3 Questions: Fortifying our planetary defenses
MIT astronomers are developing a new way to detect, monitor, and mitigate the threats posed by smaller asteroids to our critical space infrastructure.
Archives AI News
Losing dimensions: Geometric memorization in generative diffusion
arXiv:2410.08727v2 Announce Type: replace-cross Abstract: Diffusion models power leading generative AI, but when and how they memorize training data, especially on low-dimensional manifolds, remains unclear. We find memorization emerges gradually, not abruptly: as data become scarce, diffusion models experience a…
Revisiting Value Iteration: Unified Analysis of Discounted and Average-Reward Cases
arXiv:2510.23914v2 Announce Type: replace Abstract: While Value Iteration (VI) is one of the most fundamental algorithms in Reinforcement Learning, its theoretical convergence guarantees still exhibit a persistent mismatch with empirical behavior. In the discounted-reward case, classical theory guarantees geometric convergence…
Latent Poincar’e Shaping for Agentic Reinforcement Learning
arXiv:2602.09375v3 Announce Type: replace Abstract: We propose LaPha, a method for training AlphaZero-like LLM agents in a Poincar’e latent space. Under LaPha, the search process can be visualized as a tree rooted at the prompt and growing outward from the…
Kernel Tests of Equivalence
arXiv:2603.10886v1 Announce Type: cross Abstract: We propose novel kernel-based tests for assessing the equivalence between distributions. Traditional goodness-of-fit testing is inappropriate for concluding the absence of distributional differences, because failure to reject the null hypothesis may simply be a result…
An Algorithm to perform Covariance-Adjusted Support Vector Classification in Non-Euclidean Spaces
arXiv:2504.04371v3 Announce Type: replace Abstract: Traditional Support Vector Machine (SVM) classification is carried out by finding the max-margin classifier for the training data that divides the margin space into two equal sub-spaces. This study demonstrates limitations of performing Support Vector…
RACAS: Controlling Diverse Robots With a Single Agentic System
arXiv:2603.05621v2 Announce Type: replace-cross Abstract: Many robotic platforms expose an API through which external software can command their actuators and read their sensors. However, transitioning from these low-level interfaces to high-level autonomous behaviour requires a complicated pipeline, whose components demand…
Resource-constrained Amazons chess decision framework integrating large language models and graph attention
arXiv:2603.10512v1 Announce Type: cross Abstract: Artificial intelligence has advanced significantly through the development of intelligent game-playing systems, providing rigorous testbeds for decision-making, strategic planning, and adaptive learning. However, resource-constrained environments pose critical challenges, as conventional deep learning methods heavily rely…
Cluster-Aware Attention-Based Deep Reinforcement Learning for Pickup and Delivery Problems
arXiv:2603.10053v1 Announce Type: new Abstract: The Pickup and Delivery Problem (PDP) is a fundamental and challenging variant of the Vehicle Routing Problem, characterized by tightly coupled pickup–delivery pairs, precedence constraints, and spatial layouts that often exhibit clustering. Existing deep reinforcement…
Training Language Models via Neural Cellular Automata
arXiv:2603.10055v1 Announce Type: new Abstract: Pre-training is crucial for large language models (LLMs), as it is when most representations and capabilities are acquired. However, natural language pre-training has problems: high-quality text is finite, it contains human biases, and it entangles…