AI
TowerMind is a new, lightweight tower-defense game environment for testing AI agents, especially large language models (LLMs), on planning and decision-making. * Low compute cost and easy to run * Multimodal observations: pixels, text, and structured game state * Customizable levels and rules * Built-in tests for model hallucination The authors create five benchmark
AI
TL;DR Large language models can sound confident, but if you nudge the context, their beliefs can fall apart. This paper proposes a better way to check if an AI keeps its story straight. * Problem: Popular checks like self-consistency can hide brittle knowledge. Answers that look reliable vanish under mild
Neuroimaging
What if lab-grade brain imaging could go wearable—and be analyzed with the same, reproducible playbook? Meet Cedalion, an open-source Python framework for making sense of light-based brain data: fNIRS and DOT (they use harmless light to track brain activity). Cedalion unifies the whole pipeline in one place: forward modeling
AI
AI agents usually follow a slow cycle: generate an idea, execute it, then check the results. This study shows a faster path: teach agents to predict outcomes first, then verify only the most promising options. * They build “execution priors” (inspired by world models) so runtime checks can be replaced by
AI helps spot pancreatic tumors in ultrasound Pancreatic cancer is aggressive and hard to detect early. This study tested a Vision Transformer–based deep learning model that segments tumors in endoscopic ultrasound (EUS) images. * Training: 17,367 EUS images from two public datasets using 5-fold cross-validation. * External test: 350 images
AI
What’s new VideoAR is a new way to generate videos with AI that predicts the next frame, over and over, at multiple scales. By separating what happens within a frame (spatial) from what happens across frames (temporal), it aims to make video generation faster and more stable. * 3D multi-scale
When robots should ask: Which one? In safety-critical places like operating rooms, a vague command like "Pass me the vial" can be dangerous. This paper introduces a simple idea with big impact: teach AI to detect when an instruction is ambiguous in a 3D scene and pause to
AI
Texting with AI can feel off—messages arrive in odd bursts with no real “thinking” pauses. Stephanie2 changes that. * Decides to send or wait: At every step, it chooses to message now or hold, like a human pausing to think. * Natural timing: It models delay as thinking time + typing time,
Transferring from a 2‑year to a 4‑year college too often means lost credits, extra costs, and delayed degrees. Working with the State University of New York (SUNY), researchers tested a stakeholder‑informed AI that suggests course equivalencies between institutions—so more credits count the first time. * Co-designed with
AI
New research shows that popular language models don’t persuade everyone the same way. Across 13 LLMs and 16 languages, the authors found consistent shifts in tone, appeals, and strategies depending on the recipient’s labeled gender — patterns that mirror well-known gender stereotypes. * Framework tests 19 categories of persuasive language
What if a single sentence could build a lifelike apartment you can walk through, open doors and drawers, and train robots in—safely and at scale? Meet SceneFoundry. * Text in, 3D world out: an LLM plans the floor layout; a diffusion model fills it with realistic, movable furniture. * Built for
Teaching robots and AR/VR systems to understand nimble finger work is hard—fingers hide each other, and tiny motions get lost. DexterCap changes that. * Affordable + automated: A low-cost optical setup with an end-to-end pipeline that needs minimal manual cleanup. * Reliable under occlusion: Dense, character-coded marker patches keep tracking stable