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
58.39/100
前 5.2%
全站排名 #3,357
发表论文13 篇
平均评分
年均产出6.5 篇/年
Zhenheng Yang
研究方向
Multi-modality Large language model · Vision-language modeling · Object detection · 3D scene understanding · Temporal activity analysis
16
Mixture of Contexts for Long Video Generation
ICLR 2026Poster
23
FOCUS: Efficient Keyframe Selection for Long Video Understanding
ICLR 2026Poster
24
MotionSight: Boosting Fine-Grained Motion Understanding in Multimodal LLMs
ICLR 2026Poster
15
UniMoD: Efficient Unified Multimodal Transformers with Mixture-of-Depths
ICLR 2026Rejected
二作16
UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning
ICLR 2026Rejected
二作5
mmSSR: Harvesting Rich, Scalable and Transferable Multi-Modal Data for Instruction Fine-Tuning
ICLR 2026Withdrawn
通讯5
Growing Visual Generative Capacity for Pre-Trained MLLMs
ICLR 2026Withdrawn
4
Improving Text-to-Image Generation with Input-Side Inference-Time Scaling
ICLR 2026Withdrawn
通讯6
SeedFT: Structure-Preserving Fusion for Multi-Seed LLM Fine-Tuning
ICLR 2026Rejected
23
DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling
NeurIPS 2025Spotlight
21
OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation
ICLR 2025Poster
25
Show-o2: Improved Native Unified Multimodal Models
NeurIPS 2025Poster
二作7
Show-o: One Single Transformer to Unify Multimodal Understanding and Generation
ICLR 2025Poster