When the loss is set as squared loss, we can modify the functions regarding the truncated spectral projection.

It's an interesting time to be a long-running science fantasy media property in the streaming TV age. Star Trek is in the grip of an existential crisis as it (wrongly) fears it's too old-aged to be relevant. Star Wars became a battlefield in the culture war and, to duck all future bad faith criticism, gave us The Rise of Skywalker. And then there's Doctor Who, which is somehow managing to plough a 62-year furrow and still fill it with original ideas. This week the Doctor and Belinda go up against a sentient cartoon holding the patrons of a 1950s cinema hostage.

The start of any season of Doctor Who is important, doubly so when there's a new co-star to introduce. "The Robot Revolution" has to get us to fall in love with Belinda Chandra (Varada Sethu), ensnare new fans and keep existing ones hooked. Especially since it's the second of two series that Disney paid for, meaning it's got to do well enough to keep the money flowing. It's an awkward teenage date, with Alan clearly trying to win the heart of his beau by buying her one of those star adoption certificates. In 2025, Belinda is now a nurse at a busy London hospital where, in the background, the Doctor is searching for her.

In recent years, large language models (LLMs), empowered by massive text corpora and deep learning techniques, have demonstrated breakthrough advancements in cross-domain knowledge transfer and human-machine dialogue interactions [1]. Within the healthcare domain, LLMs are increasingly deployed across nine core application scenarios, including intelligent diagnosis, personalized treatment, and drug discovery, garnering significant attention from both academia and industry [2, 3]. A particularly important area of focus is the development and evaluation of Chinese medical LLMs, which face unique challenges due to the specialized nature of medical knowledge and the high-stakes implications of clinical decision-making. Hence, ensuring the reliability and safety of these models has become critical, necessitating rigorous evaluation frameworks [4]. Current research on medical LLMs evaluation exhibits two predominant trends. On one hand, general-domain benchmarks (e.g., HELM [5], MMLU [6]) assess foundational model capabilities through medical knowledge tests. On the other hand, specialized medical evaluation systems (e.g., MedQA [7], C-Eval-Medical [8]) emphasize clinical reasoning and ethical compliance. Notably, the MedBench framework [9], jointly developed by institutions including Shanghai AI Laboratory, has emerged as the most influential benchmark for Chinese medical LLMs. By establishing a standardized evaluation system spanning five dimensions--medical language comprehension, complex reasoning, and safety ethics--it has attracted participation from hundreds of research teams.

Large language model (LLM)-based agents have recently shown impressive progress in a variety of domains, including open-ended conversation and multi-step decision-making. However, applying these agents to social deduction games such as Werewolf, which requires both strategic decision-making and free-form language interaction, remains non-trivial. Traditional methods based on Counterfactual Regret Minimization (CFR) or reinforcement learning (RL) typically depend on a predefined action space, making them unsuitable for language games with unconstrained text action space. Meanwhile, pure LLM-based agents often suffer from intrinsic biases and require prohibitively large datasets for fine-tuning. We propose Latent Space Policy Optimization (LSPO), an iterative framework that addresses these challenges by first mapping free-form text to a discrete latent space, where methods like CFR and RL can learn strategic policy more effectively. We then translate the learned policy back into natural language dialogues, which are used to fine-tune an LLM via Direct Preference Optimization (DPO). By iteratively alternating between these stages, our LSPO agent progressively enhances both strategic reasoning and language communication. Experiment results on the Werewolf game show that our method improves the agent's performance in each iteration and outperforms existing Werewolf agents, underscoring its promise for free-form language decision-making.

Speech technologies are transforming interactions across various sectors, from healthcare to call centers and robots, yet their performance on African-accented conversations remains underexplored. We introduce Afrispeech-Dialog, a benchmark dataset of 50 simulated medical and non-medical African-accented English conversations, designed to evaluate automatic speech recognition (ASR) and related technologies. We assess state-of-the-art (SOTA) speaker diarization and ASR systems on long-form, accented speech, comparing their performance with native accents and discover a 10%+ performance degradation. Additionally, we explore medical conversation summarization capabilities of large language models (LLMs) to demonstrate the impact of ASR errors on downstream medical summaries, providing insights into the challenges and opportunities for speech technologies in the Global South. Our work highlights the need for more inclusive datasets to advance conversational AI in low-resource settings.

Rodriguez detailed that the MARS system gives surgeons "two extra arms" for instrument control, as well as camera stability. SURGICAL'REVOLUTION': Surgeon and CEO Dr. Alberto Rodriguez conducted the first-ever augmented reality (AR) abdominal surgery March 11 in Santiago, Chile. 'SCARY' SCHOOL TREND: Multiple Los Angeles-area school districts have investigated instances of "inappropriate," artificial intelligence-generated images of students circulating online and in text messages in recent months. AI IN PDF: Adobe announced that its new Acrobat artificial intelligence assistant will be available to Acrobat and Reader users starting on Tuesday. POTHOLE HEALER: Tech firm Robotiz3d is developing three technologies as part of its Autonomous Road Repair System.

When medical student Alyssa Murillo stepped into surgery, she was met with something most wouldn't expect to find in an operating room: a towering surgical robot. She wasn't there to observe the kind of surgeries she was used to seeing; instead she was getting an in-depth view inside the patient's body through the robot's video console. "It was incredible," says Murillo, who is now a forth-year general surgery resident at the University of California, San Francisco. "You have a full 3D view, which is different from any other minimally invasive surgery technique." The robot Murillo is referring to is the Da Vinci Surgical System.

Heart attacks could soon be diagnosed with better speed and accuracy than ever before thanks to a new AI tool. Researchers have developed an algorithm which they say could reduce pressure on A&E and reassure patients suffering from chest pain. A new study suggests that compared to current testing methods, their algorithm was able to rule out a heart attack in more than double the number of patients with an accuracy of 99.6 per cent. The team, from the University of Edinburgh, said this ability to quickly rule out a heart attack could greatly reduce hospital admissions and rapidly identify patients that are safe to go home. The current gold standard for diagnosing a heart attack involves measuring levels of the protein troponin in the blood.

Medical experts have issued a fresh call to halt the development of artificial intelligence (AI), warning it poses an'existential threat' to people. A team of five doctors and global health policy experts from across four continents said there were three ways in which the tech could wipe out humans. First is the risk that AI will help amplify authoritarian tactics like surveillance and disinformation. 'The ability of AI to rapidly clean, organise and analyse massive data sets consisting of personal data, including images collected by the increasingly ubiquitous presence of cameras,' they say, could make it easier for authoritarian or totalitarian regimes to come to power and stay in power. Second, the group warns that AI can accelerate mass murder via the expanded use of Lethal Autonomous Weapon Systems (LAWS).