Parses documents and answers questions about their contents with a 0.8B-parameter model. It combines OCR, structured extraction, and visual question answering, including support for scanned, skewed, and photographed pages.
Turns a structured state (text/JSON/images/video) plus a schema of typed questions into probabilistic decisions in one forward pass. Multimodal, Jev/SystemOne-compatible, 64k context window, post-trained from Qwen3.8-27B; no free-form text output.
Converts a state and a typed-question schema into probabilistic, structured decisions from text, JSON, images, or video—returning per-option probabilities for noul/choice/score questions in a single forward pass. Post-trained from Qwen3.5-9B and compatible with Jev/SystemOne APIs; optimized for low-latency decisioning.
Couples a continuous latent diffusion trajectory with discrete token readouts so tokens are read from the latent at every step and fed back as a scaffold, reducing token-independence in parallel decoding and improving structured-task accuracy and LM perplexity.
Provides calibrated probabilistic decisions (yes/no, 2–256 choice, 0–5 score) in one forward pass, with an optional adaptive-thinking mode that invokes Gemma‑4 when System 1 is uncertain; supports text+image, 256K context and vLLM serving, but adaptive thinking is much slower.
Introduces a token-adaptive latent recurrence for diffusion language models that allocates computation per token during denoising. Key features: iterative latent refinement, discrete-feedback commits, and learned token-wise schedules to improve parallel decoding quality-efficiency trade-offs.
Returns calibrated probabilities for yes/no and multi-choice decisions using a two-stage System 1 (fast classifier) and System 2 (Gemma‑4 reasoning) pipeline; this NVFP4 release quantizes the 3,840 routed MoE experts to 4-bit so the model fits ≈17–18 GB of GPU memory while other weights remain bf16.
Maps multimodal inputs (text + images) to structured decisions (yes/no, choice, or scored rubric) in a single forward pass and returns calibrated probabilities. 3.1B parameters, long context (32,768 tokens), optimized for low-latency edge inference; not a text-generation/chat model.
Multimodal image/video-to-text model optimized for on-device inference: the 1B variant uses early visual-token compression and multiple quantization formats to improve capability-per-compute, and supports mobile platforms and common inference frameworks.
Enables multi-head, depth-wise residual retrieval in Transformers by expanding a single residual stream into multiple context-aware streams using causal depthwise convolutions. Improves pretraining convergence and downstream benchmark scores with minimal overhead, yielding notable iso-loss compute speedups in large MoE models.
Answers structured decision questions (choice / yes-no / score) about text, images and videos in one call and returns probabilities for every option. A 27B multimodal model (includes a 0.46B vision encoder), supports zero-shot classification, image/video inputs and integrates with vLLM / vLLM Semantic Router for high-throughput serving. Apache-2.0.
Generates calibrated decisions (choice/score/noul) from a prompt and optional images, up to 256 options. Routed MoE experts are quantized to NVIDIA NVFP4 to reduce weights to ~25.6 GB and GPU memory to ~23.3 GiB; provided as a vLLM-compatible System 1 decision model with a /v1/decide endpoint.