Pengju Ren

neural network architecture (1) model quantization (1) catastrophic forgetting (1) domain generalization (1) object detection (1) deformable convolution (1) knowledge distillation (1) chain-of-thought reasoning (1) channel attention (1) instance segmentation (1) efficient inference (1) mixture of expert (1) parameter efficiency (1) inference acceleration (1) reasoning ability (1) speculative decoding (1) parameter compression (1) quantization-aware training (1) mixed precision training (1) parallel decoding (1)