最有价值项目

Heterogeneous Edge Realtime Measurement and Execution System: A Unified Open-Source Framework for Realtime Multimodal Physiological Sensing, Edge AI, and Intervention in Closed-Loop Smart Healthcare Applications

A self-hosted omni-modal agentic retrieval platform that understands, searches, and explores documents, images, audio, and video through semantic routing, hybrid retrieval, adaptive agents, and traceable citations.

A research-oriented training and evaluation framework for ECG-Language Models (ELMs)

Disentangled Graph Variational Auto-Encoder for Multimodal Recommendation with Interpretability, IEEE TMM

Codex Skill：让纯文本模型（DeepSeek）借助 StepFun step-3.7-flash 获得看图能力 | Give text-only Codex models (DeepSeek) image understanding via StepFun step-3.7-flash

Collects a multimodal dataset of Wikipedia articles and their images

Learning Adaptive Fusion Bank for Multi-modal Salient Object Detection

The code and weight for LoVA. LoVA is a novel model for Long-form Video-to-Audio generation. Based on the Diffusion Transformer (DiT) architecture, LoVA proves to be more effective at generating long-form audio compared to existing autoregressive models and UNet-based diffusion models.

[ACL 2023] VSTAR is a multimodal dialogue dataset with scene and topic transition information

The official implementation of NeurlPS 2025 D&B paper: IndustryEQA: Pushing the frontiers of Embodied Question Answering in Industrial Scenarios.

Diagnose vLLM inference servers

Interested in running a conspiracy of agents (technical term) on your Local AI Infra? Who isn't!

Local LLM speed measurements from a 4x RTX 3090 rig, with exact launch commands and per-run provenance.

Hands-on GPU/HPC infrastructure operations: K8s GPU scheduling, HAMi sharing, Slurm, observability & vLLM inference. Learn it free on a laptop; validate on one cheap GPU.

A fast TUI application (with optional webui) to visually navigate and inspect JSON and JSONL data. Easily localize parse errors in large JSONL files. Made with LLM fine-tuning workflows in mind.

SCoRe: Training Language Models to Self-Correct via Reinforcement Learning

Source code of CIKM2021 Paper 'Pre-training for Ad-hoc Retrieval: Hyperlink is Also You Need'

Get familiar with different fine-tuning techniques for text-to-image models, and learn how to teach a diffusion model a concept of your choosing

The project aim was to fine-tune the stable diffusion model in order to generate images in the LEGO style based on the prompt.

Automated Drowning Detection: A repository showcasing a deep learning-based solution using YOLO v8 architecture for swift and accurate identification of drowning instances in aquatic environments. Enhanced accuracy through meticulous fine-tuning and integrated methodologies. Empowering drowning incident response systems for improved efficiency.