Can “vibe coding” beat grad CS students? Researchers staged a coding tournament in a realistic logistics game: companies bid in auctions, then plan pickup-and-delivery routes under capacity limits. Agents must both bid strategically under uncertainty and optimize routes to maximize profit. What happened * Human-coded agents (from graduate
Can your favorite AI solve a Bengali riddle? BengaliFig is a new challenge set that puts large language models to the test on figurative, culturally grounded reasoning in Bengali—a widely spoken but low-resourced language. The dataset packs 435 riddles from oral and literary traditions, each richly labeled across
AI
Which AI better helps pharmacists-in-training? Researchers tested DeepSeek-R1 and ChatGPT-4o on 2,306 real, text-only questions (2017–2021) from China’s pharmacist licensure exam, scoring exact-answer accuracy in Chinese. * DeepSeek-R1: 90.0% accuracy vs. ChatGPT-4o: 76.1% (p<0.001) * Advantages
AI used in healthcare, cars, and finance must be trustworthy. Accuracy alone can’t show when a model is unsure or under attack. Meet PaTAS — a parallel "trust meter" for neural networks built on Subjective Logic. * Runs alongside normal model math with special Trust Nodes and Trust Functions.
AudioAI
AI that pulls the vocals out—fast Ever wished you could solo a singer from any track without artifacts? This research shows how, using a latent diffusion model that separates vocals from full mixes. * Efficient: Generates in a compact audio latent space, then decodes to sound—speeding up training and
AI
Can AI think creatively? Large language models are great at step-by-step logic, but real-world breakthroughs need more than routine problem-solving. This paper proposes a creative reasoning framework, rooted in cognitive science, and turns it into practice with "Universe of Thoughts" (UoT): methods that help
Why this matters AI agents that browse the web can be tricked by malicious webpages—a tactic called prompt injection. Instead of just spitting out wrong text, these attacks can push agents to take risky real-world actions (like misfiling forms or sending messages). BrowseSafe builds a realistic benchmark of
AudioAI
Ever wanted studio‑clean vocals from any song? This research introduces a generative system that separates singing voices from full mixes using a latent diffusion model. How it works * Generates audio in a compact latent space, then decodes it back to sound—making training and inference efficient. * Trained only on
LLMs are great at step-by-step "chain-of-thought" logic, but real breakthroughs need creative reasoning. This paper introduces Universe of Thoughts (UoT): a framework, inspired by cognitive science, that teaches AI to explore many idea paths—not just the obvious ones. * Combinational: mix existing ideas in
What if computers could not only see, but also smell? Researchers introduce New York Smells, a large, real-world dataset pairing photos with olfactory sensor readings. The set spans 7,000 smell-image pairs from 3,500 different objects across indoor and outdoor environments—about 70x more objects than prior
AI
AI assistants are starting to browse the web for us—but webpages can hide sneaky instructions that make them misbehave. This paper maps that threat, called prompt injection, and shows how to defend against it in real-world browsing. What the researchers did * Built a realistic benchmark of attacks embedded
AI
How do we know an AI is truly helpful, honest, safe—and follows instructions? Today, we usually read its answers and score them, which can be slow, costly, and subjective. This paper finds a simple clue: when compared to a trusted reference, models that write well also judge well. The