21 citations · 28 across the 22 of their papers we have counts for
28 papers
OPUS-V2: Bridging the Gap between Sparse Points and Dense Voxels
Jiabao Wang, Qiang Meng, Liujiang Yan +3
The point-based occupancy prediction paradigm has achieved an attractive trade-off between accuracy and efficiency by modeling 3D space sparsely. However, its predictions inherentl…
Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs
Yunheng Li, Guohong Mu, Hao Li +4
Multimodal large language models (MLLMs) have become a prevailing paradigm for unified video perception. However, post-training on large multi-task datasets remains challenging, as…
Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought
Yunheng Li, Hangyi Kuang, Hengrui Zhang +4
Multimodal Chain-of-Thought (CoT) reasoning requires large vision-language models to construct reasoning trajectories that interleave perceptual grounding with multi-step inference…
Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions
Yunheng Li, Hengrui Zhang, Meng-Hao Guo +5
Universal video understanding requires modeling fine-grained visual and audio information over time in diverse real-world scenarios. However, the performance of existing models is…
GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics
Modi Jin, Yiming Zhang, Boyuan Sun +3
This paper presents GeoAgent, a model capable of reasoning closely with humans and deriving fine-grained address conclusions. Previous RL-based methods have achieved breakthroughs…
The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignment
Ziheng Ouyang, Yiren Song, Yaoli Liu +4
Previous works have explored various customized generation tasks given a reference image, but they still face limitations in generating consistent fine-grained details. In this pap…
GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation
Yuhao Wan, Lijuan Liu, Jingzhi Zhou +6
Previous works that leverage video models for image-to-3D scene generation often suffer from geometric distortions and blurry content. Using video generation models to implicitly m…
TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs
Yunheng Li, Jing Cheng, Shaoyong Jia +4
This paper introduces TempSamp-R1, a new reinforcement fine-tuning framework designed to improve the effectiveness of adapting multimodal large language models (MLLMs) to video tem…
OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic Segmentation
Bo-Wen Yin, Jiao-Long Cao, Xuying Zhang +3
Recent research on representation learning has proved the merits of multi-modal clues for robust semantic segmentation. Nevertheless, a flexible pretrain-and-finetune pipeline for…
OneVAE: Joint Discrete and Continuous Optimization Helps Discrete Video VAE Train Better
Yupeng Zhou, Zhen Li, Ziheng Ouyang +8
Encoding videos into discrete tokens could align with text tokens to facilitate concise and unified multi-modal LLMs, yet introducing significant spatiotemporal compression compare…
Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment
Shi-Chen Zhang, Yunheng Li, Yu-Huan Wu +2
Semantic segmentation is fundamental to vision systems requiring pixel-level scene understanding, yet deploying it on resource-constrained devices demands efficient architectures.…
A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models
Quan-Sheng Zeng, Yunheng Li, Qilong Wang +4
Visual token compression is critical for Large Vision-Language Models (LVLMs) to efficiently process high-resolution inputs. Existing methods that typically adopt fixed compression…
Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis
Hongyu Sun, Qiuhong Ke, Ming Cheng +4
This paper proposes a general solution to enable point cloud recognition models to handle distribution shifts at test time. Unlike prior methods, which rely heavily on training dat…
DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation
Bo-Wen Yin, Jiao-Long Cao, Ming-Ming Cheng +1
Recent advances in scene understanding benefit a lot from depth maps because of the 3D geometry information, especially in complex conditions (e.g., low light and overexposed). Exi…
Re-Aligning Language to Visual Objects with an Agentic Workflow
Yuming Chen, Jiangyan Feng, Haodong Zhang +6
Language-based object detection (LOD) aims to align visual objects with language expressions. A large amount of paired data is utilized to improve LOD model generalizations. During…
KAC: Kolmogorov-Arnold Classifier for Continual Learning
Yusong Hu, Zichen Liang, Fei Yang +3
Continual learning requires models to train continuously across consecutive tasks without forgetting. Most existing methods utilize linear classifiers, which struggle to maintain a…
TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction
Xuying Zhang, Yutong Liu, Yangguang Li +8
We present TAR3D, a novel framework that consists of a 3D-aware Vector Quantized-Variational AutoEncoder (VQ-VAE) and a Generative Pre-trained Transformer (GPT) to generate high-qu…
High-Quality Mask Tuning Matters for Open-Vocabulary Segmentation
Quan-Sheng Zeng, Yunheng Li, Daquan Zhou +3
Open-vocabulary image segmentation has been advanced through the synergy between mask generators and vision-language models like Contrastive Language-Image Pre-training (CLIP). Pre…
Unbiased Region-Language Alignment for Open-Vocabulary Dense Prediction
Yunheng Li, Yuxuan Li, Quansheng Zeng +3
Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated impressive zero-shot recognition capability, but still underperform in dense prediction tasks. Self-disti…
OPUS: Occupancy Prediction Using a Sparse Set
Jiabao Wang, Zhaojiang Liu, Qiang Meng +6
Occupancy prediction, aiming at predicting the occupancy status within voxelized 3D environment, is quickly gaining momentum within the autonomous driving community. Mainstream occ…
ControlSR: Taming Diffusion Models for Consistent Real-World Image Super Resolution
Yuhao Wan, Peng-Tao Jiang, Qibin Hou +4
We present ControlSR, a new method that can tame Diffusion Models for consistent real-world image super-resolution (Real-ISR). Previous Real-ISR models mostly focus on how to activ…
Towards Stable 3D Object Detection
Jiabao Wang, Qiang Meng, Guochao Liu +4
In autonomous driving, the temporal stability of 3D object detection greatly impacts the driving safety. However, the detection stability cannot be accessed by existing metrics suc…
Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation
Yunheng Li, ZhongYu Li, Quansheng Zeng +2
Pre-trained vision-language models, e.g., CLIP, have been successfully applied to zero-shot semantic segmentation. Existing CLIP-based approaches primarily utilize visual features…
StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation
Yupeng Zhou, Daquan Zhou, Ming-Ming Cheng +2
For recent diffusion-based generative models, maintaining consistent content across a series of generated images, especially those containing subjects and complex details, presents…