工具

Mellea 0.4.0 is the latest release of an open-source research project initiated and developed by IBM Research. Building on 0.3.0 foundational libraries and workflow primitives, 0.4.0 expands the library's integration surface and introduces new architectural patterns for structuring generative workflows. Simply put, a Granite Library is a collection of specialized model adapters designed to perform well-defined operations on portions of an input chain or conversation.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Fine-tuning an embedding model requires thousands of (query, relevant document) pairs. Most use cases don’t have this data readily available. Creating it manually is expensive, slow, and often biased by the annotator’s personal interpretation of what’s “relevant.”Instead of labeling data by hand, you can use an LLM (nvidia/nemotron-3-nano-30b-a3b) to read your documents and automatically generate high-quality synthetic question–answer pairs.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Bringing VLA models to embedded platforms is not a matter of model compression, but a complex systems engineering problem requiring architectural decomposition, latency-aware scheduling, and hardware-aligned execution. Addressing these challenges is essential to translate recent advances in multimodal foundation models into practical and deployable embedded robotic systems.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

In the last two posts (Part 1 and Part 2), we explored a wide range of architectural and training tricks for diffusion models. We tried to evaluate each idea in isolation, measuring throughput, convergence speed, and final image quality, and tried to understand what actually moves the needle. Instead of optimizing one dimension at a time, we’ll stack the most promising ingredients together and see how far we can push performance under a strict compute budget.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Achieving robust spatial reasoning remains a fundamental challenge for current Multimodal Foundation Models (MFMs). Existing methods either overfit statistical shortcuts via 3D grounding data or remain confined to 2D visual perception, limiting both spatial reasoning accuracy and generalization in unseen scenarios. Inspired by the spatial cognitive mapping mechanisms of biological intelligence, we propose World2Mind, a training-free spatial intelligence toolkit. At its core, World2Mind leverages 3D reconstruction and instance segmentation models to construct structured spatial cognitive maps, empowering MFMs to proactively acquire targeted spatial knowledge regarding interested landmarks and routes of interest. To provide robust geometric-topological priors, World2Mind synthesizes an Allocentric-Spatial Tree (AST) that uses elliptical parameters to model the top-down layout of landmarks accurately. To mitigate the inherent inaccuracies of 3D reconstruction, we introduce a three-stage reasoning chain comprising tool invocation assessment, modality-decoupled cue collection, and geometry-semantics interwoven reasoning. Extensive experiments demonstrate that World2Mind boosts the performance of frontier models, such as GPT-5.2, by 5%~18%. Astonishingly, relying solely on the AST-structured text, purely text-only foundation models can perform complex 3D spatial reasoning, achieving performance approaching that of advanced multimodal models.

The sensitivity analysis and validation of simulation models require specific approaches in the case of spatial models. We describe the spatialdata scala library providing such tools, including synthetic generators for urban configurations at different scales, spatial networks, and spatial point processes. These can be used to parametrize geosimulation models on synthetic configurations, and evaluate the sensitivity of model outcomes to spatial configuration. The library also includes methods to perturb real data, and spatial statistics indicators, urban form indicators, and network indicators. It is embedded into the OpenMOLE platform for model exploration, fostering the application of such methods without technical constraints.