DeepMatcher: A Deep Transformer-based Network for Robust and Accurate Local Feature Matching

XT-1997/DeepMatcher 8 Jan 2023

In this work, we propose DeepMatcher, a deep Transformer-based network built upon our investigation of local feature matching in detector-free methods.

142
0.31 stars / hour

Why Can GPT Learn In-Context? Language Models Secretly Perform Gradient Descent as Meta-Optimizers

microsoft/lmops 20 Dec 2022

In order to better understand how ICL works, this paper explains language models as meta-optimizers and understands ICL as a kind of implicit finetuning.

Pretrained Language Models

507
0.29 stars / hour

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

BlinkDL/RWKV-LM 18 Nov 2022

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 that can be implemented efficiently.

Quantization

1,097
0.28 stars / hour

Diffusion Models for Causal Discovery via Topological Ordering

vios-s/diffan 12 Oct 2022

Topological ordering approaches for causal discovery exploit this by performing graph discovery in two steps, first sequentially identifying nodes in reverse order of depth (topological ordering), and secondly pruning the potential relations.

Causal Discovery

38
0.26 stars / hour

VToonify: Controllable High-Resolution Portrait Video Style Transfer

williamyang1991/vtoonify 22 Sep 2022

Although a series of successful portrait image toonification models built upon the powerful StyleGAN have been proposed, these image-oriented methods have obvious limitations when applied to videos, such as the fixed frame size, the requirement of face alignment, missing non-facial details and temporal inconsistency.

Face Alignment Style Transfer +1

2,751
0.25 stars / hour

How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection

hello-simpleai/chatgpt-comparison-detection 18 Jan 2023

We call the collected dataset the Human ChatGPT Comparison Corpus (HC3).

287
0.25 stars / hour

AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities

automatic1111/stable-diffusion-webui 12 Nov 2022

In this work, we present a conceptually simple and effective method to train a strong bilingual/multilingual multimodal representation model.

Contrastive Learning Cross-Modal Retrieval +11

29,774
0.24 stars / hour

Triton: An Intermediate Language and Compiler for Tiled Neural Network Computations

openai/triton MAPL 2019

The validation and deployment of novel research ideas in the field of Deep Learning is often limited by the availability of efficient compute kernels for certain basic primitives.

5,020
0.23 stars / hour

Is ChatGPT A Good Translator? A Preliminary Study

wxjiao/is-chatgpt-a-good-translator 20 Jan 2023

This report provides a preliminary evaluation of ChatGPT for machine translation, including translation prompt, multilingual translation, and translation robustness.

Machine Translation Translation

36
0.23 stars / hour

Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation

showlab/Tune-A-Video 22 Dec 2022

To reproduce the success of text-to-image (T2I) generation, recent works in text-to-video (T2V) generation employ large-scale text-video dataset for fine-tuning.

Style Transfer Text-to-Video Generation +1

147
0.23 stars / hour