Lists (1)
Starred repositories
Benchmark framework that measures cost, quality, and duration of coding agents across any AI Coding Assistant CLI, any model, and any use case — with pluggable verification and real-repo support.
AI/ML interview questions across 20+ companies , what was asked, what was tested, and how to prepare.
A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang, quantization, speculative decoding, benchmarking.
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
58 implementations of synthetic learning problems from Jürgen Schmidhuber's papers (1989-2025). Pure numpy, laptop-runnable, paper-comparison metrics per stub. Algorithmic-lineage companion to hint…
The open-source app everyone uses to manage agents at work
Set of tools to assess and improve LLM security.
[CVPR 2025] OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarking
[ICLR 2025] Official implementation for "SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations"
Official repository for "VideoPrism: A Foundational Visual Encoder for Video Understanding" (ICML 2024)
Benchmarks of approximate nearest neighbor libraries in Python
MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.
Evaluate and improve models and agents using environments
Scalable toolkit for efficient model reinforcement
Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translation—where one waits for the end of the source utterance to start translating--- H…
A vision-language model with an improved cross-attention mechanism for scalable streaming inference
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
PyTorch-based implementations of different normalization layers (e.g., BatchNorm, GroupNorm, InstanceNorm, and LayerNorm)
[NeurIPS 2025] Source Code for paper 'SharpZO: Hybrid Sharpness-Aware Vision Language Model Prompt Tuning via Forward-Only Passes'
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.