2 citations · 6 across the 20 of their papers we have counts for
20 papers
DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off
Xiaofan Li, Ming Yang, Zhiyuan Ma +9
Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed significant advances in the reasoning capabilities of Large Language Models (LLMs). However, effectively managin…
Direct Segmentation without Logits Optimization for Training-Free Open-Vocabulary Semantic Segmentation
Jiahao Li, Yang Lu, Yachao Zhang +3
Open-vocabulary semantic segmentation (OVSS) aims to segment arbitrary category regions in images using open-vocabulary prompts, necessitating that existing methods possess pixel-l…
PC-CrossDiff: Point-Cluster Dual-Level Cross-Modal Differential Attention for Unified 3D Referring and Segmentation
Wenbin Tan, Jiawen Lin, Fangyong Wang +4
3D Visual Grounding (3DVG) aims to localize the referent of natural language referring expressions through two core tasks: Referring Expression Comprehension (3DREC) and Segmentati…
Continual-NExT: A Unified Comprehension And Generation Continual Learning Framework
Jingyang Qiao, Zhizhong Zhang, Xin Tan +3
Dual-to-Dual MLLMs refer to Multimodal Large Language Models, which can enable unified multimodal comprehension and generation through text and image modalities. Although exhibitin…
Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability Perspective
Jiahao Li, Yang Lu, Yachao Zhang +4
Open-vocabulary semantic segmentation (OVSS) employs pixel-level vision-language alignment to associate category-related prompts with corresponding pixels. A key challenge is enhan…
Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation
Jiahao Li, Yang Lu, Yachao Zhang +3
Open-vocabulary semantic segmentation (OVSS) conducts pixel-level classification via text-driven alignment, where the domain discrepancy between base category training and open-voc…
SeqVLM: Proposal-Guided Multi-View Sequences Reasoning via VLM for Zero-Shot 3D Visual Grounding
Jiawen Lin, Shiran Bian, Yihang Zhu +4
3D Visual Grounding (3DVG) aims to localize objects in 3D scenes using natural language descriptions. Although supervised methods achieve higher accuracy in constrained settings, z…
T2S: Tokenized Skill Scaling for Lifelong Imitation Learning
Hongquan Zhang, Jingyu Gong, Zhizhong Zhang +3
The main challenge in lifelong imitation learning lies in the balance between mitigating catastrophic forgetting of previous skills while maintaining sufficient capacity for acquir…
One-for-More: Continual Diffusion Model for Anomaly Detection
Xiaofan Li, Xin Tan, Zhuo Chen +8
With the rise of generative models, there is a growing interest in unifying all tasks within a generative framework. Anomaly detection methods also fall into this scope and utilize…
Fusion-then-Distillation: Toward Cross-modal Positive Distillation for Domain Adaptive 3D Semantic Segmentation
Yao Wu, Mingwei Xing, Yachao Zhang +2
In cross-modal unsupervised domain adaptation, a model trained on source-domain data (e.g., synthetic) is adapted to target-domain data (e.g., real-world) without access to target…
Large Continual Instruction Assistant
Jingyang Qiao, Zhizhong Zhang, Xin Tan +3
Continual Instruction Tuning (CIT) is adopted to continually instruct Large Models to follow human intent data by data. It is observed that existing gradient update would heavily d…
Data-free Distillation with Degradation-prompt Diffusion for Multi-weather Image Restoration
Pei Wang, Xiaotong Luo, Yuan Xie +1
Multi-weather image restoration has witnessed incredible progress, while the increasing model capacity and expensive data acquisition impair its applications in memory-limited devi…
Mutual Information Guided Optimal Transport for Unsupervised Visible-Infrared Person Re-identification
Zhizhong Zhang, Jiangming Wang, Xin Tan +4
Unsupervised visible infrared person re-identification (USVI-ReID) is a challenging retrieval task that aims to retrieve cross-modality pedestrian images without using any label in…
Exploring the Untouched Sweeps for Conflict-Aware 3D Segmentation Pretraining
Tianfang Sun, Zhizhong Zhang, Xin Tan +2
LiDAR-camera 3D representation pretraining has shown significant promise for 3D perception tasks and related applications. However, two issues widely exist in this framework: 1) So…
Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception
Haoming Chen, Zhizhong Zhang, Yanyun Qu +3
An effective pre-training framework with universal 3D representations is extremely desired in perceiving large-scale dynamic scenes. However, establishing such an ideal framework t…
Robust Pseudo-label Learning with Neighbor Relation for Unsupervised Visible-Infrared Person Re-Identification
Xiangbo Yin, Jiangming Shi, Yachao Zhang +4
Unsupervised Visible-Infrared Person Re-identification (USVI-ReID) presents a formidable challenge, which aims to match pedestrian images across visible and infrared modalities wit…
Gradient Projection For Continual Parameter-Efficient Tuning
Jingyang Qiao, Zhizhong Zhang, Xin Tan +4
Parameter-efficient tunings (PETs) have demonstrated impressive performance and promising perspectives in training large models, while they are still confronted with a common probl…
PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection
Xiaofan Li, Zhizhong Zhang, Xin Tan +4
The vision-language model has brought great improvement to few-shot industrial anomaly detection, which usually needs to design of hundreds of prompts through prompt engineering. F…
Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification
Jiangming Shi, Xiangbo Yin, Yachao Zhang +3
Unsupervised visible-infrared person re-identification (USVI-ReID) aims to match specified people in infrared images to visible images without annotations, and vice versa. USVI-ReI…
Multi-Memory Matching for Unsupervised Visible-Infrared Person Re-Identification
Jiangming Shi, Xiangbo Yin, Yeyun Chen +4
Unsupervised visible-infrared person re-identification (USL-VI-ReID) is a promising yet challenging retrieval task. The key challenges in USL-VI-ReID are to effectively generate ps…