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
44.81/100
前 11.1%
全站排名 #7,143
发表论文11 篇
平均评分
年均产出3.7 篇/年
Zhiyuan Ma
研究方向
Video Generation · Vision-Language Models · Image Synthesis · Diffusion Models · Task-oriented Dialog Systems · Multimodal Dialog Systems
11
Multi-Layer Diffusion Strategy for Multi-IP Interaction-Aware Human Erasing
ICLR 2026Rejected
三作21
MARTI: A Framework for Multi-Agent LLM Systems Reinforced Training and Inference
ICLR 2026Poster
16
Z-Cache: Accelerating Diffusion Transformers via Self-Reflection
ICLR 2026Rejected
5
Generative Spatial Reasoners via Reinforcement Learning based Intrinsic Reflection
ICLR 2026Withdrawn
二作5
Flow Diverse and Efficient: Learning Momentum Flow Matching via Stochastic Velocity Field Sampling
ICLR 2026Withdrawn
一作5
Context-Aware Autoregressive Models for Multi-Conditional Image Generation
ICLR 2026Withdrawn
二作5
Self-Reflective Reinforcement Learning for Diffusion-based Image Reasoning Generation
ICLR 2026Withdrawn
一作