Profiles2023-2026
Wenqi Shao
Shanghai AI Laboratory
16Papers
1Last author
20Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers16
- Design First, Code Later: Aesthetically Pleasing Template-Free Slides GenerationAuthor 5 of 7ACL Findings 2026 · 3 citations
- CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype LearningAuthor 5 of 7ICLR 2026 · 1 citation
- LiT: Delving into a Simple Linear Diffusion Transformer for Image GenerationAuthor 13 of 16ICCV 2025 · 10 citations
- GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile DevicesAuthor 2 of 10ICCV 2025 · 7 citations
- TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR PerceptionAuthor 4 of 6NeurIPS 2025 · 4 citations
- Learning Dense Feature Matching via Lifting Single 2D Image to 3D SpaceAuthor 3 of 4ICCV 2025 · 2 citations
- Distilling Monocular Foundation Model for Fine-grained Depth CompletionAuthor 3 of 5CVPR 2025
- EfficientQAT: Efficient Quantization-Aware Training for Large Language ModelsAuthor 2 of 7ACL 2025
- JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World DataAuthor 2 of 6CVPR 2025
- MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language ModelsAuthor 12 of 13ICLR 2025
- Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video GenerationAuthor 4 of 10ICML 2025
- MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGIAuthor 21 of 21ICML 2024 · 184 citations
- BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity AllocationAuthor 2 of 9ICLR 2024 · 52 citations
- ChartAssistant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction TuningAuthor 2 of 7ACL Findings 2024 · 43 citations
- DiffRate : Differentiable Compression Rate for Efficient Vision TransformersAuthor 2 of 9ICCV 2023 · 87 citations
- CO3: Cooperative Unsupervised 3D Representation Learning for Autonomous DrivingAuthor 4 of 9ICLR 2023
