LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

microsoft/LLMLingua 19 Mar 2024

The challenge is that information entropy may be a suboptimal compression metric: (i) it only leverages unidirectional context and may fail to capture all essential information needed for prompt compression; (ii) it is not aligned with the prompt compression objective.

GSM8K Language Modelling +3

3,804
0.67 stars / hour

Graphic Design with Large Multimodal Model

graphic-design-ai/graphist 22 Apr 2024

One existing practice is Graphic Layout Generation (GLG), which aims to layout sequential design elements.

46
0.66 stars / hour

Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations

facebookresearch/generative-recommenders 27 Feb 2024

Large-scale recommendation systems are characterized by their reliance on high cardinality, heterogeneous features and the need to handle tens of billions of user actions on a daily basis.

 Ranked #1 on Recommendation Systems on MovieLens 20M (HR@10 (full corpus) metric)

Recommendation Systems

193
0.65 stars / hour

Unrecognizable Yet Identifiable: Image Distortion with Preserved Embeddings

Recognito-Vision/Face-SDK-Android-Demo 26 Jan 2024

In the realm of security applications, biometric authentication systems play a crucial role, yet one often encounters challenges concerning privacy and security while developing one.

Face Recognition Security Studies

204
0.63 stars / hour

How Good Are Low-bit Quantized LLaMA3 Models? An Empirical Study

macaronlin/llama3-quantization 22 Apr 2024

This exploration holds the potential to unveil new insights and challenges for low-bit quantization of LLaMA3 and other forthcoming LLMs, especially in addressing performance degradation problems that suffer in LLM compression.

Language Modelling Large Language Model +1

44
0.62 stars / hour

GhostFaceNets: Lightweight Face Recognition Model From Cheap Operations

Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection IEEE Access 2023

The development of deep learning-based biometric models that can be deployed on devices with constrained memory and computational resources has proven to be a significant challenge.

Face Identification Face Verification +1

203
0.62 stars / hour

Prompts As Programs: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization

microsoft/sammo 2 Apr 2024

We show that SAMMO generalizes previous methods and improves the performance of complex prompts on (1) instruction tuning, (2) RAG pipeline tuning, and (3) prompt compression, across several different LLMs.

129
0.62 stars / hour

SpaceByte: Towards Deleting Tokenization from Large Language Modeling

kjslag/spacebyte 22 Apr 2024

Tokenization is widely used in large language models because it significantly improves performance.

Language Modelling

23
0.61 stars / hour

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

fudan-generative-vision/champ 21 Mar 2024

In this study, we introduce a methodology for human image animation by leveraging a 3D human parametric model within a latent diffusion framework to enhance shape alignment and motion guidance in curernt human generative techniques.

Animated GIF Generation Image Animation +1

3,066
0.61 stars / hour

Arc2Face: A Foundation Model of Human Faces

Recognito-Vision/NIST-FRVT-Top-1-Face-Recognition 18 Mar 2024

This paper presents Arc2Face, an identity-conditioned face foundation model, which, given the ArcFace embedding of a person, can generate diverse photo-realistic images with an unparalleled degree of face similarity than existing models.

Diffusion Personalization Tuning Free Face Generation +1

210
0.61 stars / hour