Lists (4)
Starred repositories
[ACL 2026 Main] Training, inference, and testing of the SAC speech codec model.
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
[ICLR 26] TempFlow-GRPO (Temporal Flow GRPO), a principled GRPO framework that captures and exploits the temporal structure inherent in flow-based generation.
[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
the dataset and code for "Flow-guided One-shot Talking Face Generation with a High-resolution Audio-visual Dataset"
Official implementations for paper: DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models
MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering
AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D.
Perceptual video quality assessment based on multi-method fusion.
RTMPose series (RTMPose, DWPose, RTMO, RTMW) without mmcv, mmpose, mmdet etc.
A drop-in replacement for the standard Categorical Cross-Entropy (CCE) loss that significantly improves OOD and Calibration performance without reducing ID performance.
[CVPR2026]We present FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length videos while achieving up to 6$\times$ acceleration in inference…
Unified Schema-Based Information Extraction
"ClawTeam: Agent Swarm Intelligence" (One Command → Full Automation)
A local-first multi-agent runtime for ML research. One task in, continuous iteration out, with leader, researcher, and trainer working through a forum-style runtime board and a separate training q…
Multi-scale Attention Network for Single Image Super-Resolution (CVPRW 2024)
Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with file, network, and credential controls.
Few-step diffusion for audio-driven talking head generation making diffusion models speak faster without losing their composure.
[ICLR 2025] Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation
N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution (CVPR2023 Accepted)
Write scalable load tests in plain Python 🚗💨
This was my private research codebase during grad school. After graduation I made it all public
Tiny AutoEncoder for Stable Diffusion (and other image models)
OpenFace 3.0 – open-source toolkit for facial landmark detection, action unit detection, eye-gaze estimation, and emotion recognition.