Yining Li

Researcher@Shanghai AI Laboratory·中国·OpenReview

研究方向

large language model · multimodal learning · LLM agent · learning from synthetic data · deep learning · computer vision · pose estimation · representation learning

7.5

InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD

NeurIPS 2024Poster

5.3

Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization

NeurIPS 2024Poster

三作

5.2

MotionBooth: Motion-Aware Customized Text-to-Video Generation

NeurIPS 2024Spotlight

3.8

DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection

合作者 (20)

Yining Li

RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything

MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning

RTMPose: Real-Time Models for Multi-Person Pose Estimation

InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD

Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization

MotionBooth: Motion-Aware Customized Text-to-Video Generation

DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection