Profiles2020-2026
Xiaoshuai Sun
Xiamen University
38Papers
10Last author
66Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers38
- Grounded Chain-of-Thought for Multimodal Large Language ModelsAuthor 6 of 7CVPR 2026 · 55 citations
- ForensicConcept: Transferable Forensic Concepts for AIGI DetectionAuthor 6 of 7ICML 2026 · 1 citation
- CrackSSM: Reviving SSMs for Crack Segmentation via Dynamic ScanningAuthor 6 of 6CVPR 2026
- Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal ReasoningAuthor 2 of 8ICML 2026
- Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical FindingsAuthor 6 of 7NeurIPS 2025 · 16 citations
- IPDN: Image-enhanced Prompt Decoding Network for 3D Referring Expression SegmentationAuthor 6 of 6AAAI 2025 · 5 citations
- StoryWeaver: A Unified World Model for Knowledge-Enhanced Story Character CustomizationAuthor 5 of 5AAAI 2025 · 3 citations
- HRSeg: High-Resolution Visual Perception and Enhancement for Reasoning SegmentationAuthor 3 of 7ACM MM 2025 · 1 citation
- ACL: Activating Capability of Linear Attention for Image RestorationAuthor 4 of 4CVPR 2025
- FlashSloth : Lightning Multimodal Large Language Models via Embedded Visual CompressionAuthor 7 of 8CVPR 2025
- Routing Experts: Learning to Route Dynamic Experts in Existing Multi-modal Large Language ModelsAuthor 4 of 5ICLR 2025
- I2EBench: A Comprehensive Benchmark for Instruction-based Image EditingAuthor 8 of 9NeurIPS 2024 · 67 citations
- 3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression SegmentationAuthor 7 of 7AAAI 2024 · 40 citations
- X-RefSeg3D: Enhancing Referring 3D Instance Segmentation via Structured Cross-Modal Graph Neural NetworksAuthor 4 of 4AAAI 2024 · 27 citations
- Towards Efficient Diffusion-Based Image Editing with Instant Attention MasksAuthor 8 of 8AAAI 2024 · 24 citations
- SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-Supervised Referring Expression SegmentationAuthor 6 of 7ICML 2024 · 19 citations
- Toward Open-Set Human Object Interaction DetectionAuthor 4 of 5AAAI 2024 · 12 citations
- Fast Text-to-3D-Aware Face Generation and Manipulation via Direct Cross-modal Mapping and Geometric RegularizationAuthor 7 of 8ICML 2024 · 9 citations
- Improving Panoptic Narrative Grounding by Harnessing Semantic Relationships and Visual ConfirmationAuthor 5 of 5AAAI 2024 · 5 citations
- Deep Instruction Tuning for Segment Anything ModelAuthor 6 of 7ACM MM 2024 · 3 citations
- Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image SegmentationAuthor 6 of 7CVPR 2024
- Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language ModelsAuthor 5 of 6NeurIPS 2023 · 157 citations
- End-to-End Zero-Shot HOI Detection via Vision and Language Knowledge DistillationAuthor 6 of 6AAAI 2023 · 64 citations
- Beat: Bi-directional One-to-Many Embedding Alignment for Text-based Person RetrievalAuthor 2 of 3ACM MM 2023 · 34 citations
- Towards Real-Time Panoptic Narrative Grounding by an End-to-End Grounding NetworkAuthor 5 of 5AAAI 2023 · 18 citations
- Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained ModelsAuthor 5 of 6NeurIPS 2023 · 16 citations
- Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D RepresentationAuthor 3 of 10ACM MM 2023 · 11 citations
- RefCLIP: A Universal Teacher for Weakly Supervised Referring Expression ComprehensionAuthor 4 of 7CVPR 2023
- RefTeacher: A Strong Baseline for Semi-Supervised Referring Expression ComprehensionAuthor 4 of 7CVPR 2023
- Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation ApproachAuthor 5 of 7NeurIPS 2022 · 102 citations
Showing the 30 most recent indexed papers.
