29 citations · 76 across the 23 of their papers we have counts for
24 papers
SERO: Learning from Executable Oracle Continuations for Long-Horizon Agentic Reinforcement Learning
Dingyi Rong, Yue Shi, Chaofan Ma +5
Long-horizon agentic RL is constrained by the futures visited by the current policy. When rollouts fail to reach useful behaviors, improved credit assignment cannot provide supervi…
TRACE-Bench: Decomposing and Diagnosing Multi-Reference Image Generation
Haoran Wang, Chaofan Ma, Ran Yi +1
Despite recent advances in unified multimodal models for multi-reference image generation, existing benchmarks remain organized around predefined task types (e.g., "subject composi…
H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models
Dingyi Rong, Yue Shi, Chaofan Ma +6
Large-scale manipulation data is essential for robot learning, yet collecting robot demonstrations remains expensive and difficult to scale. Meanwhile, abundant egocentric human ma…
Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning
Chaofan Ma, Zhenjie Mao, Yuhuan Yang +5
Spatial reasoning from egocentric videos is inherently challenging because the observable evidence is constrained by the camera trajectory. Existing methods rely on single-turn inf…
Robo2Process: Benchmarking and Learning Process-Aware Understanding in Vision-Language Robotic Manipulation
Dayu Xia, Yue Shi, Yao Mu +7
Vision-language models (VLMs) used as robotic critics, reward generators, and failure detectors must understand how manipulation unfolds, not only whether it succeeds. Yet fine-gra…
GenMask: Adapting DiT for Segmentation via Direct Mask Generation
Yuhuan Yang, Xianwei Zhuang, Yuxuan Cai +6
Recent approaches for segmentation have leveraged pretrained generative models as feature extractors, treating segmentation as a downstream adaptation task via indirect feature ret…
UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing
Dianyi Wang, Chaofan Ma, Feng Han +8
Unified multimodal models often struggle with complex synthesis tasks that demand deep reasoning, and typically treat text-to-image generation and image editing as isolated capabil…
DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing
Dianyi Wang, Ruihang Li, Feng Han +17
Current unified multimodal models for image generation and editing typically rely on massive parameter scales (e.g., >10B), entailing prohibitive training costs and deployment foot…
SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation
Zhenjie Mao, Yuhuan Yang, Chaofan Ma +4
Referring Image Segmentation (RIS) aims to segment the target object in an image given a natural language expression. While recent methods leverage pre-trained vision backbones and…
Unsupervised Domain Adaptation via Similarity-based Prototypes for Cross-Modality Segmentation
Ziyu Ye, Chen Ju, Chaofan Ma +1
Deep learning models have achieved great success on various vision challenges, but a well-trained model would face drastic performance degradation when applied to unseen data. Sinc…
MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition
Yuhuan Yang, Chaofan Ma, Zhenjie Mao +3
Video understanding is a complex challenge that requires effective modeling of spatial-temporal dynamics. With the success of image foundation models (IFMs) in image understanding,…
Contrast-Unity for Partially-Supervised Temporal Sentence Grounding
Haicheng Wang, Chen Ju, Weixiong Lin +4
Temporal sentence grounding aims to detect event timestamps described by the natural language query from given untrimmed videos. The existing fully-supervised setting achieves grea…
ReMamber: Referring Image Segmentation with Mamba Twister
Yuhuan Yang, Chaofan Ma, Jiangchao Yao +3
Referring Image Segmentation~(RIS) leveraging transformers has achieved great success on the interpretation of complex visual-language tasks. However, the quadratic computation cos…
Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation
Fei Zhang, Tianfei Zhou, Boyang Li +6
This paper studies the problem of weakly open-vocabulary semantic segmentation (WOVSS), which learns to segment objects of arbitrary classes using mere image-text pairs. Existing w…
AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation
Chaofan Ma, Yuhuan Yang, Chen Ju +3
Open-vocabulary semantic segmentation is a challenging task that requires segmenting novel object categories at inference time. Recent studies have explored vision-language pre-tra…
Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation
Jinxiang Liu, Chen Ju, Chaofan Ma +3
The goal of the audio-visual segmentation (AVS) task is to segment the sounding objects in the video frames using audio cues. However, current fusion-based methods have the perform…
Multi-Modal Prototypes for Open-World Semantic Segmentation
Yuhuan Yang, Chaofan Ma, Chen Ju +4
In semantic segmentation, generalizing a visual system to both seen categories and novel categories at inference time has always been practically valuable yet challenging. To enabl…
Annotation-free Audio-Visual Segmentation
Jinxiang Liu, Yu Wang, Chen Ju +3
The objective of Audio-Visual Segmentation (AVS) is to localise the sounding objects within visual scenes by accurately predicting pixel-wise segmentation masks. To tackle the task…
Boundary-aware Supervoxel-level Iteratively Refined Interactive 3D Image Segmentation with Multi-agent Reinforcement Learning
Chaofan Ma, Qisen Xu, Xiangfeng Wang +4
Interactive segmentation has recently been explored to effectively and efficiently harvest high-quality segmentation masks by iteratively incorporating user hints. While iterative…
DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery
Chaofan Ma, Yuhuan Yang, Chen Ju +5
Learning from a large corpus of data, pre-trained models have achieved impressive progress nowadays. As popular generative pre-training, diffusion models capture both low-level vis…
Constraint and Union for Partially-Supervised Temporal Sentence Grounding
Chen Ju, Haicheng Wang, Jinxiang Liu +5
Temporal sentence grounding aims to detect the event timestamps described by the natural language query from given untrimmed videos. The existing fully-supervised setting achieves…
DARF: Depth-Aware Generalizable Neural Radiance Field
Yue Shi, Dingyi Rong, Chang Chen +3
Neural Radiance Field (NeRF) has revolutionized novel-view rendering tasks and achieved impressive results. However, the inefficient sampling and per-scene optimization hinder its…
Open-vocabulary Semantic Segmentation with Frozen Vision-Language Models
Chaofan Ma, Yuhuan Yang, Yanfeng Wang +2
When trained at a sufficient scale, self-supervised learning has exhibited a notable ability to solve a wide range of visual or language understanding tasks. In this paper, we inve…
Transforming the Interactive Segmentation for Medical Imaging
Wentao Liu, Chaofan Ma, Yuhuan Yang +2
The goal of this paper is to interactively refine the automatic segmentation on challenging structures that fall behind human performance, either due to the scarcity of available a…