AI Image2025
Self-supervised vision foundation model producing dense, patch-level features that transfer to classification, segmentation, depth, and detection with a frozen backbone. Spans ViT-S (21M) to ViT-7B (6.7B params), plus ConvNeXt and satellite variants.
AI Agent2025
Framework for building multi-modal AI agents that watch, listen, and reason over live video, pairing vision models (YOLO, Roboflow, Moondream) with LLMs like Gemini and OpenAI. Agents join calls in ~500ms and keep audio/video latency under 30ms.
AI Video2025
Generates explorable, 3D-consistent virtual worlds from a single image or short video. Includes official implementations of Lyra‑1 (feed‑forward 3D/4D scene generation via video-diffusion self-distillation) and Lyra‑2 (long-horizon, explorable generative 3D worlds). Best for research and creative prototyping; requires substantial GPU compute.
AI Video Papers2025
Argues a single web-scale generative video model handles vision tasks zero-shot the way LLMs handle language. Probes Veo 3 on segmentation, edge detection, image editing, physical and affordance reasoning, and puzzles like maze solving and symmetry.
AI Agent2025
Automates multi-step web tasks by perceiving webpages as pixels and issuing low-level mouse, keyboard and scroll actions. A 7B-parameter multimodal agent trained on 145K synthetic trajectories (FaraGen), designed for on-device deployment and efficient task completion (~16 steps/task).
AI Agent2026
Grows a personal skill tree by crystallizing each solved task into reusable skills; a ~3K-line autonomous agent framework that gives an LLM system-level control of browser, terminal, filesystem, input/vision and mobile (ADB) via nine atomic tools, optimized for low token cost.
Reduces object-driven shortcut learning in zero-shot compositional action recognition by enforcing temporal verb cues and regularizing against frequent object-verb co-occurrence priors. Proposes RCORE with Co-occurrence Prior Regularization (treats frequent co-occurrences as hard negatives) and Temporal Order Regularization. Evaluated on Sth-com and EK100-com with improved compositional generalization.
AI Image2026
Multimodal OCR and document-understanding toolkit for recognizing complex layouts, tables, formulas and code. Uses Multi-Token Prediction and stable RL for better training; ships as a 0.9B-parameter model with a Python SDK and deployment guides for vLLM, SGLang and Ollama.
AI Dataset2026
Paired brain MRI scans and radiology text annotations for multimodal vision–language research. Provides image-level labels and image–text pairs suited for VQA, classification, and image-to-text tasks; CC BY-NC-SA 4.0 and ~10K–100K samples — research/non-commercial use.
AI Deploy2026
Runs local AI models on Apple Silicon as an OpenAI‑compatible server, emphasizing low latency, prompt caching, and reliable tool-calling. Optimized for M1–M4 Macs with multimodal support and drop‑in compatibility for IDEs and agent frameworks.
AI Model2026
An instruction‑tuned Gemma 4 E4B multimodal model on Hugging Face that accepts text, images and audio and generates text; notable for 128K long context support, built-in thinking mode, and an on‑device‑friendly E4B architecture under an Apache‑2.0 license.
AI Model2026
Instruction-tuned Gemma 4 31B multimodal model that generates text from text+image inputs with up to 256K context. Dense 31B variant optimized for vision-language understanding, long-context reasoning, and coding; Apache‑2.0 licensed.