February 2026

Quadruped robots are used for primary searches during the early stages of indoor fires. A typical primary search involves quickly and thoroughly looking for victims under hazardous conditions and monitoring flammable materials. However, situational awareness in complex indoor environments and rapid stair climbing across different staircases remain the main challenges for robot-assisted primary searches. In this project, we designed a two-stage end-to-end deep reinforcement learning (RL) approach to optimize both navigation and locomotion. In the first stage, the […]

Ver mais

The Homotopy paradigm, a general principle for solving challenging problems, appears across diverse domains such as robust optimization, global optimization, polynomial root-finding, and sampling. Practical solvers for these problems typically follow a predictor-corrector (PC) structure, but rely on hand-crafted heuristics for step sizes and iteration termination, which are often suboptimal and task-specific. To address this, we unify these problems under a single framework, which enables the design of a general neural solver. Building on this unified view, we […]

Ver mais

How infrastructure decisions shaped the AI we’re building Photo by Google DeepMind on Unsplash We have exactly one example of general intelligence: the human brain. We are spending hundreds of billions trying to build another with AI. And we are not copying the one that works. Why? The answer has less to do with science than with which hardware happened to be available. This is not obvious at first glance. Over the last few years, research comparing brains and large […]

Ver mais

Prenatal psychological stress affects 15-25% of pregnancies and increases risks of preterm birth, low birth weight, and adverse neurodevelopmental outcomes. Current screening relies on subjective questionnaires (PSS-10), limiting continuous monitoring. We developed deep learning models for stress detection from electrocardiography (ECG) using the FELICITy 1 cohort (151 pregnant women, 32-38 weeks gestation). A ResNet-34 encoder was pretrained via SimCLR contrastive learning on 40,692 ECG segments per subject. Multi-layer feature extraction enabled binary classification and continuous PSS prediction across […]

Ver mais

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key approach for enhancing LLM reasoning. However, standard frameworks like Group Relative Policy Optimization (GRPO) typically employ a uniform rollout budget, leading to resource inefficiency. Moreover, existing adaptive methods often rely on instance-level metrics, such as task pass rates, failing to capture the model’s dynamic learning state. To address these limitations, we propose CoBA-RL, a reinforcement learning algorithm designed to adaptively allocate rollout budgets based on the model’s […]

Ver mais

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key approach for enhancing LLM reasoning.However, standard frameworks like Group Relative Policy Optimization (GRPO) typically employ a uniform rollout budget, leading to resource inefficiency. Moreover, existing adaptive methods often rely on instance-level metrics, such as task pass rates, failing to capture the model’s dynamic learning state. To address these limitations, we propose CoBA-RL, a reinforcement learning algorithm designed to adaptively allocate rollout budgets based on the model’s evolving […]

Ver mais

Most developer machines are not clean. They just look clean. At some point, every dev laptop turns into a dumping ground. You install tools to follow a blog post. You try a framework for a weekend. You switch jobs and inherit a new stack. You uninstall things, but only halfway. Binaries stick around. Config files stay buried in your home directory. Caches grow quietly in the background. Nothing is fully broken, but nothing feels right either. Your terminal […]

Ver mais