Code for PaperRobot: Incremental Draft Generation of Scientific Ideas
- pytorch
- memory-networks
- generation
- end-to-end-learning
132,218 visible repositories in the index
8,737–8,760 of 10,048 · Most stars
Code for PaperRobot: Incremental Draft Generation of Scientific Ideas
Skill for rigorous academic paper writing, revision, and submission. Field-agnostic with per-paper journal overrides.
Sequential regulatory activity predictions with deep convolutional neural networks.
Open-source embodied agent framework: execution, feedback, and continual improvement
The 2012 Forza Horizon, native on Windows and Linux, and online again: Horizon World, leaderboards and Rivals on a public server you can also self-host. Bring your own copy.
cell detection in calcium imaging recordings
[Reimplementation Antol et al 2015] Keras-based LSTM/CNN models for Visual Question Answering
Convert and edit files with a liquid-glass radial menu: start dragging a file, press Shift, drop it on a slice. Windows, Mac and Linux.
OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.
Directions overlay for working with pandas in an analysis environment
Intensity-based_Lidar_Camera_Calibration
Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving
Turkish voice design with VoxCPM2 on a 4 GB GPU: describe a voice, pick a variant, read text in 30 languages. Patched audio.cpp, local UI in 30 languages, 14 ready-made voices.
Point Claude at your camera roll: it sorts photos and videos into folders, finds duplicates, and plays it back on a live localhost dashboard.
Built-in Panther detection rules and policies
Code for Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention
A tool for holistic analysis of language generations systems
Independent reproduction of SuperMimic (arXiv:2610.28480) on mjlab/MuJoCo Warp, written from the paper before the official release. For the authors' code see HybridRobotics/supermimic. Kept as a record: experiment log, full BONES-SEED results, checkpoint.
A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.
A "run" function for asyncio-based apps that does all the boilerplate.
Tools for computational pathology
HALO: Perceptive Humanoid Motion from Simulation
Build and execute GraphQL queries in the terminal.
Streaming reactive and dataflow graphs in Python