Shamanga
Follow
Starred repositories
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
CUGA is an open-source generalist agent for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware f…
Repository for Deep Structural Causal Models for Tractable Counterfactual Inference
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
⚡ TabPFN: Foundation Model for Tabular Data ⚡
TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's …
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
A Reproduction of GDM's Nested Learning Paper
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
Automatic Video Generation from Scientific Papers
The absolute trainer to light up AI agents.
TradingAgents: Multi-Agents LLM Financial Trading Framework
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of …
MTBBench is a benchmark designed to evaluate the reasoning capabilities of multimodal large language models (LLMs) in complex clinical decision-making scenarios. It focuses on two core challenges i…
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
We present a comprehensive and deep review of the HFM in challenges, opportunities, and future directions. The released paper: https://arxiv.org/abs/2404.03264
Official PyTorch implementation of BigVGAN (ICLR 2023)
🤗 A specialized library for integrating context-free grammars (CFG) in EBNF with the Hugging Face Transformers
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
Model Weights and Code for Pulse-PPG: An Open-Source Field-Trained PPG Foundation Model for Wearable Applications Across Lab and Field Settings (UbiComp 2025)
An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.
