AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System

salesforceairesearch/agentlite 23 Feb 2024

Thus, we open-source a new AI agent library, AgentLite, which simplifies this process by offering a lightweight, user-friendly platform for innovating LLM agent reasoning, architectures, and applications with ease.

214
0.73 stars / hour

Logit Standardization in Knowledge Distillation

sunshangquan/logit-standardardization-kd 3 Mar 2024

Knowledge distillation involves transferring soft labels from a teacher to a student using a shared temperature-based softmax function.

Knowledge Distillation

74
0.72 stars / hour

Chronos: Learning the Language of Time Series

amazon-science/chronos-forecasting 12 Mar 2024

We introduce Chronos, a simple yet effective framework for pretrained probabilistic time series models.

Gaussian Processes Language Modelling +2

1,256
0.71 stars / hour

MedPromptX: Grounded Multimodal Prompting for Chest X-ray Diagnosis

biomedia-mbzuai/medpromptx 22 Mar 2024

Chest X-ray images are commonly used for predicting acute and chronic cardiopulmonary conditions, but efforts to integrate them with structured clinical data face challenges due to incomplete electronic health records (EHR).

Medical Diagnosis Medical Visual Question Answering +3

33
0.69 stars / hour

Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions

compvis/attribute-control 25 Mar 2024

We demonstrate that these directions can be used to augment the prompt text input with fine-grained control over attributes of specific subjects in a compositional manner (control over multiple attributes of a single subject) without having to adapt the diffusion model.

Attribute

26
0.67 stars / hour

FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation

williamyang1991/fresco 19 Mar 2024

In this paper, we introduce FRESCO, intra-frame correspondence alongside inter-frame correspondence to establish a more robust spatial-temporal constraint.

Translation valid

507
0.67 stars / hour

AID: Attention Interpolation of Text-to-Image Diffusion

qy-h00/attention-interpolation-diffusion 26 Mar 2024

To that end, we introduce a novel training-free technique named Attention Interpolation via Diffusion (AID).

Spatial Interpolation

25
0.64 stars / hour

Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference

h-zhao1997/cobra 21 Mar 2024

In recent years, the application of multimodal large language models (MLLM) in various fields has achieved remarkable success.

Language Modelling Large Language Model

87
0.63 stars / hour

PCToolkit: A Unified Plug-and-Play Prompt Compression Toolkit of Large Language Models

3DAgentWorld/Toolkit-for-Prompt-Compression 26 Mar 2024

Prompt compression is an innovative method for efficiently condensing input prompts while preserving essential information.

Code Completion Few-Shot Learning +2

20
0.61 stars / hour

MegaBlocks: Efficient Sparse Training with Mixture-of-Experts

stanford-futuredata/megablocks 29 Nov 2022

We present MegaBlocks, a system for efficient Mixture-of-Experts (MoE) training on GPUs.

864
0.61 stars / hour