[ICLR 2026 Oral] Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation

Code for the paper “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling”

Real-Time VLAs via Future-state-aware Asynchronous Inference.

Code for the paper “Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs”

[ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter

[CVPR 2026] ForeAct: Steering Your VLA with Efficient Visual Foresight Planning

A sparse attention kernel supporting mix sparse patterns

[NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation

A PyTorch-based framework for Quantum Classical Simulation, Quantum Machine Learning, Quantum Neural Networks, Parameterized Quantum Circuits with support for easy deployments on real quantum computers.