Search Results for author:
Found 9 papers, 8 papers with code
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
We present two levels of fine-tuning procedures for Medusa to meet the needs of different use cases: Medusa-1: Medusa is directly fine-tuned on top of a frozen backbone LLM, enabling lossless inference acceleration.
One-Step Diffusion Distillation via Deep Equilibrium Models
We demonstrate that the DEQ architecture is crucial to this capability, as GET matches a $5\times$ larger ViT in terms of FID scores while striking a critical balance of computational cost and image quality.
TorchDEQ: A Library for Deep Equilibrium Models
Deep Equilibrium (DEQ) Models, an emerging class of implicit models that maps inputs to fixed points of neural networks, are of growing interest in the deep learning community.
Deep Equilibrium Approaches to Diffusion Models
In this paper, we look at diffusion models through a different perspective, that of a (deep) equilibrium (DEQ) fixed point model.
Eliminating Gradient Conflict in Reference-based Line-Art Colorization
To understand the instability in training, we detect the gradient flow of attention and observe gradient conflict among attention branches.
Deep Equilibrium Optical Flow Estimation
Many recent state-of-the-art (SOTA) optical flow models use finite-step recurrent update operations to emulate traditional algorithms by encouraging iterative refinements toward a stable flow estimation.
Ranked #1 on
Optical Flow Estimation
on KITTI 2015 (train)
Residual Relaxation for Multi-view Representation Learning
Multi-view methods learn representations by aligning multiple views of the same image and their performance largely depends on the choice of data augmentation.
Is Attention Better Than Matrix Decomposition?
As an essential ingredient of modern deep learning, attention mechanism, especially self-attention, plays a vital role in the global correlation discovery.
Ranked #7 on
Semantic Segmentation
on PASCAL VOC 2012 test
