[ACL 2026 Findings] CoV: Chain-of-View Prompting for Spatial Reasoning

[NeurIPS 2025] Atom of Thoughts for Markov LLM Test-Time Scaling

Code for paper "Rethinking Text-based Protein Understanding: Retrieval or LLM?"

[ICLR'26] Towards All-Atom Foundation Models for Biomolecular Binding Affinity Prediction

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶

[ECCV 2024 Best Paper Candidate & TPAMI 2025] PointLLM: Empowering Large Language Models to Understand Point Clouds

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Source code for RNA-FrameFlow: SE(3) Flow Matching for 3D RNA Backbone Design

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

🔬 Harness Vibe Research with Self-evolving AI Scientists

Generative model for protein binder design for protein and small molecule targets. Combines a pretrained flow-based generative model (built on La-Proteina) with inference-time optimization.

Shrinking Proteins with Diffusion

Implementation of [CVPR 2025] "DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation"

Fast and Interpretable Protein Substructure Alignment via Optimal Transport (ICLR 2026)

LoRAMoE: Revolutionizing Mixture of Experts for Maintaining World Knowledge in Language Model Alignment

[AAAI 2025] Dynamic Protein Data Bank

AbBiBench (Antibody Binding Benchmarking), a benchmarking framework for optimizing antibody binding affinity.

A fully open source biomolecular structure prediction model based on AlphaFold3

A partially latent flow matching model for the joint generation of a protein’s amino acid sequence and full atomistic structure, including both the backbone and side chain.

Toward High-Accuracy Open-Source Biomolecular Structure Prediction.

All-atom protein generation using latent diffusion, with compositional function and taxonomic prompts. http://bit.ly/plaid-proteins

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

Implementation of Alphafold 3 from Google Deepmind in Pytorch