Profiles2019-2026ORCID 0000-0003-4822-8939
Yong Liu
Zhejiang University
36Papers
23Last author
80Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers36
- LumosX: Relate Any Identities with Their Attributes for Personalized Video GenerationAuthor 10 of 10ICLR 2026 · 6 citations
- M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image UnderstandingAuthor 8 of 10ICLR 2026 · 3 citations
- OptMark: Robust Multi-bit Diffusion Watermarking via Inference Time OptimizationAuthor 5 of 6AAAI 2026 · 2 citations
- Contact Matrix: Enhancing Dance Motion Synthesis with Precise Interaction ModelingAuthor 6 of 6CVPR Findings 2026
- Drive-Cascade: Autoregressive Occupancy to LiDAR and Video SynthesisAuthor 14 of 14CVPR Findings 2026
- Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous DrivingAuthor 8 of 8AAAI 2025 · 53 citations
- CogDDN: A Cognitive Demand-Driven Navigation with Decision Optimization and Dual-Process ThinkingAuthor 8 of 10ACM MM 2025 · 1 citation
- GroundingFace: Fine-grained Face Understanding via Pixel Grounding Multimodal Large Language ModelAuthor 9 of 9CVPR 2025
- Decentralized Riemannian Conjugate Gradient Method on the Stiefel ManifoldAuthor 7 of 7ICLR 2024 · 21 citations
- A Multimodal, Multi-Task Adapting Framework for Video Action RecognitionAuthor 9 of 9AAAI 2024 · 13 citations
- MambaGesture: Enhancing Co-Speech Gesture Generation with Mamba and Disentangled Multi-Modality FusionAuthor 10 of 10ACM MM 2024 · 10 citations
- Solving Homogeneous and Heterogeneous Cooperative Tasks with Greedy Sequential ExecutionAuthor 6 of 6ICLR 2024 · 2 citations
- Structured Optimal Brain Pruning for Large Language ModelsAuthor 7 of 7EMNLP 2024 · 2 citations
- SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object TrackingAuthor 11 of 11CVPR 2024
- Revisiting the Spatial and Temporal Modeling for Few-Shot Action RecognitionAuthor 3 of 4AAAI 2023 · 51 citations
- Boosting Few-shot Action Recognition with Graph-guided Hybrid MatchingAuthor 9 of 9ICCV 2023 · 41 citations
- Unified Data-Free Compression: Pruning and Quantization without Fine-TuningAuthor 5 of 5ICCV 2023 · 31 citations
- Synchronize Feature Extracting and Matching: A Single Branch Framework for 3D Object TrackingAuthor 5 of 5ICCV 2023 · 21 citations
- Learning Global-aware Kernel for Image HarmonizationAuthor 8 of 8ICCV 2023 · 14 citations
- CenterLPS: Segment Instances by Centers for LiDAR Panoptic SegmentationAuthor 6 of 8ACM MM 2023 · 7 citations
- SUBP: Soft Uniform Block Pruning for 1×N Sparse CNNs Multithreading AccelerationAuthor 7 of 7NeurIPS 2023 · 2 citations
- Better "CMOS" Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-ResolutionAuthor 6 of 6CVPR 2023
- High-Fidelity Generalized Emotional Talking Face Generation with Multi-Modal Emotion Space LearningAuthor 9 of 9CVPR 2023
- Region-Aware Face SwappingAuthor 6 of 6CVPR 2022 · 46 citations
- SCSNet: An Efficient Paradigm for Learning Simultaneously Image Colorization and Super-resolutionAuthor 7 of 7AAAI 2022 · 19 citations
- HR-Depth: High Resolution Self-Supervised Monocular Depth EstimationAuthor 6 of 8AAAI 2021 · 341 citations
- FCFR-Net: Feature Fusion based Coarse-to-Fine Residual Learning for Depth CompletionAuthor 6 of 7AAAI 2021 · 125 citations
- Self-supervised Monocular Depth Estimation for All Day Images using Domain SeparationAuthor 4 of 5ICCV 2021 · 95 citations
- Analogous to Evolutionary Algorithm: Designing a Unified Sequence ModelAuthor 10 of 10NeurIPS 2021 · 27 citations
- Structure-aware Person Image Generation with Pose Decomposition and Semantic CorrelationAuthor 4 of 6AAAI 2021 · 22 citations
Showing the 30 most recent indexed papers.
