AI Video2026
Enables Claude to “watch” videos by extracting timestamped frames plus captions/transcripts and feeding them to Claude for grounded Q&A. Key features: native captions first, Whisper fallback, frame deduplication, and multiple detail modes (transcript/efficient/balanced/token-burner). Useful for summarizing, debugging, and extracting moments.
AI Dataset2026
Provides ~55K multimodal VQA items with matched contrastive pairs and model‑generated rationales across five categories (General, Reasoning, Math, Graph/Chart, OCR), enabling research on faithful visual reasoning and robustness. Train split: 54,844 examples; license unspecified—verify before use.
AI Model2026
Provides unquantized BF16 weights of Qwen3.6-27B with the base model's MTP head grafted in for high-fidelity, uncensored text (and multimodal) generation. Includes deployment guidance and hardware-tuned variants for A100/H100 and Blackwell-class GPUs.
AI Model2026
Provides a GGUF-quantized build of NVIDIA's Nemotron 3 Nano Omni 30B (Reasoning) for local inference — enables multimodal (video/audio/image/text) reasoning, transcription, and document understanding on compatible runtimes such as llama.cpp, Ollama, vLLM, and TensorRT-LLM.
AI Dataset2026
Collection of 76 image-centric multimodal subdatasets (≈6.9M samples, ~39.56B estimated tokens) for training vision–language models, each published with a standardized conversation JSONL and dataset card. Media are referenced by path/URL and must be fetched separately; licensing is primarily CC-BY-4.0 with per-subdataset variations.
AI Dataset2026
Large-scale synthetic video dataset of 236,937 1080p clips (≈5,841 hours) of digital humans with per-frame metric depth and camera parameters — built as a controllable supplement for world-model pretraining, camera-motion generalization, and geometry-aware physical-AI research.
AI Dataset2026
Curated multimodal training corpus for spatial intelligence: ~8.16M QA-style samples paired with ~2.72M unique images (≈1.1 TB). Provides JSONL annotations, a 1,000-sample preview, and 52 independent image archives — used to train SenseNova-SI models.
AI Model2026
Image-to-video (I2V) diffusion model merge tuned for prompt-conditioned motion and evolution. Uses layer-scaled weight merges (not straight averaging) with BF16 and FP8 checkpoint options; prompt engineering is required for predictable motion and audio. Avoid large distilled Loras for best results.
AI Model2026
Distills DeepSeek‑V4's multi-step structured reasoning into a Qwen3.5‑9B model for fast image-text-to-text reasoning and agentic tool workflows. Trades larger teacher size for inference efficiency and improved procedural reasoning — good for low-latency research, evaluation, and agent integration.
AI Model2026
Unified 4B vision-language model for document understanding that converts images or text into template-driven structured JSON or clean Markdown. Key features: multimodal inputs (image+text), template-based extraction, reasoning vs non-reasoning modes, and vLLM/OpenAI-compatible deployment for OCR, invoice/forms extraction, and RAG preprocessing.
AI Agent2026
Lets developers build stateful, tool-enabled Python AI agents that run on Google's Antigravity runtime. Includes built-in tools (file I/O, shell, image generation), a declarative policy/hook system, multimodal input, and MCP integration.
AI Dataset2026
Provides ~85K contrastive visual question–answer pairs where each example contains an anchor and a matched counterpart (image, question, answer). Pairs span General, Reasoning, Math, Graph/Chart and OCR categories to help train and evaluate fine‑grained, faithful visual reasoning in VLMs.