Trending Research
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
BlinkDL/RWKV-LM
•
•
We propose SmoothQuant, a training-free, accuracy-preserving, and general-purpose post-training quantization (PTQ) solution to enable 8-bit weight, 8-bit activation (W8A8) quantization for LLMs.
Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators
Recent text-to-video generation approaches rely on computationally heavy training and require large-scale video datasets.
Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models
We present Text2Room, a method for generating room-scale textured 3D meshes from a given text prompt as input.
Zero-1-to-3: Zero-shot One Image to 3D Object
We introduce Zero-1-to-3, a framework for changing the camera viewpoint of an object given just a single RGB image.
LoRA: Low-Rank Adaptation of Large Language Models
We propose Low-Rank Adaptation, or LoRA, which freezes the pre-trained model weights and injects trainable rank decomposition matrices into each layer of the Transformer architecture, greatly reducing the number of trainable parameters for downstream tasks.
ReVersion: Diffusion-Based Relation Inversion from Images
Specifically, we propose a novel relation-steering contrastive learning scheme to impose two critical properties of the relation prompt: 1) The relation prompt should capture the interaction between objects, enforced by the preposition prior.
LLaMA: Open and Efficient Foundation Language Models
tatsu-lab/stanford_alpaca
•
•
arXiv 2023
We introduce LLaMA, a collection of foundation language models ranging from 7B to 65B parameters.
Ranked #1 on
Question Answering
on PIQA
VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking
Our core insight is to predict objects directly based on sparse voxel features, without relying on hand-crafted proxies.
Ranked #1 on
3D Object Detection
on Argoverse2
SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
We present SadTalker, which generates 3D motion coefficients (head pose, expression) of the 3DMM from audio and implicitly modulates a novel 3D-aware face render for talking head generation.
A Dynamic Multi-Scale Voxel Flow Network for Video Prediction
megvii-research/CVPR2023-DMVFN
•
•
The performance of video prediction has been greatly boosted by advanced deep neural networks.
Ranked #1 on
Video Prediction
on DAVIS 2017
