Profiles2026
Xiaohuan Pei
School of Computer Science, The University of Sydney
3Papers
0Last author
6Unique co-authors
2First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers3
- Action-aware Dynamic Pruning for Efficient Vision-Language-Action ManipulationAuthor 1 of 6ICLR 2026 · 31 citations
- Catching the Details: Self-Distilled RoI Predictors for Fine-Grained MLLM PerceptionAuthor 2 of 4ICLR 2026 · 10 citations
- Rethinking Causal Mask Attention for Vision-Language InferenceAuthor 1 of 4ICLR 2026 · 7 citations
