SOAP: Style-Omniscient Animatable Portraits

tingtingliao/soap 8 May 2025

Creating animatable 3D avatars from a single image remains challenging due to style limitations (realistic, cartoon, anime) and difficulties in handling accessories or hairstyles.

Image to 3D

142
0.73 stars / hour

Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning

going-doer/paper2code 24 Apr 2025

Despite the rapid growth of machine learning research, corresponding code implementations are often unavailable, making it slow and labor-intensive for researchers to reproduce results and build upon prior work.

Code Generation

2,139
0.70 stars / hour

Continuous Thought Machines

SakanaAI/continuous-thought-machines 8 May 2025

The CTM has two core innovations: (1) neuron-level temporal processing, where each neuron uses unique weight parameters to process a history of incoming signals; and (2) neural synchronization employed as a latent representation.

Computational Efficiency Question Answering

811
0.70 stars / hour

HealthBench: Evaluating Large Language Models Towards Improved Human Health

openai/simple-evals 13 May 2025

We present HealthBench, an open-source benchmark measuring the performance and safety of large language models in healthcare.

Instruction Following Multiple-choice

3,482
0.66 stars / hour

AlphaNet: Scaling Up Local-frame-based Atomistic Interatomic Potential

zmyybc/alphanet 13 Jan 2025

Molecular dynamics simulations demand an unprecedented combination of accuracy and scalability to tackle grand challenges in catalysis and materials design.

Computational Efficiency

102
0.66 stars / hour

Spherical Channels for Modeling Atomic Interactions

Open-Catalyst-Project/ocp 29 Jun 2022

We propose the Spherical Channel Network (SCN) to model atomic energies and forces.

10-shot image generation Computational chemistry +1

1,398
0.66 stars / hour

Absolute Zero: Reinforced Self-play Reasoning with Zero Data

LeapLabTHU/Absolute-Zero-Reasoner 6 May 2025

Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning capabilities of large language models by learning directly from outcome-based rewards.

Mathematical Reasoning

1,241
0.61 stars / hour

SkyReels-V2: Infinite-length Film Generative Model

skyworkai/skyreels-v2 17 Apr 2025

Recent advances in video generation have been driven by diffusion models and autoregressive frameworks, yet critical challenges persist in harmonizing prompt adherence, visual quality, motion dynamics, and duration: compromises in motion dynamics to enhance temporal visual quality, constrained video duration (5-10 seconds) to prioritize resolution, and inadequate shot-aware generation stemming from general-purpose MLLMs' inability to interpret cinematic grammar, such as shot composition, actor expressions, and camera motions.

Large Language Model model +2

2,397
0.58 stars / hour

MTVCrafter: 4D Motion Tokenization for Open-World Human Image Animation

dingyanb/mtvcrafter 15 May 2025

To tackle this problem, we propose MTVCrafter (Motion Tokenization Video Crafter), the first framework that directly models raw 3D motion sequences (i. e., 4D motion) for human image animation.

Image Animation Video Generation

21
0.57 stars / hour

Finetune-RAG: Fine-Tuning Language Models to Resist Hallucination in Retrieval-Augmented Generation

Pints-AI/Finetune-Bench-RAG 16 May 2025

Retrieval-Augmented Generation (RAG) has emerged as a powerful framework to improve factuality in large language models (LLMs) by grounding their outputs in retrieved documents.

Hallucination RAG +1

18
0.55 stars / hour