Jianfei Cai

Full Professor@Monash University·澳大利亚·OpenReview

研究方向

3D vision · diffusion models · training and inference efficiency · vision and language · weak and self supervision · image captioning · face · hand · body 3D reconstruction and pose estimation · image segmentation · 3D reconstruction · multimedia processing

Jianfei Cai

CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs

Gradient-Aligned Calibration for Post-Training Quantization of Diffusion Models

WarpFace: Revisiting Face Reenactment via Self-Supervised Motion Learning in Diffusion Models

T2G-Reasoner: Deep Reasoning for Text-to-Gloss Translation

LOGAussian: Efficient Local Gathering for Online Feed-forward 3DGS

K-Gen: Unlocking High-Resolution Data-Free Knowledge Distillation via Key Region Generation

R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning

Bagel-World: Towards High-Quality Visual Question-Visual Answering

Adaptive Layer-Wise Transformations for Post-Training Quantization of Large Language Models

Rethinking Output Alignment for 1-bit Post-Training Quantization of Large Language Models

PaRa: Personalizing Text-to-Image Diffusion via Parameter Rank Reduction

T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching

Fast Feedforward 3D Gaussian Splatting Compression

Zero-shot Mixed Precision Quantization via Joint Optimization of Data Generation and Bit Allocation

ME-Switch: A Memory-Efficient Expert Switching Framework for Large Language Models