Jiaxin Chen

6

Papers

8

Total Citations

Papers (6)

FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation

TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models

APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers

3D²-Actor: Learning Pose-Conditioned 3D-Aware Denoiser for Realistic Gaussian Avatar Modeling

Unified Knowledge Maintenance Pruning and Progressive Recovery with Weight Recalling for Large Vision-Language Models

Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model