影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
81.63/100
前 1.2%
全站排名 #790
发表论文28 篇
平均评分
年均产出9.3 篇/年
Xiaoyi Dong
研究方向
Multi-modality LLM · Vision Transformer · Adversarial samples
9
Beyond Fixed: Training-Free Variable-Length Denoising for Diffusion Large Language Models
ICLR 2026Poster
二作23
STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence
ICLR 2026Poster
15
Visual Self-Refine: A Pixel-Guided Paradigm for Accurate Chart Parsing
ICLR 2026Poster
二作15
Advancing Complex Video Object Segmentation via Progressive Concept Construction
ICLR 2026Poster
三作23
SIM-CoT: Supervised Implicit Chain-of-Thought
ICLR 2026Poster
20
ScaleCap: Scalable Image Captioning via Dual-Modality Debiasing
ICLR 2026Poster
三作15
CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning
ICLR 2026Rejected
22
CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning
ICLR 2026Poster
二作9
SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience
ICLR 2026Withdrawn
13
SPARK: Synergistic Policy And Reward Co-Evolving Framework
ICLR 2026Withdrawn
4
Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisition
ICLR 2026Withdrawn
6
BoostStep: Boosting Mathematical Capability of Large Language Models via Step-aligned In Context Learning
ICLR 2026Rejected
三作17
VideoRoPE: What Makes for Good Video Rotary Position Embedding?
ICML 2025Oral
28
HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance
NeurIPS 2025Poster
23
MotionClone: Training-Free Motion Cloning for Controllable Video Generation
ICLR 2025Poster
52
MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models
ICLR 2025Poster
三作13
SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation
ICML 2025Poster
33
RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition
ICLR 2025Rejected
6
Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate
ICLR 2025Withdrawn
二作10
SAM2Long: Enhancing SAM2 for Long Video Segmentation with a Training-Free Memory Tree
ICLR 2025Withdrawn
三作4
DualFocus: Integrating Macro and Micro Perspectives in Multi-modal Large Language Models
ICLR 2025Withdrawn
三作7
SongComposer: A Large Language Model for Lyric and Melody Composition in Song Generation
ICLR 2025Rejected
三作6
BroadWay: Boost Your Text-to-Video Generation Model in a Training-free Way
ICLR 2025Withdrawn
5
Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data
ICLR 2025Withdrawn
5
PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
ICLR 2025Withdrawn
三作