-
Harbin Institute of Technology
- Shanghai China
- 1838635312@qq.com
Starred repositories
An awesome list of Agent Harness engineering resources, including GitHub projects, tools, benchmarks, and practical guides.
Turn ideas into autonomous research with Git-like evidence histories—inspectable, reproducible, and reversible.
45+ tips for getting the most out of Claude Code, from basics to advanced - includes a custom status line script and Claude Code running itself in a container. Also includes the dx plugin: skills f…
12 Weeks, 24 Lessons, AI for All!
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
A curated collection of papers, benchmarks, surveys, and tools for model quantization, covering low-bit networks, LLMs, multimodal and generative models, vector and lattice quantization, and effici…
Bjontegaard metric calculation. Include BD-PSNR and BD-rate
Fast and differentiable MS-SSIM and SSIM for pytorch.
Accelerated Python package for computing the PSNR-HVS-M image metric
Comparison of IQA models in Perceptual Optimization
Code for Paper (Preserving Diversity in Supervised Fine-tuning of Large Language Models)
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation
Automatically Update Text-to-speech (TTS) Papers Daily using Github Actions (Update Every 12th hours)
LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis
This is an evolving repo for the paper "Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey".
torchange - A Unified Change Representation Learning Benchmark Library
[CVPR 2025] MatAnyone: Stable Video Matting with Consistent Memory Propagation
X-AnyLabeling: A lightweight, efficient, and unified cross-platform desktop application for annotating text, image, video, point cloud and multimodal data, combining versatile built-in tools with s…
A ComfyUI custom node designed for advanced image background removal and object, face, clothes, and fashion segmentation, utilizing multiple models including RMBG-2.0, VRMBG-3.0, FeyNoBg, Finegrain…
[ICCV 2025, Highlight] ZIM: Zero-Shot Image Matting for Anything
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
[CVPRW 2022] Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network
Speech Human Evaluation Estimation Toolkit (SHEET)