AVI-HT is an adaptive visual-IMU fusion approach for 3D hand pose tracking that jointly models egocentric images with on-glove 6-DoF IMU signals. It achieves significantly improved accuracy and availability, especially in hand-object interaction scenarios with heavy visual occlusion. Key ingredients include synchronized multi-modal training data and a cross-sensor deep attention mechanism. Experiments on the DexGloveHOI dataset show that AVI-HT reduces mean keypoint error by 16.1% and its wrist-aligned variant by 24.2% over baselines.

MRecover is a conditional generative model that synthesizes T2w TSE images from routinely acquired T1w MRI to recover motion-corrupted hippocampal subfield segmentation. Trained on 7T data (n=577), it achieved high in-domain fidelity (SSIM=0.84, FSIM=0.94) and generalized well to 3T data. In the ADNI3 dataset, it increased analyzable subjects by 31.8% (593 vs 450) and improved effect sizes for diagnostic group differences.

Existing vision-language models underperform in ultrasound visual question answering because they fail to emulate sonographers' active zooming into lesions and ignore annotation subjectivity. This paper introduces a framework with a Zoom-then-Diagnose paradigm and an uncertainty-aware reward within GRPO, encouraging accurate predictions on clear cases and caution under ambiguity. Lesion localization improves by 39.3% on liver, breast, and thyroid datasets.

This paper proposes the Ablate-to-Validate diagnostic principle and its instantiation, the Token Replacement Test (TRT), to determine whether vision-language models (VLMs) genuinely use continuous latent tokens for reasoning. Experiments show that VLMs retain most performance gains even when token content is corrupted or replaced, indicating that accuracy improvements are a misleading proxy for latent-token reasoning.

UniVL introduces a spatially grounded contextual image generation task that uses a unified visual input with rendered text instructions, eliminating the need for a separate text encoder. The method achieves improved image quality (FID from 14 to 11, PSNR from 16 to 20) and up to 52% reduction in inference TFLOPs and 44% faster runtime on a new benchmark of 477K images.

GenEvolve is a self-evolving framework for image generation agents that models each generation attempt as a tool-orchestrated trajectory. It compares multiple trajectories for the same request and extracts best-worst differences into structured visual experience, providing dense token-level supervision. Experiments show state-of-the-art performance on public benchmarks and the newly constructed GenEvolve-Bench.

PhysX-Omni is a unified framework for generating simulation-ready physical 3D assets across diverse categories including rigid, deformable, and articulated objects. It introduces a novel geometry representation tailored for Vision-Language Models that directly encodes high-resolution 3D structures without compression, significantly improving generation performance. The framework also presents the first general simulation-ready 3D dataset, PhysXVerse, and a comprehensive benchmark, PhysX-Bench, for evaluating both generative and understanding capabilities. Experiments demonstrate strong performance in generation and understanding, with potential applications in simulation-ready scene generation and robotic policy learning, advancing embodied AI and physics-based simulation.

Streaming vision-language models (VLMs) continuously generate responses from an instruction and an online frame stream, crucial for real-time visual assistants. Existing benchmarks focus on offline evaluation, missing metrics like proactiveness and consistency. VSAS-Bench introduces a new framework with over 18,000 dense annotations, synchronous/asynchronous protocols, and reveals that conventional VLMs can be adapted without extra training to outperform dedicated streaming models.

Amazon Nova Act is now a HIPAA eligible service, enabling the deployment of autonomous browser-based AI agents in regulated healthcare environments to process ePHI and automate workflows like claims processing and referral coordination.

LangSmith Auth Proxy keeps credentials out of sandbox runtimes, injects auth headers at the network layer, and lets teams define egress policies and dynamic credential flows to secure agent network access.

Move beyond token streaming. Learn how the latest streaming primitives in Deep Agents, LangChain, and LangGraph enable typed events, scoped subscriptions, subagent visibility, multimodal outputs, and resilient frontend experiences for building production-ready agent applications.

Simon Willison announces the first release of Datasette Agent, an extensible AI assistant for Datasette that allows users to ask questions about their data through a conversational interface. It supports plugins for charts, image generation, and code execution in sandboxes, and can run against local models. The assistant is built on the LLM library and represents the convergence of LLM and Datasette.

Traditional radiology worklist systems rely on rigid rules that cause diagnostic delays and increased costs. This post shows how to build an intelligent workflow using AI agents on Amazon Bedrock AgentCore and Strands Agents SDK, enabling context-aware case assignment that considers radiologist specialization, workload, fatigue, and case complexity.

A Datasette Agent plugin for running commands in a Fly Sprites sandbox.