6 citations · 54 across the 65 of their papers we have counts for
68 papers
DRT: Dense Reasoning Trace for Efficient and Grounded Multimodal Reasoning
Wan Xu, Yuanfan Guo, Kevin Han +2
Despite the remarkable progress in Multimodal Large Language Models (MLLMs), prevailing Chain-of-Thought (CoT) paradigms remain confined to the natural-language expression space. C…
Improving Complex Moiré Removal with Generative Supervision
Xinyang Gu, Zhilu Zhang, Honglei Xu +3
The availability of high-quality paired data is essential for training learning-based image demoiréing models. However, it remains challenging for existing datasets to encompass th…
GS-RealBlur: A Flexible Data Acquisition Framework for Real-World Image Deblurring
Mingyang Chen, Zhilu Zhang, Honglei Xu +3
High-quality, large-scale paired data is essential for training learning-based image deblurring models. However, synthetic blurry images generally lack realism, while real-world ca…
FedSmoothLoRA: Toward Smoother and Faster Convergence in Federated Low-Rank Adaptation
Zehao Wang, Guanglei Yang, Yihan Zeng +4
Federated fine-tuning of foundation models with Low-Rank Adaptation (LoRA) provides an efficient solution for reducing communication and computation costs while preserving data loc…
CGL: Advancing Continual GUI Learning via Reinforcement Fine-Tuning
Zhenquan Yao, Zitong Huang, Yihan Zeng +5
Graphical User Interface (GUI) Agents, benefiting from recent advances in multimodal large language models (MLLM), have achieved significant development. However, due to the freque…
Mind the Generative Details: Direct Localized Detail Preference Optimization for Video Diffusion Models
Zitong Huang, Kaidong Zhang, Yukang Ding +4
Aligning text-to-video diffusion models with human preferences is crucial for generating high-quality videos. Existing Direct Preference Otimization (DPO) methods rely on multi-sam…
PhysWorld: From Real Videos to World Models of Deformable Objects via Physics-Aware Demonstration Synthesis
Yu Yang, Zhilu Zhang, Xiang Zhang +3
Interactive world models that simulate object dynamics are crucial for robotics, VR, and AR. However, it remains a significant challenge to learn physics-consistent dynamics models…
SelfHVD: Self-Supervised Handheld Video Deblurring
Honglei Xu, Zhilu Zhang, Junjie Fan +2
Shooting video with handheld shooting devices often results in blurry frames due to shaking hands and other instability factors. Although previous video deblurring methods have ach…
Text to Image for Multi-Label Image Recognition with Joint Prompt-Adapter Learning
Chun-Mei Feng, Kai Yu, Xinxing Xu +4
Benefited from image-text contrastive learning, pre-trained vision-language models, e.g., CLIP, allow to direct leverage texts as images (TaI) for parameter-efficient fine-tuning (…
Image Demoiréing Using Dual Camera Fusion on Mobile Phones
Yanting Mei, Zhilu Zhang, Xiaohe Wu +1
When shooting electronic screens, moiré patterns usually appear in captured images, which seriously affects the image quality. Existing image demoiréing methods face great challeng…
MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM
Bowen Dong, Minheng Ni, Zitong Huang +3
Multimodal hallucination in multimodal large language models (MLLMs) restricts the correctness of MLLMs. However, multimodal hallucinations are multi-sourced and arise from diverse…
Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning
Minheng Ni, Zhengyuan Yang, Linjie Li +4
Recent advances in large language models have significantly improved textual reasoning through the effective use of Chain-of-Thought (CoT) and reinforcement learning. However, exte…
Pseudo-Label Guided Real-World Image De-weathering: A Learning Framework with Imperfect Supervision
Heming Xu, Xiaohui Liu, Zhilu Zhang +3
Real-world image de-weathering aims at removingvarious undesirable weather-related artifacts, e.g., rain, snow,and fog. To this end, acquiring ideal training pairs is crucial.Exist…
Measurement of LLM's Philosophies of Human Nature
Minheng Ni, Ennan Wu, Zidong Gong +6
The widespread application of artificial intelligence (AI) in various tasks, along with frequent reports of conflicts or violations involving AI, has sparked societal concerns abou…
Segmenting Objectiveness and Task-awareness Unknown Region for Autonomous Driving
Mi Zheng, Guanglei Yang, Zitong Huang +3
With the emergence of transformer-based architectures and large language models (LLMs), the accuracy of road scene perception has substantially advanced. Nonetheless, current road…
ACE: Anti-Editing Concept Erasure in Text-to-Image Models
Zihao Wang, Yuxiang Wei, Fan Li +3
Recent advance in text-to-image diffusion models have significantly facilitated the generation of high-quality images, but also raising concerns about the illegal creation of harmf…
MetricDepth: Enhancing Monocular Depth Estimation with Deep Metric Learning
Chunpu Liu, Guanglei Yang, Wangmeng Zuo +1
Deep metric learning aims to learn features relying on the consistency or divergence of class labels. However, in monocular depth estimation, the absence of a natural definition of…
Multi-Modality Driven LoRA for Adverse Condition Depth Estimation
Guanglei Yang, Rui Tian, Yongqiang Zhang +3
The autonomous driving community is increasingly focused on addressing corner case problems, particularly those related to ensuring driving safety under adverse conditions (e.g., n…
Unprejudiced Training Auxiliary Tasks Makes Primary Better: A Multi-Task Learning Perspective
Yuanze Li, Chun-Mei Feng, Qilong Wang +2
Human beings can leverage knowledge from relative tasks to improve learning on a primary task. Similarly, multi-task learning methods suggest using auxiliary tasks to enhance a neu…
Diffusion-Enhanced Test-time Adaptation with Text and Image Augmentation
Chun-Mei Feng, Yuanyang He, Jian Zou +6
Existing test-time prompt tuning (TPT) methods focus on single-modality data, primarily enhancing images and using confidence ratings to filter out inaccurate images. However, whil…
MR-GDINO: Efficient Open-World Continual Object Detection
Bowen Dong, Zitong Huang, Guanglei Yang +2
Open-world (OW) recognition and detection models show strong zero- and few-shot adaptation abilities, inspiring their use as initializations in continual learning methods to improv…
UniRestorer: Universal Image Restoration via Adaptively Estimating Image Degradation at Proper Granularity
Jingbo Lin, Zhilu Zhang, Wenbo Li +4
Recently, considerable progress has been made in all-in-one image restoration. Generally, existing methods can be degradation-agnostic or degradation-aware. However, the former are…
Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation
Qizhang Li, Xiaochen Yang, Wangmeng Zuo +1
Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstratin…
LPT++: Efficient Training on Mixture of Long-tailed Experts
Bowen Dong, Pan Zhou, Wangmeng Zuo
We introduce LPT++, a comprehensive framework for long-tailed classification that combines parameter-efficient fine-tuning (PEFT) with a learnable model ensemble. LPT++ enhances fr…