TL;DR People don’t agree on what ‘good’ UI design looks like—and AI shouldn’t assume they do. DesignPref is a new dataset: 12,000 head-to-head UI design comparisons, each labeled by 20 professional designers with multi-level ratings and short rationales. Designers often disagreed (low agreement), driven by
Can AI pass the pharmacist exam? New study says: mostly yes. Researchers tested two large language models on 2,306 real, text-only questions from China’s national pharmacist licensing exams (2017–2021), entered exactly as written in Chinese. The results: DeepSeek-R1 hit 90.0% accuracy, clearly ahead of ChatGPT-4o at
AI
If you’re a writer, artist, or publisher, you can now verify whether your content was used to train large language models—without a data center or a PhD. In “Copyright Detection in Large Language Models,” David Szczecina, Senan Gaffori, and Edmond Li introduce an open-source platform that makes copyright
AI
Fighting AI with AI How do we trust AI inside airplanes and self-driving cars? Deep neural networks are powerful, but opaque—and that makes traditional safety checks hard. This paper proposes using foundation models to make AI-enabled systems safer, from requirements to deployment. * REACT: uses Large Language Models to translate
MotionV2V is a new way to edit videos: instead of repainting pixels, it edits the motion itself. How it works: the system extracts a few motion trajectories from your video, you (or a prompt/tool) adjust them, and a motion-conditioned diffusion model regenerates the clip so content stays the same
When AI helps fly aircraft or drive cars, “just trust the model” isn’t enough. Deep neural networks are opaque, and the gap between plain‑English requirements and low‑level code blocks traditional safety assurance. This paper proposes using foundation models to assure AI itself, via two complementary tools: * REACT:
AIMusic
What if you could sketch a “tension curve” and have an AI compose music that follows it? That’s exactly what this study delivers. Tonal tension—the ebb and flow of stability vs. suspense in harmony—drives how music feels. The authors plug a computational tension model into a Transformer
Meet DeCo, a new way to generate images directly in pixels - faster and sharper. Instead of one big model juggling everything, DeCo splits the job by "frequencies": the Diffusion Transformer learns low-frequency stuff (overall shapes and colors), while a lightweight pixel decoder paints high-frequency details (edges and
6G
LLM-powered network agents often decide based on simple averages—ignoring rare but catastrophic events. In 6G, that bias can break service guarantees. This work introduces a risk-aware negotiation framework for 6G network slicing that teaches agents to plan for the worst, not just the mean. * Predict the full latency distribution
Large language models are powerful but can be tricked into harmful outputs (jailbreaks). Most research isolates either attacks or defenses. This paper introduces ACE-Safety, a "train both sides" approach where an attacking AI and a defending AI grow stronger together—like sparring partners—to harden real-world systems. * GS-MCTS:
QuantumComputing
What if we could let evolution design quantum circuits that compress data? This paper explores exactly that with quantum autoencoders—models that shrink high‑dimensional quantum or classical data while keeping the important bits. The authors introduce a neural architecture search framework powered by a genetic algorithm. Instead of hand‑
AI
Meet MAESTRO: an AI coach for teamwork Training teams of AI agents is hard: you must design the right "score" (rewards) and the right practice plan (curriculum). Get either wrong and learning stalls. MAESTRO uses a large language model (LLM) as an offline training architect—so it guides