84 citations · 172 across the 43 of their papers we have counts for
48 papers
BridgeAfford: Bridging Query-Target Gap for Generalizable 3D Affordance Grounding
Yijie Su, Yakun Zhu, Yi Bin +5
Language-guided 3D affordance grounding aims to localize functional regions on 3D objects according to interaction intents. However, existing methods exhibit poor generalization to…
Understanding and Mitigating Token-Pruning-Induced Vulnerabilities in VLMs
Shuailong Wang, Xinyu Lyu, Shengming Yuan +3
Token-Pruning accelerates Vision-Language Models by removing redundant visual tokens, yet its safety implications remain underexplored. In this work, we present the first comprehen…
Janus-LoRA: A Balanced Low-Rank Adaptation for Continual Learning
Cheng Chen, Pengpeng Zeng, Yuyu Guo +3
Low-Rank Adaptation (LoRA) has emerged as a promising paradigm for Continual Learning. It independently updates its low-rank factors ( and ), creating a composite update to t…
Beyond the Majority: Long-tail Imitation Learning for Robotic Manipulation
Junhong Zhu, Ji Zhang, Jingkuan Song +2
While generalist robot policies hold significant promise for learning diverse manipulation skills through imitation, their performance is often hindered by the long-tail distributi…
Reversible Inversion for Training-Free Exemplar-guided Image Editing
Yuke Li, Lianli Gao, Ji Zhang +5
Exemplar-guided Image Editing (EIE) aims to modify a source image according to a visual reference. Existing approaches often require large-scale pre-training to learn relationships…
More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse Exploration
Xiaoyang Yuan, Yujuan Ding, Yi Bin +5
Reinforcement Learning with Verifiable Rewards (RLVR) is a promising paradigm for enhancing the reasoning ability in Large Language Models (LLMs). However, prevailing methods prima…
Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation
Yi Bin, Tianyi Jiang, Yujuan Ding +5
Large Language Models (LLMs) have demonstrated remarkable reasoning abilities on complex problems using long Chain-of-Thought (CoT) reasoning. However, they often suffer from overt…
Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation
Youguang Xing, Xu Luo, Junlin Xie +3
Generalist robot policies trained on large-scale datasets such as Open X-Embodiment (OXE) demonstrate strong performance across a wide range of tasks. However, they often struggle…
SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism
Beitao Chen, Xinyu Lyu, Lianli Gao +2
By incorporating visual inputs, Multimodal Large Language Models (MLLMs) extend LLMs to support visual reasoning. However, this integration also introduces new vulnerabilities, mak…
A Closer Look at Conditional Prompt Tuning for Vision-Language Models
Ji Zhang, Shihan Wu, Lianli Gao +3
Despite the great promise of Prompt Tuning (PT) in adapting large Vision-Language Pretrained Models (VLPMs) to downstream tasks, they often struggle to overcome the Base-New Tradeo…
Generalizing vision-language models to novel domains: A comprehensive survey
Xinyao Li, Jingjing Li, Fengling Li +3
Recently, vision-language pretraining has emerged as a transformative technique that integrates the strengths of both visual and textual modalities, resulting in powerful vision-la…
Reliable Few-shot Learning under Dual Noises
Ji Zhang, Jingkuan Song, Lianli Gao +2
Recent advances in model pre-training give rise to task adaptation-based few-shot learning (FSL), where the goal is to adapt a pre-trained task-agnostic model for capturing task-sp…
Truth in the Few: High-Value Data Selection for Efficient Multi-Modal Reasoning
Shenshen Li, Xing Xu, Kaiyuan Deng +3
While multi-modal large language models (MLLMs) have made significant progress in complex reasoning tasks via reinforcement learning, it is commonly believed that extensive trainin…
Towards Generalized and Training-Free Text-Guided Semantic Manipulation
Yu Hong, Xiao Cai, Pengpeng Zeng +4
Text-guided semantic manipulation refers to semantically editing an image generated from a source prompt to match a target prompt, enabling the desired semantic changes (e.g., addi…
Attention Hijackers: Detect and Disentangle Attention Hijacking in LVLMs for Hallucination Mitigation
Beitao Chen, Xinyu Lyu, Lianli Gao +2
Despite their success, Large Vision-Language Models (LVLMs) remain vulnerable to hallucinations. While existing studies attribute the cause of hallucinations to insufficient visual…
CFReID: Continual Few-shot Person Re-Identification
Hao Ni, Lianli Gao, Pengpeng Zeng +2
Real-world surveillance systems are dynamically evolving, requiring a person Re-identification model to continuously handle newly incoming data from various domains. To cope with t…
Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves
Shihan Wu, Ji Zhang, Pengpeng Zeng +3
Prompt tuning (PT) has long been recognized as an effective and efficient paradigm for transferring large pre-trained vision-language models (VLMs) to downstream tasks by learning…
GT23D-Bench: A Comprehensive General Text-to-3D Generation Benchmark
Xiao Cai, Sitong Su, Jingkuan Song +6
Text-to-3D (T23D) generation has emerged as a crucial visual generation task, aiming at synthesizing 3D content from textual descriptions. Studies of this task are currently shifti…
SeMv-3D: Towards Concurrency of Semantic and Multi-view Consistency in General Text-to-3D Generation
Xiao Cai, Pengpeng Zeng, Lianli Gao +3
General Text-to-3D (GT23D) generation is crucial for creating diverse 3D content across objects and scenes, yet it faces two key challenges: 1) ensuring semantic consistency betwee…
VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector Quantization
Yixuan Zhou, Xing Xu, Zhe Sun +3
Normalizing flows, a category of probabilistic models famed for their capabilities in modeling complex data distributions, have exhibited remarkable efficacy in unsupervised anomal…
MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct
Run Luo, Haonan Zhang, Longze Chen +13
The development of Multimodal Large Language Models (MLLMs) has seen significant advancements with increasing demands in various fields (e.g., multimodal agents, embodied intellige…
Text-Video Retrieval with Global-Local Semantic Consistent Learning
Haonan Zhang, Pengpeng Zeng, Lianli Gao +4
Adapting large-scale image-text pre-training models, e.g., CLIP, to the video domain represents the current state-of-the-art for text-video retrieval. The primary approaches involv…
CoIN: A Benchmark of Continual Instruction tuNing for Multimodel Large Language Model
Cheng Chen, Junchen Zhu, Xu Luo +3
Instruction tuning represents a prevalent strategy employed by Multimodal Large Language Models (MLLMs) to align with human instructions and adapt to new tasks. Nevertheless, MLLMs…
Towards Redundancy-Free Sub-networks in Continual Learning
Cheng Chen, Jingkuan Song, LianLi Gao +1
Catastrophic Forgetting (CF) is a prominent issue in continual learning. Parameter isolation addresses this challenge by masking a sub-network for each task to mitigate interferenc…