AgentKit: Structured LLM Reasoning with Dynamic Graphs

holmeswww/agentkit 17 Apr 2024

The chains of nodes can be designed to explicitly enforce a naturally structured "thought process".

377
0.74 stars / hour

IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation

yangling0818/itercomp 9 Oct 2024

IterComp opens new research avenues in reward feedback learning for diffusion models and compositional generation.

Attribute Text-to-Image Generation

56
0.63 stars / hour

A Multi-Level Superoptimizer for Tensor Programs

mirage-project/mirage 9 May 2024

We introduce Mirage, the first multi-level superoptimizer for tensor programs.

Navigate

506
0.59 stars / hour

LightRAG: Simple and Fast Retrieval-Augmented Generation

hkuds/lightrag 8 Oct 2024

Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tailored to user needs.

Information Retrieval RAG +1

77
0.58 stars / hour

SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration

thu-ml/SageAttention 3 Oct 2024

Although quantization has proven to be an effective method for accelerating model inference, existing quantization methods primarily focus on optimizing the linear layer.

Image Generation Quantization +1

153
0.58 stars / hour
36
0.54 stars / hour

Diffusion Models are Evolutionary Algorithms

Zhangyanbo/diffusion-evolution 3 Oct 2024

In a convergence of machine learning and biology, we reveal that diffusion models are evolutionary algorithms.

Denoising Evolutionary Algorithms

74
0.53 stars / hour

Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale

microsoft/windowsagentarena 12 Sep 2024

To demonstrate Windows Agent Arena's capabilities, we also introduce a new multi-modal agent, Navi.

299
0.51 stars / hour

Text2SQL is Not Enough: Unifying AI and Databases with TAG

tag-research/tag-bench 27 Aug 2024

Such systems would allow users to leverage the powerful reasoning and knowledge capabilities of language models (LMs) alongside the scalable computational power of data management systems.

RAG Text-To-SQL +1

538
0.51 stars / hour

CursorCore: Assist Programming through Aligning Anything

TechxGenus/CursorCore 9 Oct 2024

In this work, we propose a new conversational framework that comprehensively integrates these information sources, collect data to train our models and evaluate their performance.

Code Completion

36
0.50 stars / hour