient fine-tuning (PEFT). Yet, its efficacy is hampered by two fundamental limitations: semantic drift, by trea…
Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection
Xi Xiao, Zhuxuanzi Wang, Mingqiao Mo +6
The deployment of automated pavement defect detection is often hindered by poor cross-domain generalization. Supervised detectors achieve strong in-domain accuracy but require cost…
CTR-LoRA: Curvature-Aware and Trust-Region Guided Low-Rank Adaptation for Large Language Models
Zhuxuanzi Wang, Mingqiao Mo, Xi Xiao +6
Parameter-efficient fine-tuning (PEFT) has become the standard approach for adapting large language models under limited compute and memory budgets. Although previous methods impro…
Towards Foundation Models for Cryo-ET Subtomogram Analysis
Runmin Jiang, Wanyue Feng, Yuntian Yang +11
Cryo-electron tomography (cryo-ET) enables in situ visualization of macromolecular structures, where subtomogram analysis tasks such as classification, alignment, and averaging are…
Prompt-based Adaptation in Large-scale Vision Models: A Survey
Xi Xiao, Yunbei Zhang, Lin Zhao +12
In computer vision, Visual Prompting (VP) and Visual Prompt Tuning (VPT) have recently emerged as lightweight and effective alternatives to full fine-tuning for adapting large-scal…
HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance
Hao Zhang, Zhenjia Li, Runfeng Bao +8
Parameter-Efficient Fine-Tuning (PEFT), especially Low-Rank Adaptation (LoRA), has emerged as a promising approach to fine-tuning large language models(LLMs) while reducing computa…
Stochastic Interpolants via Conditional Dependent Coupling
Chenrui Ma, Xi Xiao, Tianyang Wang +2
Existing image generation models face critical challenges regarding the trade-off between computation and fidelity. Specifically, models relying on a pretrained Variational Autoenc…
Sensitivity-LoRA: Low-Load Sensitivity-Based Fine-Tuning for Large Language Models
Hao Zhang, Bo Huang, Zhenjia Li +6
Large Language Models (LLMs) have transformed both everyday life and scientific research. However, adapting LLMs from general-purpose models to specialized tasks remains challengin…
Information-Theoretic Graph Fusion with Vision-Language-Action Model for Policy Reasoning and Dual Robotic Control
Shunlei Li, Longsen Gao, Jin Wang +5
Teaching robots dexterous skills from human videos remains challenging due to the reliance on low-level trajectory imitation, which fails to generalize across object types, spatial…
Visual Instance-aware Prompt Tuning
Xi Xiao, Yunbei Zhang, Xingjian Li +5
Visual Prompt Tuning (VPT) has emerged as a parameter-efficient fine-tuning paradigm for vision transformers, with conventional approaches utilizing dataset-level prompts that rema…
RoadBench: A Vision-Language Foundation Model and Benchmark for Road Damage Understanding
Xi Xiao, Yunbei Zhang, Janet Wang +9
Accurate road damage detection is crucial for timely infrastructure maintenance and public safety, but existing vision-only datasets and models lack the rich contextual understandi…
FOCUS: Fused Observation of Channels for Unveiling Spectra
Xi Xiao, Aristeidis Tsaris, Anika Tabassum +4
Hyperspectral imaging (HSI) captures hundreds of narrow, contiguous wavelength bands, making it a powerful tool in biology, agriculture, and environmental monitoring. However, inte…
ETT-CKGE: Efficient Task-driven Tokens for Continual Knowledge Graph Embedding
Lijing Zhu, Qizhen Lan, Qing Tian +8
Continual Knowledge Graph Embedding (CKGE) seeks to integrate new knowledge while preserving past information. However, existing methods struggle with efficiency and scalability du…
Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions
Chenrui Ma, Xi Xiao, Tianyang Wang +1
Current text-driven image editing methods typically follow one of two directions: relying on large-scale, high-quality editing pair datasets to improve editing precision and divers…
Describe Anything in Medical Images
Xi Xiao, Yunbei Zhang, Thanh-Huy Nguyen +10
Localized image captioning has made significant progress with models like the Describe Anything Model (DAM), which can generate detailed region-specific descriptions without explic…
TWIG: Two-Step Image Generation using Segmentation Masks in Diffusion Models
Mazharul Islam Rakib, Showrin Rahman, Joyanta Jyoti Mondal +4
In today's age of social media and marketing, copyright issues can be a major roadblock to the free sharing of images. Generative AI models have made it possible to create high-qua…
CryoCCD: Conditional Cycle-consistent Diffusion with Biophysical Modeling for Cryo-EM Synthesis
Runmin Jiang, Genpei Zhang, Yuntian Yang +10
Single-particle cryo-electron microscopy (cryo-EM) has become a cornerstone of structural biology, enabling near-atomic resolution analysis of macromolecules through advanced compu…
MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding
Yuxiang Wei, Yanteng Zhang, Xi Xiao +3
Decoding visual experiences from fMRI offers a powerful avenue to understand human perception and develop advanced brain-computer interfaces. However, current progress often priori…
ORBIT-2: Scaling Exascale Vision Foundation Models for Weather and Climate Downscaling
Xiao Wang, Jong-Youl Choi, Takuya Kurihaya +15
Sparse observations and coarse-resolution climate models limit effective regional decision-making, underscoring the need for robust downscaling. However, existing AI methods strugg…