48 citations · 128 across the 22 of their papers we have counts for
23 papers
Learning from Hard Prompts: Difficulty-aware Advantage Amplification in Dynamic Sampling
Siyuan Gan, Yuhan Li, Xiran Wang +6
Decoupled Clip and Dynamic Sampling Policy Optimization (DAPO) is a prominent variant of Group Relative Policy Optimization (GRPO). DAPO introduces several improvements over GRPO.…
SigLIP-HD by Fine-to-Coarse Supervision
Lihe Yang, Zhen Zhao, Hengshuang Zhao
High-quality visual representation is a long-standing pursuit in computer vision. In the context of multimodal LLMs (MLLMs), feeding higher-resolution images can produce more fine-…
UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation
Lihe Yang, Zhen Zhao, Hengshuang Zhao
Semi-supervised semantic segmentation (SSS) aims at learning rich visual knowledge from cheap unlabeled images to enhance semantic segmentation capability. Among recent works, UniM…
Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation
Yunxin Li, Haoyuan Shi, Baotian Hu +5
Traditional animation generation methods depend on training generative models with human-labelled data, entailing a sophisticated multi-stage pipeline that demands substantial huma…
Depth Anything V2
Lihe Yang, Bingyi Kang, Zilong Huang +4
This work presents Depth Anything V2. Without pursuing fancy techniques, we aim to reveal crucial findings to pave the way towards building a powerful monocular depth estimation mo…
SOEDiff: Efficient Distillation for Small Object Editing
Yiming Wu, Qihe Pan, Zhen Zhao +3
In this paper, we delve into a new task known as small object editing (SOE), which focuses on text-based image inpainting within a constrained, small-sized area. Despite the remark…
Roll With the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning
Yue Duan, Zhen Zhao, Lei Qi +3
While semi-supervised learning (SSL) has yielded promising results, the more realistic SSL scenario remains to be explored, in which the unlabeled data exhibits extremely high reco…
Alternate Diverse Teaching for Semi-supervised Medical Image Segmentation
Zhen Zhao, Zicheng Wang, Longyue Wang +3
Semi-supervised medical image segmentation studies have shown promise in training models with limited labeled data. However, current dominant teacher-student based approaches can s…
GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation
Zhanyu Wang, Longyue Wang, Zhen Zhao +7
While the recent advances in Multimodal Large Language Models (MLLMs) constitute a significant leap forward in the field, these models are predominantly confined to the realm of in…
DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model
Zhenhua Xu, Yujia Zhang, Enze Xie +5
Multimodal large language models (MLLMs) have emerged as a prominent area of interest within the research community, given their proficiency in handling and reasoning with non-text…
Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning
Guan Gui, Zhen Zhao, Lei Qi +3
In semi-supervised learning, unlabeled samples can be utilized through augmentation and consistency regularization. However, we observed certain samples, even undergoing strong aug…
Rethinking Data Perturbation and Model Stabilization for Semi-supervised Medical Image Segmentation
Zhen Zhao, Ye Liu, Meng Zhao +3
Studies on semi-supervised medical image segmentation (SSMIS) have seen fast progress recently. Due to the limited labelled data, SSMIS methods mainly focus on effectively leveragi…
Towards Semi-supervised Learning with Non-random Missing Labels
Yue Duan, Zhen Zhao, Lei Qi +3
Semi-supervised learning (SSL) tackles the label missing problem by enabling the effective usage of unlabeled data. While existing SSL methods focus on the traditional setting, a p…
Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning
Lihe Yang, Zhen Zhao, Lei Qi +3
Semi-supervised learning is attracting blooming attention, due to its success in combining unlabeled data. To mitigate potentially incorrect pseudo labels, recent frameworks mostly…
Radio Sources Segmentation and Classification with Deep Learning
Baoqiang Lao, Sumit Jaiswal, Zhen Zhao +4
Modern large radio continuum surveys have high sensitivity and resolution, and can resolve previously undetected extended and diffuse emissions, which brings great challenges for t…
Task-Oriented Multi-Modal Mutual Leaning for Vision-Language Models
Sifan Long, Zhen Zhao, Junkun Yuan +5
Prompt learning has become one of the most efficient paradigms for adapting large pre-trained vision-language models to downstream tasks. Current state-of-the-art methods, like CoO…
Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation
Zicheng Wang, Zhen Zhao, Xiaoxia Xing +3
Semi-supervised semantic segmentation (SSS) has recently gained increasing research interest as it can reduce the requirement for large-scale fully-annotated training data. The cur…
Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation
Zhen Zhao, Lihe Yang, Sifan Long +3
Recent studies on semi-supervised semantic segmentation (SSS) have seen fast progress. Despite their promising performance, current state-of-the-art methods tend to increasingly co…
Instance-specific and Model-adaptive Supervision for Semi-supervised Semantic Segmentation
Zhen Zhao, Sifan Long, Jimin Pi +2
Recently, semi-supervised semantic segmentation has achieved promising performance with a small fraction of labeled data. However, most existing studies treat all unlabeled data eq…
Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers
Sifan Long, Zhen Zhao, Jimin Pi +2
Vision transformers have achieved significant improvements on various vision tasks but their quadratic interactions between tokens significantly reduce computational efficiency. Ma…
MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularization
Yue Duan, Zhen Zhao, Lei Qi +4
The core issue in semi-supervised learning (SSL) lies in how to effectively leverage unlabeled data, whereas most existing methods tend to put a great emphasis on the utilization o…
VLBI Network SIMulator: An Integrated Simulation Tool for Radio Astronomers
Zhen Zhao, Tao An, Baoqiang Lao
In this paper we introduce a software package, the Very Long Baseline Interferometry Network SIMulator (VNSIM), which provides an integrated platform assisting radio astronomers to…
A cosmic microscope to probe the Universe from Present to Cosmic Dawn - dual-element low-frequency space VLBI observatory
Tao An, Sumit Jaiswal, Prashanth Mohan +2
A space-based very long baseline interferometry (VLBI) programme, named as the Cosmic Microscope, is proposed to involve dual VLBI telescopes in the space working together with gia…