影响力指数

60.91/100

前 4.6%

全站排名 #2,970

发表论文13 篇

平均评分5.8

年均产出4.3 篇/年

Hanrong Ye

Researcher@NVIDIA·美国·OpenReview

研究方向

Image Generation · Image Segmentation · Multimodal · Multi-task Learning · Computer Vision · Deep Learning

6.0

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

ICLR 2026Rejected

4.0

Compact GSPN: Scaling Spatial Propagation to Vision Foundation Models

ICLR 2026Withdrawn

7.3

Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models

NeurIPS 2025Poster

6.8

GSPN-2: Efficient Parallel Sequence Modeling

NeurIPS 2025Poster

6.8

Scaling RL to Long Videos

NeurIPS 2025Poster

6.1

I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models

ICML 2025Poster

6.0

MMEgo: Towards Building Egocentric Multimodal LLMs for Video QA

ICLR 2025Poster

一作

6.0

MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs

ICLR 2025Poster

二作

4.8

X-VILA: Cross-Modality Alignment for Large Language Models

合作者 (20)

Hanrong Ye

QeRL: Beyond Efficiency - Quantization-enhanced Reinforcement Learning for LLMs

UALM: Unified Audio Language Model for Understanding, Generation and Reasoning

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

Compact GSPN: Scaling Spatial Propagation to Vision Foundation Models

Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models

GSPN-2: Efficient Parallel Sequence Modeling

Scaling RL to Long Videos

I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models

MMEgo: Towards Building Egocentric Multimodal LLMs for Video QA

MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs

X-VILA: Cross-Modality Alignment for Large Language Models