3 citations · 4 across the 34 of their papers we have counts for
38 papers
Self-Aligned Forcing: Streaming Video Diffusion with Differentiable Noisy History
Weiqiang Wang, Zhuokun Chen, Yusheng Dai +5
Autoregressive video diffusion enables interactive streaming generation, but suffers from error accumulation over long rollouts. Self-rollout training reduces exposure bias, yet fi…
TUE-Detector: A Tool-Using Expert MLLM-Based Detector for AI-Generated Videos
Yichen Wu, Haoxuan Qu, Yongxing Dai +5
AI-generated video detection, which aims to distinguish AI-generated videos from real ones, has recently received increasing research attention. To perform this task reliably, a ke…
CANVAS: Consistency-Aware Navigation via Visual Adaptive Sampling for Long-Context Text-to-SVG Generation
Yichen Wu, Haoxuan Qu, Yihang Lou +2
Autoregressive large models have recently advanced Text-to-SVG generation from simple icons to complex, long-context graphics, yet standard autoregressive decoding often fails to m…
Boot-and-Feedback Framework for Generalist-Expert Model Collaboration in Breast Ultrasound Diagnosis
Ming Cheng, Hongyu Sun, Zhaolin Chen +3
Breast ultrasound (BUS) is widely used for breast cancer diagnosis yet remains operator-dependent. While deep learning shows promise, ensuring diagnostic reliability and interpreta…
Test-Time Hallucination Control in Large Vision-Language Models
Mehran Tamjidi, Hamidreza Dastmalchi, Ali Cheraghian +3
Object Hallucination in large vision-language models (LVLMs), where models generate non-factual content about input images, remains a critical barrier to their reliability in real-…
Introspective Attention Modulation for Safe Text-to-Image Generation
Basim Azam, Hossein Rahmani, Naveed Akhtar
State-of-the-art flow based text-to-image (T2I) models exhibit remarkable generative abilities but remain vulnerable to producing unsafe content. Prior safety efforts range from co…
Beyond Global Editing: Per-Instance Disentangled Subspaces for Training-Free Hallucination Mitigation in LVLMs
Ali Cheraghian, Hamidreza Dastmalchi, Hamed Barzamini +4
Recent advances in large vision-language models (LVLMs) have enabled powerful multimodal reasoning by integrating visual encoders with large language models (LLMs). However, their…
HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Models
Yu Xue, Haoxuan Qu, Zhuoling Li +5
Training-free text-to-high-resolution image generation has recently attracted growing research attention. However, existing studies on this task primarily focus on adapting off-the…
Training-free Controllable Human Motion Generation under Heterogeneous Constraints
Xiaofei Hui, Bo Yan, Haoxuan Qu +2
Training-free controllable motion generation has attracted growing interest for enabling flexible constraint enforcement without constraint-specific training. However, existing tra…
TraMP-LLaMA: Generative Interpretability with Decoupled Instruction Tuning for Facial Expression Quality Assessment
Shuchao Duan, Alan Whone, Hossein Rahmani +2
Existing facial expression quality assessment (FEQA) methods typically produce only a severity score, without explicitly communicating the observable facial motion evidence that su…
SkelHCC: A Hyperbolic CLIP-Driven Cache Adaptation Framework for Skeleton-based One-Shot Action Recognition
Yanan Liu, Anqi Zhu, Jingmin Zhu +6
Skeleton-based action recognition aims to understand human behaviors from body joint sequences and is especially challenging in the one-shot setting, where only a single labeled ex…
ToolFG: Towards Well-Grounded Fine-Grained Image Classification
Yu Xue, Haoxuan Qu, Zhuoling Li +4
Fine-grained image classification (FGIC) has broad applications and has attracted significant research attention. In this paper, we explore a novel paradigm for solving FGIC by pro…
NDPP-Grasp: Non-Differentiable Physical Plausibility Constraint-Guided Task-Oriented Dexterous Grasp Generation
Qiuchi Xiang, Haoxuan Qu, Hossein Rahmani +1
Task-oriented dexterous grasp generation aims to produce dexterous grasp poses that are both physically plausible and functionally suitable for specified manipulation tasks. Existi…
Translating Signals to Languages for sEMG-Based Activity Recognition
Ming Wang, Haoxuan Qu, Qiuhong Ke +3
Surface electromyography (sEMG) signal-based activity recognition has attracted increasing research attention in recent years. To develop accurate sEMG signal-based activity recogn…
New Wide-Net-Casting Jailbreak Attacks Risk Large Models
Qiuchi Xiang, Haoxuan Qu, Hossein Rahmani +1
Jailbreak attacks on large models have drawn growing attention due to their close ties to societal safety. This work identifies a practical yet unexplored jailbreak scenario, the w…
MicroscopyMatching: Towards a Ready-to-use Framework for Microscopy Image Analysis in Diverse Conditions
Xiaofei Hui, Haoxuan Qu, Hossein Rahmani +3
Analyzing microscopy images to extract biological object properties (e.g., their morphological organization, temporal dynamics, and population density) is fundamental to various bi…
Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration
Zhuoling Li, Jiarui Zhang, Ping Hu +4
Method illustrations (MIs) play a crucial role in conveying the core ideas of scientific papers, yet their generation remains a labor-intensive process. Here, we take inspiration f…
DiffGraph: An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image Generation
Zhuoling Li, Hossein Rahmani, Jiarui Zhang +5
The rapid growth of the text-to-image (T2I) community has fostered a thriving online ecosystem of expert models, which are variants of pretrained diffusion models specialized for d…
When Visual Privacy Protection Meets Multimodal Large Language Models
Xiaofei Hui, Qian Wu, Haoxuan Qu +3
The emergence of Multimodal Large Language Models (MLLMs) and the widespread usage of MLLM cloud services such as GPT-4V raised great concerns about privacy leakage in visual data.…
Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussions
Qiuchi Xiang, Haoxuan Qu, Hossein Rahmani +1
Multi-agent discussions have been widely adopted, motivating growing efforts to develop attacks that expose their vulnerabilities. In this work, we study a practical yet largely un…
Learning to Generate Cross-Task Unexploitable Examples
Haoxuan Qu, Qiuchi Xiang, Yujun Cai +4
Unexploitable example generation aims to transform personal images into their unexploitable (unlearnable) versions before they are uploaded online, thereby preventing unauthorized…
TSkel-Mamba: Temporal Dynamic Modeling via State Space Model for Human Skeleton-based Action Recognition
Yanan Liu, Jun Liu, Hao Zhang +4
Skeleton-based action recognition has garnered significant attention in the computer vision community. Inspired by the recent success of the selective state-space model (SSM) Mamba…
Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation
Jingmin Zhu, Anqi Zhu, Hossein Rahmani +3
We introduce Skeleton-Cache, the first training-free test-time adaptation framework for skeleton-based zero-shot action recognition (SZAR), aimed at improving model generalization…
DynaPURLS: Dynamic Refinement of Part-Aware Representations for Skeleton-Based Zero-Shot Action Recognition
Jingmin Zhu, Anqi Zhu, James Bailey +5
Zero-shot skeleton-based action recognition (ZS-SAR) is fundamentally constrained by prevailing approaches that rely on aligning skeleton features with static, class-level semantic…