Trending Research
Salesforce CausalAI Library: A Fast and Scalable Framework for Causal Analysis of Time Series and Tabular Data
We introduce the Salesforce CausalAI Library, an open-source library for causal analysis using observational data.
LAION-5B: An open large-scale dataset for training next generation image-text models
mlfoundations/open_clip
•
•
NeurIPS 2022 Datasets and Benchmarks 2022
We show successful replication and fine-tuning of foundational models like CLIP, GLIDE and Stable Diffusion using the dataset, and discuss further experiments enabled with an openly available dataset of this scale.
TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation
As such, we study the challenging problem of task oriented detection, which aims to find objects that best afford an action indicated by verbs like sit comfortably on.
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities
automatic1111/stable-diffusion-webui
•
•
In this work, we present a conceptually simple and effective method to train a strong bilingual/multilingual multimodal representation model.
SEANet: A Multi-modal Speech Enhancement Network
We explore the possibility of leveraging accelerometer data to perform speech enhancement in very noisy conditions.
Hungry Hungry Hippos: Towards Language Modeling with State Space Models
hazyresearch/h3
•
•
First, we use synthetic language modeling tasks to understand the gap between SSMs and attention.
How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection
We call the collected dataset the Human ChatGPT Comparison Corpus (HC3).
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 that can be implemented efficiently.
Generate rather than Retrieve: Large Language Models are Strong Context Generators
We call our method generate-then-read (GenRead), which first prompts a large language model to generate contextutal documents based on a given question, and then reads the generated documents to produce the final answer.
Image Super-Resolution using Efficient Striped Window Transformer
fried-rice-lab/friedricelab
•
•
To further exploit the potential of the transformer, we propose a novel flexible window training strategy.
