February 2026

Recent advances in deep reinforcement learning (RL) have achieved strong results on high-dimensional control tasks, but applying RL to reachability problems raises a fundamental mismatch: reachability seeks to maximize the set of states from which a system remains safe indefinitely, while RL optimizes expected returns over a user-specified distribution. This mismatch can result in policies that perform poorly on low-probability states that are still within the safe set. A natural alternative is to frame the problem as a […]

Ver mais

I’m a graduate research assistant working on autonomous vehicle research using TD3 in MetaDrive. I was given an existing training script by my supervisor. When the script trains, it produces a saved .zipmodel file (Stable-Baselines3 format). My supervisor has a trained model .zip, and I trained my own model using what appears to be the exact same script : same reward function, wrapper, hyperparameters, architecture, and total timesteps. Now here’s the issue: when I load the supervisor’s .zip […]

Ver mais

Object detection has compelling applications over a range of domains, including human-computer interfaces, security and video surveillance, navigation and road traffic monitoring, transportation systems, industrial automation healthcare, the world of Augmented Reality (AR) and Virtual Reality (VR), environment monitoring and activity identification. Applications of real time object detection in all these areas provide dynamic analysis of the visual information that helps in immediate decision making. Furthermore, advanced deep learning algorithms leverage the progress in the field of object […]

Ver mais

Let me start off by saying “I just started studying RL and I don’t know if what I’m going to describe is a thing or if there’s an analogue to it in the DL world”. Now, onto the idea: Humans have an ability to know right from wrong and have a general sense of what’s good for them and what’s bad. Even babies seem to behave in a way that indicates this knowledge. eg. babies preferring helpers over […]

Ver mais

This paper presents the first demonstration of a viable, ultra-fast, radiation-hard machine learning (ML) application on FPGAs, which could be used in future high-energy physics experiments. We present a three-fold contribution, with the PicoCal calorimeter, planned for the LHCb Upgrade II experiment, used as a test case. First, we develop a lightweight autoencoder to compress a 32-sample timing readout, representative of that of the PicoCal, into a two-dimensional latent space. Second, we introduce a systematic, hardware-aware quantization strategy […]

Ver mais

Recent advances in urban region representation learning have enabled a wide range of applications in urban analytics, yet existing methods remain limited in their capabilities to generalize across cities and analytic tasks. We aim to generalize urban representation learning beyond city- and task-specific settings, towards a foundation-style model for urban analytics. To this end, we propose UrbanVerse, a model for cross-city urban representation learning and cross-task urban analytics. For cross-city generalization, UrbanVerse focuses on features local to the […]

Ver mais