PyGlove: Efficiently Exchanging ML Ideas as Code

google/pyglove 3 Feb 2023

We also perform a case study of a large codebase where PyGlove led to an 80% reduction in the number of lines of code.

542
1.31 stars / hour

PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation

stevenlsw/physgen 27 Sep 2024

We present PhysGen, a novel image-to-video generation method that converts a single image and an input condition (e. g., force and torque applied to an object in the image) to produce a realistic, physically plausible, and temporally consistent video.

Image to Video Generation

115
0.94 stars / hour

ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models

bytedance/abq-llm 16 Aug 2024

Based on W2*A8 quantization configuration on LLaMA-7B model, it achieved a WikiText2 perplexity of 7. 59 (2. 17$\downarrow $ vs 9. 76 in AffineQuant).

Model Compression Quantization

178
0.66 stars / hour

Cross-video Identity Correlating for Person Re-identification Pre-training

zplusdragon/cion_reidzoo 27 Sep 2024

For example, compared with the previous state-of-the-art~\cite{ISR}, CION with the same ResNet50-IBN achieves higher mAP of 93. 3\% and 74. 3\% on Market1501 and MSMT17, while only utilizing 8\% training samples.

Denoising Person Re-Identification

54
0.61 stars / hour

WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild

rolpotamias/WiLoR 18 Sep 2024

In recent years, 3D hand pose estimation methods have garnered significant attention due to their extensive applications in human-computer interaction, virtual reality, and robotics.

3D Hand Pose Estimation Hand Detection

103
0.59 stars / hour

OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquer

om-ai-lab/OmAgent 24 Jun 2024

Recent advancements in Large Language Models (LLMs) have expanded their capabilities to multimodal contexts, including comprehensive video understanding.

AI Agent Video Understanding

741
0.42 stars / hour

VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models

microsoft/vptq 25 Sep 2024

Due to the redundancy in LLM weights, recent research has focused on pushing weight-only quantization to extremely low-bit (even down to 2 bits).

Quantization

199
0.41 stars / hour

TensorIR: An Abstraction for Automatic Tensorized Program Optimization

mlc-ai/web-llm 9 Jul 2022

Finally, we build an end-to-end framework on top of our abstraction to automatically optimize deep learning models for given tensor computation primitives.

BIG-bench Machine Learning

13,114
0.41 stars / hour

Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers

liruiw/HPT 30 Sep 2024

Previous robot learning methods often collect data to train with one specific embodiment for one task, which is expensive and prone to overfitting.

81
0.40 stars / hour