Picture for Wen Li

Wen Li

ResCLIP: Residual Attention for Training-free Dense Vision-language Inference

Add code
Nov 24, 2024
Viaarxiv icon

Generalized Eigenvalue Problems with Generative Priors

Add code
Nov 02, 2024
Viaarxiv icon

Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective

Add code
Oct 06, 2024
Figure 1 for Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective
Figure 2 for Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective
Figure 3 for Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective
Figure 4 for Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective
Viaarxiv icon

AIM 2024 Challenge on Efficient Video Super-Resolution for AV1 Compressed Content

Add code
Sep 25, 2024
Figure 1 for AIM 2024 Challenge on Efficient Video Super-Resolution for AV1 Compressed Content
Figure 2 for AIM 2024 Challenge on Efficient Video Super-Resolution for AV1 Compressed Content
Figure 3 for AIM 2024 Challenge on Efficient Video Super-Resolution for AV1 Compressed Content
Figure 4 for AIM 2024 Challenge on Efficient Video Super-Resolution for AV1 Compressed Content
Viaarxiv icon

StyleTokenizer: Defining Image Style by a Single Instance for Controlling Diffusion Models

Add code
Sep 04, 2024
Viaarxiv icon

Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction

Add code
Jul 16, 2024
Viaarxiv icon

Powerful and Flexible: Personalized Text-to-Image Generation via Reinforcement Learning

Add code
Jul 09, 2024
Viaarxiv icon

PerlDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Models

Add code
Jul 08, 2024
Viaarxiv icon

AI-Based Beam-Level and Cell-Level Mobility Management for High Speed Railway Communications

Add code
Jul 05, 2024
Viaarxiv icon

Beyond Viewpoint: Robust 3D Object Recognition under Arbitrary Views through Joint Multi-Part Representation

Add code
Jul 04, 2024
Figure 1 for Beyond Viewpoint: Robust 3D Object Recognition under Arbitrary Views through Joint Multi-Part Representation
Figure 2 for Beyond Viewpoint: Robust 3D Object Recognition under Arbitrary Views through Joint Multi-Part Representation
Figure 3 for Beyond Viewpoint: Robust 3D Object Recognition under Arbitrary Views through Joint Multi-Part Representation
Figure 4 for Beyond Viewpoint: Robust 3D Object Recognition under Arbitrary Views through Joint Multi-Part Representation
Viaarxiv icon