AI Model2026
Processes images and text to produce structured, reasoning-rich text outputs for high-throughput agentic workflows. Sparse MoE design (198B total, ~11B active per token), 256k context window and selectable reasoning levels—optimized for single-pass parsing, verification, and multi-step automation.
AI Model2026
Performs hour-scale video understanding and fine-grained temporal localization while exposing agent-style multimodal tool/code/search abilities. Built on a sparse-attention long-context architecture (DSA) and a specialized inference stack—best used in GPU-backed research or production evaluation.
AI Model2026
Performs fast, high-quality vision–language grounding: given an image plus a natural-language prompt it returns bounding boxes or points for referred objects. Uses Parallel Box Decoding for parallel coordinate prediction (higher throughput) and targets research/non-commercial use.
AI Model2026
Performs image-to-text document parsing and OCR for complex elements (tables, formulas, charts, seals), with multilingual support (en/zh). It uses region-aware data optimization and progressive post-training to improve weak-region supervision and is plug-and-play compatible with PaddleOCR-VL-1.5.
AI Model2026
Quantized NVFP4 build of the Qwen3.6-35B MoE language model, optimized with NVIDIA Model Optimizer to cut model size and GPU memory by ~3.06× for inference. Designed for vLLM and NVIDIA GPU deployments (Hopper/Blackwell).
AI Model2026
Generates high-fidelity images from text prompts using NVIDIA's 64B Cosmos3-Super multimodal foundation model. Integrates with Hugging Face Diffusers and vLLM‑Omni, is released under OpenMDW1.1 for commercial use, and is optimized for Physical AI workflows (robotics, AV, simulation).
AI Model2026
Hybrid LFM2.5 text-generation model optimized for on-device assistants and agentic workflows — 8.3B total / 1.5B active parameters with 131,072-token context. Prioritizes low-latency, high-throughput inference and multilingual instruction-following; not optimized for pure heavy programming or knowledge-heavy QA without retrieval.
AI Video Papers2026
Performs training-free early-stage visual token compression inside the vision encoder to cut time-to-first-token (TTFT) and FLOPs for Video-LLMs. Introduces a decoupled spatial token selection strategy and reports up to 2.65× TTFT reduction and 61% FLOPs savings on LLaVA-OneVision-7B (NVIDIA A100) while preserving full-token accuracy — aimed at latency-sensitive video understanding.
AI Model2026
GGUF quantizations of Step-3.7-Flash: a sparse multimodal Mixture-of-Experts LLM with native image understanding, selectable reasoning levels, and a 256K context window. Ships multiple calibrated Q3/Q4/IQ quant files plus an mmproj vision projector for local llama.cpp inference on high-memory hosts.
AI Video Papers2026
Enables real-time streaming video-to-video editing (1280×704 @24 FPS) on a single RTX 5090 GPU. Uses a Hybrid Diffusion Transformer for balanced local/global modeling, Cycle‑Reverse Regularization for temporal consistency, and system-level mixed-precision and fused kernels to maximize throughput.
Introduces Draft-OPD, an on-policy distillation method for training lightweight draft models used in speculative decoding — it focuses learning on draft-induced errors via target-assisted rollouts and replay, improving acceptance length and enabling >5× lossless LLM inference acceleration.
Reallocates injected noise energy across frequency bands to match a diffusion model's spectral bias, improving sampling fidelity without retraining. Uses a timestep- and frequency-dependent colored-noise schedule as a plug-and-play inference-time SDE solver; shows sizable FID drops on ImageNet-256.