Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW?

Multimodal large reasoning models (MLRMs) are rapidly advancing vision-language reasoning and are emerging as a foundation for cross-modal intelligence. Hallucination remains a persistent failure mode, manifesting itself as erroneous reasoning chains and misinterpretation of visual content. In this study, we observe that attention heads exhibit a staged division: shallow heads predominantly serve perception, while deeper heads shift toward symbolic reasoning, revealing two major causes of hallucination, namely perceptual bias and reasoning drift. To address these issues, we propose a lightweight and interpretable two-step plugin, Functional Head Identification and Class-conditioned Rescaling, which locates perception- and reasoning-oriented heads and regulates their contributions without retraining. Evaluations on three real-world MLRMs (Kimi-VL, Ocean-R1, R1-Onevision), six benchmarks across three domains, and four baselines show that our plugin achieves an average improvement of 5% and up to 15%, with only <1% additional computation and 9% of baseline latency. Our approach is completely model-agnostic and significantly enhances both the reliability and interpretability of the off-the-shelf MLRMs, thereby enabling their safe deployment in high-stakes applications. Our code is available at https://anonymous.4open.science/r/Functional-Attention-Control.

Ronald Reagan's daughter, Patti Davis, weighed in on the age issue at the forefront of the 2024 election on Sunday and said presidential candidates probably should face cognitive tests while running for office. Before President Biden was elected, Reagan was the oldest person to be elected president, at the age of 69. "Now, obviously, the president is in his 80s, former President Trump, the frontrunner, is in his late 70s. Do you think there should be cognitive tests for people running for the highest office in the land?" And just what we know about what age can do, it doesn't always do that, but it would probably be a good idea.

No technology since the atomic bomb has inspired the apocalyptic imagination like artificial intelligence. Ever since ChatGPT began exhibiting glints of logical reasoning in November, the internet has been awash in doomsday scenarios. Many are self-consciously fanciful--they're meant to jar us into envisioning how badly things could go wrong if an emerging intelligence comes to understand the world, and its own goals, even a little differently from how its human creators do. One scenario, however, requires less imagination, because the first steps toward it are arguably already being taken--the gradual integration of AI into the most destructive technologies we possess today. Check out more from this issue and find your next story to read. The world's major military powers have begun a race to wire AI into warfare.

When he looks back on it now – gambling his house, battling Robert Maxwell, turning up in the Soviet Union on a wing and a prayer – Henk Rogers still insists that he never considered giving up. "People ask me how much naivety was involved?" he recalls. "I would say 20% naivety/stupidity and 80% determination." That may be the key to success in many aspects of life. In Rogers's case, he was a video game publisher who knew he had discovered the next big thing: Tetris, a strangely addictive puzzle in which players must arrange falling bricks of differing shapes to form a solid wall.