We can't let them hide behind their models From Gaza to Iran, the pattern is the same: precision weapons, chosen blindness, and dead children. There is an Israeli military strategy called the "fog procedure". First used during the second intifada, it's an unofficial rule that requires soldiers guarding military posts in conditions of low visibility to shoot bursts of gunfire into the darkness, on the theory that an invisible threat might be lurking. It's violence licensed by blindness. Shoot into the darkness and call it deterrence. With the dawn of AI warfare, that same logic of chosen blindness has been refined, systematized, and handed off to a machine.

Knowledge Tracing (KT) models face a critical ``Performance-Complexity Trap'': capturing complex cognitive dynamics like learning sessions and memory decay typically requires deep hierarchical architectures, which incur prohibitive computational costs for real-time deployment. To resolve this, we propose FlatFormer, a streamlined architecture based on the novel design paradigm of ``Information Injection over Structural Stacking.'' Unlike parameter-heavy hierarchical models, FlatFormer leverages a standard flat Transformer augmented with two lightweight injection mechanisms: (i) a hybrid input encoding strategy combining learnable session identifiers with fixed sinusoidal step embeddings; and (ii) a pre-computed power-law bias integrated directly into attention logits to explicitly model the forgetting curve. Extensive experiments on four large-scale datasets (e.g., EdNet, Junyi) show that FlatFormer achieves state-of-the-art performance. For example, on the EdNet dataset, compared to the strongest hierarchical baseline (HiTSKT), its absolute AUC increased by 8.3%, while using less than 15% of parameters, and inference speed was about three times faster. These results validate that high cognitive fidelity does not necessitate architectural complexity.

In risk-averse reinforcement learning (RL), the goal is to optimize some risk measure of the returns.

In risk-averse reinforcement learning (RL), the goal is to optimize some risk measure of the returns.

Brian Bussard has 25 tiny chips in his brain. They were installed in February 2022 as part of a study testing a wireless device designed to produce rudimentary vision in blind people. Bussard is the first participant. Bussard, who's 56, lost vision in his left eye at age 17 after his retina detached. The right eye followed in 2016, leaving him completely blind.

Agents trained with DQN rely on an observation at each timestep to decide what action to take next. However, in real world applications observations can change or be missing entirely. Examples of this could be a light bulb breaking down, or the wallpaper in a certain room changing. While these situations change the actual observation, the underlying optimal policy does not change. Because of this we want our agent to continue taking actions until it receives a (recognized) observation again. To achieve this we introduce a combination of a neural network architecture that uses hidden representations of the observations and a novel n-step loss function. Our implementation is able to withstand location based blindness stretches longer than the ones it was trained on, and therefore shows robustness to temporary blindness. For access to our implementation, please email Nathan, Marije, or Pau.

A robotic arm that can accurately inject drugs directly into tiny veins at the back of the eyeballs could help treat a disease that causes degenerative blindness. Retinal vein occlusion occurs when blood clots block veins in the retina. It affects more than 16 million people worldwide and can eventually lead to blindness.

Since 2017, ophthalmology has been the busiest of all the medical specialties in the UK's National Health Service in terms of clinical appointments. Nearly 10 percent of all NHS outpatient appointments are related to eye problems. That's nearly 10 million appointments per year, and that number has risen by more than a third in the past five years. Between the ages of 18 and 65, the main cause of blindness is diabetic eye disease. But the population is getting older, and we're also seeing an increasing prevalence of diseases like age-related macular degeneration (AMD).