Xiaoyi Dong
- Papers
- 43
Cite
Notes
Only stored in your browser.
Authored papers
43Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisition
arXiv 2026
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
arXiv 2025
Visual Agentic Reinforcement Fine-Tuning
arXiv 2025
OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?
CVPR 2025 1
SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation
arXiv 2025
InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model
arXiv 2025
Light-A-Video: Training-free Video Relighting via Progressive Light Fusion
arXiv 2025
Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction
CVPR 2025 1
ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning
arXiv 2025
Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning
arXiv 2025
Think Visually, Reason Textually: Vision-Language Synergy in ARC
arXiv 2025
SPARK: Synergistic Policy And Reward Co-Evolving Framework
arXiv 2025
STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence
arXiv 2025
VideoRoPE: What Makes for Good Video Rotary Position Embedding?
arXiv 2025
ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing
arXiv 2025
BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning
arXiv 2025
TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition
arXiv 2025
Beyond Fixed: Training-Free Variable-Length Denoising for Diffusion Large Language Models
arXiv 2025
CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning
arXiv 2025
SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction
arXiv 2025
SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience
arXiv 2025
MM-IFEngine: Towards Multimodal Instruction Following
arXiv 2025
CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning
arXiv 2025
Open-Sora Plan: Open-Source Large Video Generation Model
arXiv 2024
Long-CLIP: Unlocking the Long-Text Capability of CLIP
arXiv 2024
SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree
ICCV 2025
DualFocus: Integrating Macro and Micro Perspectives in Multi-modal Large Language Models
arXiv 2024
Are We on the Right Way for Evaluating Large Vision-Language Models?
arXiv 2024
PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
arXiv 2024
MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs
arXiv 2024
MotionClone: Training-Free Motion Cloning for Controllable Video Generation
arXiv 2024
SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition
arXiv 2024
X-Prompt: Towards Universal In-Context Image Generation in Auto-Regressive Vision Language Foundation Models
arXiv 2024
MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models
arXiv 2024
ShareGPT4V: Improving Large Multi-Modal Models with Better Captions
arXiv 2023
VIGC: Visual Instruction Generation and Correction
arXiv 2023
OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation
CVPR 2024 1
Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization
arXiv 2023
MLLM-DataEngine: An Iterative Refinement Approach for MLLM
arXiv 2023
Diversity-Aware Meta Visual Prompting
CVPR 2023 1
Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting
ICCV 2023 1
CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet
arXiv 2022
CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows
cswin-transformer-a-general-vision-1
Affiliations
Frequent co-authors
10from 43 papers