Yin Li

12

Papers

39

Total Citations

Papers (12)

AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning

RICA^2: Rubric-Informed, Calibrated Assessment of Actions

Fix-CLIP: Dual-Branch Hierarchical Contrastive Learning via Synthetic Captions for Better Understanding of Long Text

PAVE: Patching and Adapting Video Large Language Models

Recovering Parametric Scenes from Very Few Time-of-Flight Pixels

Towards 3D Vision with Low-Cost Single-Photon Cameras

SnAG: Scalable and Accurate Video Grounding

FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition

LETS Forecast: Learning Embedology for Time Series Forecasting

AeroGen: Enhancing Remote Sensing Object Detection with Diffusion-Driven Data Generation

Learning to Inference Adaptively for Multimodal Large Language Models

Robust 3D Object Detection using Probabilistic Point Clouds from Single-Photon LiDARs