Profiles2023-2026
Dingkang Liang
Huazhong University of Science and Technology
18Papers
0Last author
22Unique co-authors
3First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers18
- Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic ShuffleAuthor 3 of 9ICLR 2026 · 18 citations
- ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance DecodingAuthor 3 of 9ICLR 2026 · 5 citations
- Cook and Clean Together: Teaching Embodied Agents for Parallel Task ExecutionAuthor 1 of 6AAAI 2026 · 4 citations
- PointTPA: Dynamic Network Parameter Adaptation for 3D Scene UnderstandingAuthor 5 of 6CVPR 2026 · 3 citations
- OneSparse: A Unified Framework for Sparse Activation Layers in Vision ModelsAuthor 2 of 8CVPR 2026
- When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion ModelsAuthor 6 of 7CVPR 2026
- Orion: A Holistic End-To-End Autonomous Driving Framework by Vision-Language Instructed Action GenerationAuthor 5 of 10ICCV 2025 · 19 citations
- NAUTILUS: A Large Multimodal Model for Underwater Scene UnderstandingAuthor 3 of 7NeurIPS 2025 · 16 citations
- HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and GenerationAuthor 2 of 9ICCV 2025 · 5 citations
- More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion ModelsAuthor 2 of 5NeurIPS 2025 · 4 citations
- A Unified Image-Dense Annotation Generation Model for Underwater ScenesAuthor 2 of 4CVPR 2025
- MINIMA: Modality Invariant Image MatchingAuthor 4 of 6CVPR 2025
- SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text SpottingAuthor 4 of 7CVPR 2025
- PointMamba: A Simple State Space Model for Point Cloud AnalysisAuthor 1 of 8NeurIPS 2024 · 380 citations
- MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision TasksAuthor 3 of 6NeurIPS 2024 · 15 citations
- A Simple Vision Transformer for Weakly Semi-supervised 3D Object DetectionAuthor 2 of 8ICCV 2023 · 36 citations
- CrowdCLIP: Unsupervised Crowd Counting via Vision-Language ModelAuthor 1 of 6CVPR 2023
- SOOD: Towards Semi-Supervised Oriented Object DetectionAuthor 2 of 7CVPR 2023
