LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control

KwaiVGI/LivePortrait 3 Jul 2024

Instead of following mainstream diffusion-based methods, we explore and extend the potential of the implicit-keypoint-based framework, which effectively balances computational efficiency and controllability.

Computational Efficiency Face Reenactment +3

10.82 stars / hour

MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention

microsoft/MInference 2 Jul 2024

With the pattern and sparse indices, we perform efficient sparse attention calculations via our optimized GPU kernels to significantly reduce the latency in the pre-filling stage of long-context LLMs.

Language Modelling Large Language Model

1.43 stars / hour

RouteLLM: Learning to Route LLMs with Preference Data

lm-sys/routellm 26 Jun 2024

Large language models (LLMs) exhibit impressive capabilities across a wide range of tasks, yet the choice of which model to use often involves a trade-off between performance and cost.

Data Augmentation Transfer Learning

1.37 stars / hour

Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion

buoyancy99/diffusion-forcing 1 Jul 2024

This paper presents Diffusion Forcing, a new training paradigm where a diffusion model is trained to denoise a set of tokens with independent per-token noise levels.

Decision Making

1.13 stars / hour

Agentless: Demystifying LLM-based Software Engineering Agents

OpenAutoCoder/Agentless 1 Jul 2024

However, the complexity of these agent-based approaches, together with the limited abilities of current LLMs, raises the following question: Do we really have to employ complex autonomous software agents?

Program Repair

0.87 stars / hour

Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation

g-u-n/be-your-outpainter 20 Mar 2024

We introduce MOTIA Mastering Video Outpainting Through Input-Specific Adaptation, a diffusion-based pipeline that leverages both the intrinsic data-specific patterns of the source video and the image/video generative prior for effective outpainting.

0.83 stars / hour

HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models

osu-nlp-group/hipporag 23 May 2024

In order to thrive in hostile and ever-changing natural environments, mammalian brains evolved to store large amounts of knowledge about the world and continually integrate new information while avoiding catastrophic forgetting.

Hippocampus Knowledge Graphs +4

0.71 stars / hour

Occupancy as Set of Points

hustvl/osp 4 Jul 2024

Owing to the inherent flexibility of the point-based representation, OSP achieves strong performance compared with existing methods and excels in terms of training and inference adaptability.

0.71 stars / hour

Self-Play Preference Optimization for Language Model Alignment

uclaml/sppo 1 May 2024

Our method can effectively increase the log-likelihood of the chosen response and decrease that of the rejected response, which cannot be trivially achieved by symmetric pairwise loss such as Direct Preference Optimization (DPO) and Identity Preference Optimization (IPO).

Language Modelling

0.71 stars / hour

Scaling Synthetic Data Creation with 1,000,000,000 Personas

tencent-ailab/persona-hub 28 Jun 2024

We propose a novel persona-driven data synthesis methodology that leverages various perspectives within a large language model (LLM) to create diverse synthetic data.

Language Modelling Large Language Model +2

0.68 stars / hour