Dipta04/RNN: A simple RNN-based project focused on sequence learning and deep learning model implementation.
A simple RNN-based project focused on sequence learning and deep learning model implementation.
Repositories
MAC-AutoML/Awesome-Self-Distillation: A curated reading list for awesome self-distillation works in LLMs, MLLMs, reasoning models, diffusion LLMs, and large generative models.
A curated reading list for awesome self-distillation works in LLMs, MLLMs, reasoning models, diffusion LLMs, and large generative models.
NeXra-AI/awesome-ai-image-prompts: Prompt-as-Code library — 955 curated prompts for GPT-Image-2, Nano Banana, Seedance and more. RAG-ready, multi-language (zh/en/ms).
Prompt-as-Code library — 955 curated prompts for GPT-Image-2, Nano Banana, Seedance and more. RAG-ready, multi-language (zh/en/ms).
cclank/lanshu-awesome-ai-video-kit: 做企业 AI 视频项目逼出来的工具包 · 411 prompt · 15 模型 · 7 Claude Skill · 14 篇方法论
做企业 AI 视频项目逼出来的工具包 · 411 prompt · 15 模型 · 7 Claude Skill · 14 篇方法论
Tejas-TA/predikit: pypi-predikit: Turn any sklearn/XGBoost model into an LLM-callable tool. Framework-agnostic
pypi-predikit: Turn any sklearn/XGBoost model into an LLM-callable tool. Framework-agnostic
Harahan/RTDMD: [Arxiv 2026] This is the official PyTorch implementation of "RTDMD: Reinforcing Few-step Generators via Reward-Tilted Distribution Matching"
[Arxiv 2026] This is the official PyTorch implementation of "RTDMD: Reinforcing Few-step Generators via Reward-Tilted Distribution Matching"
satharsait/AI-Phishing-Detection: AI-based phishing detection system developed as a BCA academic project using cybersecurity and machine learning concepts.
AI-based phishing detection system developed as a BCA academic project using cybersecurity and machine learning concepts.
yakhyo/face-image-quality-assessment: eDifFIQA: Towards Efficient Face Image Quality Assessment Based on Denoising Diffusion Probabilistic Models
eDifFIQA: Towards Efficient Face Image Quality Assessment Based on Denoising Diffusion Probabilistic Models
baoweise-bot/aimili-vpngate: aimili-vpngate是一个借助vpngate.net让Linux用干净ip出站的代理工具。
aimili-vpngate是一个借助vpngate.net让Linux用干净ip出站的代理工具。
lynote-ai/ai-detector-skill: A free detector capable of identifying content generated by all advanced AI models.
A free detector capable of identifying content generated by all advanced AI models.
UditAkhourii/adhd: ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude Agent SDK. Fans out parallel divergent thoughts under different cognitive frames, scores, prunes traps, deepens the survivors. The no-brainer skill for creative and interdisciplinary work.
ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude Agent SDK. Fans out parallel divergent thoughts under different cognitive frames, scores, prunes...
credkellar-boop/Mona: Mona is an open-source, long-form video generation framework built on advanced Spatio-Temporal Diffusion Transformers. While standard models cap at short clips, Mona is engineered for narrative coherence up to 30 minutes. Using streaming VAEs and memory-augmented transformers, it bypasses VRAM limits to create unified, cinematic stories.
Mona is an open-source, long-form video generation framework built on advanced Spatio-Temporal Diffusion Transformers. While standard models cap at short clips, Mona is engineered ...
Merserk/ComfyUI-PiD: ComfyUI custom node for NVIDIA PiD pixel diffusion decoding and upscale workflows
ComfyUI custom node for NVIDIA PiD pixel diffusion decoding and upscale workflows
infiniteYuanyl/VRCD: Official implementation of paper “Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large Language Models”
Official implementation of paper “Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large Language Models”
code-yeongyu/lazycodex: LazyCodex: Codex for no-brainers. You don't need to think. Just prompt with ultrawork.
LazyCodex: Codex for no-brainers. You don't need to think. Just prompt with ultrawork.
HiDream-ai/DMSampler: [ICML 2026] Official Implementation of DMSampler: Distillation Models are Good Samplers for Diffusion Reinforcement Learning
[ICML 2026] Official Implementation of DMSampler: Distillation Models are Good Samplers for Diffusion Reinforcement Learning
JasonLam08/cursor_agent_status_light: A BLE-powered status light for Cursor Agent, using ESP32-C3 to visualize AI coding states such as thinking, busy, success, error, and waiting for user action. 基于 ESP32-C3 的 Cursor Agent BLE 状态灯，用红绿灯直观显示 AI 编程过程中的思考、忙碌、成功、错误以及等待用户操作 等状态。
A BLE-powered status light for Cursor Agent, using ESP32-C3 to visualize AI coding states such as thinking, busy, success, error, and waiting for user action. 基于 ESP32-C3 的 Cursor ...
1ove9/antenna-forge: AI-driven inverse antenna design with real NEC2 + openEMS in the loop. Try the live in-browser playground.
AI-driven inverse antenna design with real NEC2 + openEMS in the loop. Try the live in-browser playground.
iOptimizeThings/dlmserve: OpenAI-compatible HTTP serving for diffusion language models. Continuous batching + LocalLeap acceleration.
OpenAI-compatible HTTP serving for diffusion language models. Continuous batching + LocalLeap acceleration.
SheerWill007/Fintech-Fraudies: Real-time fintech fraud detection system combining machine learning, risk analysis, and transaction monitoring in a scalable monorepo architecture.
Real-time fintech fraud detection system combining machine learning, risk analysis, and transaction monitoring in a scalable monorepo architecture.
realrossmanngroup/no_ai_slop_writing_rules: Claude Code reference: write in Louis Rossmann's voice, never like AI slop. Portable CLAUDE.md plus skills.
Claude Code reference: write in Louis Rossmann's voice, never like AI slop. Portable CLAUDE.md plus skills.
quarqlabs/agent-oss: A recursive evidence-gated cognitive runtime for memory-native AI agents, combining hybrid retrieval, temporal reasoning, async learning, and plug-and-play tools.
A recursive evidence-gated cognitive runtime for memory-native AI agents, combining hybrid retrieval, temporal reasoning, async learning, and plug-and-play tools.