Goto

Collaborating Authors

 Industry



Review for NeurIPS paper: Organizing recurrent network dynamics by task-computation to enable continual learning

Neural Information Processing Systems

Summary and Contributions: This manuscript addresses the problem of continual learning in RNN. The authors propose a new learning rule that allows to organize the dynamics for different tasks into orthogonal subspaces. Using a set of neuroscience tasks, they show how this learning rule allows to avoid catastrophic interferences between tasks. By analyzing the dynamics of trained networks they provide evidence for why their learning rule is successful, it also allows them to discuss the problem of transfer learning. Strengths: - propose a new original solution to the problem of continual learning, which also allows them to address and understand under which conditions learning in one task can be transfered to learning off another task.


Review for NeurIPS paper: Adversarial Attacks on Linear Contextual Bandits

Neural Information Processing Systems

Summary and Contributions: Summary & Contributions: Authors study the scopes of adversarial attacks in linear contextual bandit algorithms which have applications in a wide range of domains. The authors consider adversarial attacks on both reward and the context and analyze the robustness (or lack of it) of various contextual linear bandit algorithms including LinUCB, LinTS, epsilon-greedy etc. Empirical evaluations are presented on various synthetic and two real datasets to examine the effect of attacks on these algorithms. Strengths: The problem of analyzing the effect of adversarial attacks on bandit algorithms are indeed interesting and well motivated, and present work is supposedly the first one to analyze this for stochastic contextual linear bandits. Authors also analyze some popularly studied bandit algorithms, like LinUCB, LinTS, epsilon-greedy, and showed the attacking strategies (as optimization problems) to fool above algorithms for playing some targeted suboptimal arm majority number of times. Experiments are fairly detailed and reported on a large set of datasets showing the effect on learning rate of existing techniques on different degree+type of attacks.


From florist to drone maker: How the weapon became so mainstream

BBC News

The ongoing conflict in Ukraine is often described as the world's first drone war. It has led to a continuing huge growth in the production of military drones, both within and outside Ukraine. Before Russia's invasion of Ukraine Kseniia Kalmus was a floral artist. Now, she makes drones for use against the Russians. It was just an obvious decision for me, she tells the BBC from the Ukrainian capital.



The 100 life decisions people dread most, according to psychologists

Popular Science

Answers were'surprisingly stable' across 4,380 survey participants. Breakthroughs, discoveries, and DIY tips sent every weekday. Some decisions are relatively easy to make: "What do I want to eat for dinner?" is low-risk and comparatively inconsequential in the grand scheme of things. Other scenarios, however, are much, more difficult . But what choices do people struggle with the most?


Football's Pep Guardiola calls on fans to attend Palestine charity match

Al Jazeera

How many times has Israel violated the ceasefire? How Israel is using'no war, no peace' model in Gaza How is Israel using PR firms to frame its war? Football's Pep Guardiola calls on fans to attend Palestine charity match NewsFeed Football's Pep Guardiola calls on fans to attend Palestine charity match Manchester City manager Pep Guardiola urged football fans to support an upcoming charity match featuring Palestine's national team at Barcelona's stadium, with the proceeds set to be donated to aid projects in Palestine. Ukraine's Kyiv pounded by hundreds of Russian drones Italian prosecutors investigate Bosnian war'sniper safaris' How many times has Israel violated the Gaza ceasefire?


AI's Impact on Mental Health

Communications of the ACM

There is no doubt artificial intelligence (AI) has the potential to improve access to mental health care. "One could imagine a world where AI serves as the'front line' for mental health, providing a clearinghouse of resources and available services for individuals seeking help,'' wrote the authors of the 2023 article "The Potential Influence of AI on Population Mental Health." Targeted interventions delivered digitally through chatbots "can help reduce the population burden of mental illness, particularly in hard-to-reach populations and contexts, for example, through stepped care approaches that aim to help populations with the highest risk following natural disasters," the article states. Besides Nomi, there are an increasing number of AI platforms people are using to create chatbots to take on several roles, including that of ad hoc therapist. Yet, while AI can assist in mental health management, it cannot replace human intuition. A trained therapist observes nuances that AI can't, such as body language, tone shifts, and unspoken emotions. Chatbots can be helpful, but mental health experts stress that they should never fully replace the human experience. That said, these mainstream chatbots are frequently being used for therapeutic purposes, as opposed to chatbots designed with mental health management in mind. Industry observers say the reasons are many: They provide emotional support when people are not ready to reach out to a therapist. They are anonymous, easy to use, convenient, available anytime, safe, judgment-free, affordable, and fast. These general-purpose chatbots help by providing comfort, validation, and a safe space for users to express themselves--all without the stigma that sometimes comes with traditional therapy settings. "Talking to a therapist can be intimidating, expensive, or complicated to access, and sometimes you need someone--or something--to listen at that exact moment,'' said Stephanie Lewis, a licensed clinical social worker and executive director of Epiphany Wellness addiction and mental health treatment centers.


Need to melt ice? Try high voltage metal

Popular Science

Technology Engineering Need to melt ice? A new molecular trick could transform deicing. Breakthroughs, discoveries, and DIY tips sent every weekday. As winter approaches, large swaths of the United States are eagerly awaiting their first big snowfalls of the season. As the snowflakes fall, many will dig out old, rusted sleds, toil over shaping the perfect snowball, and relish an evening brought back to life by a warm cup of hot cocoa .


30 Best Early Black Friday Deals on WIRED-Tested Gear (2025)

WIRED

We found early Black Friday deals on WIRED-tested smart bird feeders, smartwatches, vacuums, and more. Black Friday and Cyber Monday are two of the biggest shopping holidays of the year. Falling on the Friday and Monday after Thanksgiving, it's safe to expect Black Friday deals on thousands of items big and small. As always, the WIRED Reviews team will be scouring the Internet to find truly good deals on items we've actually hand-tested and would recommend to a friend. While the official sales have not yet started, there are already some great early discounts on reliable gear.