Artificial Intelligence Medical Compendium

As Multimodal Large Language Models (MLLMs) can describe increasingly complex visual scenes, token-level grounding becomes crucial. Yet, when an MLLM generates "the yellow banana on the left", established grounding approaches focus on what is in the ... read more 

Most image generation models rely on uniform tokenization, allocating the exact same computational budget to equally-sized image patches. This static paradigm cannot adapt to different resource constraints at inference time, and yields suboptimal qua... read more 

Anatomical continuity provides complementary information for medical image restoration, but its use requires accounting for local anatomy and variations in slice sampling. We introduce ContiLNN, which augments two-dimensional restoration backbones wi... read more 

Large Multi-modality Models (LMMs) have made significant progress in visual understanding and generation, but still face challenges in visual editing, particularly in following complex instructions, preserving appearance consistency, and supporting f... read more 

Most robot policies keep a model in the control loop: a VLA maps observations to actions, and an Agent Harness, such as Agent-as-Policy or Harness VLA queries a VLM for decision making at run time. We propose a different view: the embodied world is a... read more 

Faithful visual world simulation requires generated videos to maintain 4D world consistency, encompassing both static and dynamic consistency. Static consistency requires coherent 3D structure in static environments across viewpoints, while dynamic c... read more 

Reconstructing complete 3D object assets from monocular or sparse multi-view observations remains challenging. Generative 3D foundation models can complete object geometry beyond the observed views, but their predictions may not faithfully reproduce ... read more 

Current 3D generation methods lack explicit local control: geometric adherence is often defined by a global control strength, and appearance cannot be specified locally. We present SpaceFlow, a training-free pipeline for locally controllable 3D gener... read more 

Existing spatial reasoning benchmarks mainly test spatial perception: reading off relations already visible in the input. Yet real-world spatial intelligence demands predictive spatial reasoning: constructing a scene from observations, anticipating h... read more 

Multiplayer world models must generate independently controlled views with consistent representations of both players and their shared environment. Most existing approaches coordinate multiple players through joint multi-view generation, whose cost g... read more