Equivariant Similarity for Vision-Language Foundation Models

wangt-cn/eqben 25 Mar 2023

Unlike the existing image-text similarity objective which only categorizes matched pairs as similar and unmatched pairs as dissimilar, equivariance also requires similarity to vary faithfully according to the semantic changes.

Retrieval Text Retrieval +1

1.70 stars / hour

More than you've asked for: A Comprehensive Analysis of Novel Prompt Injection Threats to Application-Integrated Large Language Models

greshake/lm-safety 23 Feb 2023

In such attacks, an adversary can prompt the LLM to produce malicious content or override the original instructions and the employed filtering schemes.

Instruction Following Retrieval

1.67 stars / hour

MGTBench: Benchmarking Machine-Generated Text Detection

xinleihe/mgtbench 26 Mar 2023

Nonetheless, we note that only a small fraction of adversarial-crafted perturbations on MGTs can evade the ChatGPT Detector, thus highlighting the need for more robust MGT detection methods.

Benchmarking Question Answering +3

1.38 stars / hour
1.29 stars / hour

Self-Instruct: Aligning Language Model with Self Generated Instructions

tatsu-lab/stanford_alpaca 20 Dec 2022

Applying our method to vanilla GPT3, we demonstrate a 33% absolute improvement over the original model on Super-NaturalInstructions, on par with the performance of InstructGPT_001, which is trained with private user data and human annotations.

Instruction Following Language Modelling

1.26 stars / hour

Colossal-Auto: Unified Automation of Parallelization and Activation Checkpoint for Large-scale Models

hpcaitech/colossalai 6 Feb 2023

To address these challenges, we introduce a system that can jointly optimize distributed execution and gradient checkpointing plans.


1.17 stars / hour

SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications

amshaker/swiftformer 27 Mar 2023

Using our proposed efficient additive attention, we build a series of models called "SwiftFormer" which achieves state-of-the-art performance in terms of both accuracy and mobile inference speed.

1.11 stars / hour

Reflexion: an autonomous agent with dynamic memory and self-reflection

noahshinn024/reflexion 20 Mar 2023

To achieve full automation, we introduce a straightforward yet effective heuristic that enables the agent to pinpoint hallucination instances, avoid repetition in action sequences, and, in some environments, construct an internal memory map of the given environment.

Decision Making Language Modelling

1.05 stars / hour

Your Diffusion Model is Secretly a Zero-Shot Classifier

diffusion-classifier/diffusion-classifier 28 Mar 2023

Our generative approach to classification attains strong results on a variety of benchmarks and outperforms alternative methods of extracting knowledge from diffusion models.

Image Generation Relational Reasoning +1

1.04 stars / hour

GLM-130B: An Open Bilingual Pre-trained Model

thudm/glm-130b 5 Oct 2022

We introduce GLM-130B, a bilingual (English and Chinese) pre-trained language model with 130 billion parameters.

Language Modelling Multi-task Language Understanding +1

1.01 stars / hour