EfficientSAM3 compresses SAM3 into lightweight, edge-friendly models via progressive knowledge distillation for fast promptable concept segmentation and tracking.
- artificial-intelligence
- computer-vision
- edge-ai
- efficient-ai
142,187 visible repositories in the index
97–120 of 123 · Most stars
EfficientSAM3 compresses SAM3 into lightweight, edge-friendly models via progressive knowledge distillation for fast promptable concept segmentation and tracking.
On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators
MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks. In NeurIPS 2020 workshop.
[CVPR 2024 Highlight] Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
Prompt engineering for developers
Official inference code for BluePixel, a native 4K image editing model with 4-step distilled inference, built on FLUX.2 Klein and DCAE.
Flash Diffusion — accelerating conditional diffusion models (AAAI 2025 Oral)
SIGKDD'2019: DeepGBM: A Deep Learning Framework Distilled by GBDT for Online Prediction Tasks
A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.
Distill your knowledge, memories, and decisions into an open-source, inspectable AI Agent Twin.
A meta-skill that produces skills. Point it at any codebase and it distills the project's rules, workflows, and hard-won lessons into a dedicated skills/<name>/ directory — a project skill that becomes the single source of truth every AI agent (Cursor, Claude Code, Codex, Windsurf, Gemini) consults before every task.
Segmind Distilled diffusion
AI Code Security Anti-Patterns distilled from 150+ sources to help LLMs generate safer code.
Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL.
💭 Aspect-Based-Sentiment-Analysis: Transformer & Explainable ML (TensorFlow)
Knowledge Distillation: CVPR2020 Oral, Revisiting Knowledge Distillation via Label Smoothing Regularization
A general framework for distilling human-created multimodal resources into reusable, executable skills that AI agents can browse, compose, and run, validated across diverse domains including web, PowerPoint, Excel, Blender, CAD, Unreal Engine 5, and REAPER-based music production.
Official code for "Parser-Free Virtual Try-on via Distilling Appearance Flows", CVPR 2021.
From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracle, and interpretability tooling.
a systemone proxy using embeddings that distills a teacher model
[Writing] Claude / Codex skill for drafting abstracts, introductions, methods and experiments in the style of CVPR/ICCV/NeurIPS best papers, distilled from 60 award-winning papers.
[Tech Report] Simplifying and Improving On-Policy Distillation for Few-step Diffusion
Local-first AI trend radar and live-session distillation
Out-of-the-box E2E relay server (relay-e2e/v1) for Cloudflare Workers — one-command deploy. Reference agent & client included. Distilled from Alma with permission.