Granite 4.0 3B Vision: Compact Multimodal Intelligence for Enterprise Documents
More from the blog
Measuring benchmark optimization in speech recognition
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
State of Open Models: Summer 2026 Observations
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Related papers
Iterative Flow Matching - Path Correction and Gradual Refinement for Enhanced Generative Modeling
This work explores image generation using flow matching using flow matching and proposes an iterative process that can be integrated into virtually any generative modeling technique, thereby enhancing the performance and robustness of image synthesis systems.
EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding
EgoMemReason is introduced, a comprehensive benchmark for week-long egocentric video understanding through memory-driven reasoning that evaluates three complementary memory types: entity memory, tracking how object states evolve and change across days; event memory, recalling and ordering activities separated by hours or days; and behavior memory, abstracting recurring patterns from sparse, repeated observations over the whole week period.
Mask2Real-WM: Segmentation Masks as a Sim-to-Real Bridge for Controllable Dexterous World Models
Mask2Real-WM is presented, a two-stage action-conditioned world model for dexterous manipulation that decouples pixel prediction into a dynamics model and a rendering model that shows that mask conditioning and simulation pretraining are both required for per-DoF action controllability across all 23 degrees of freedom.
Planning-aligned Token Compression for Long-Context Autonomous Driving
This work proposes COMPACT-VA, a planning-aligned working memory framework built on conditional VQ-VAE, compressing extended context into bounded representations, and evaluates on high-signal dynamic scenarios where historical context is most critical for behavior correctness, and accordingly design behavioral metrics.