arXiv:2606.04053v1 Announce Type: new Abstract: The Boolean Task Algebra (BTA) provides a principled framework for zero-shot task composition in reinforcement learning by equipping goal-reaching tasks with Boolean operations. We revisit its structural assumptions and formalize a collapse in the space…
arXiv:2602.19799v2 Announce Type: replace-cross Abstract: Despite recent algorithmic advances, we still lack principled ways to leverage the well-documented rescaling symmetries in ReLU neural network parameters. While two properly rescaled weights implement the same function, the training dynamics can be dramatically…
arXiv:2606.04058v1 Announce Type: new Abstract: Orthonormalized update rules have rapidly become a leading choice of optimizer for training large language models, with recent open-source state-of-the-art models adopting Muon. To keep these updates tractable, Muon performs the orthonormalization with the Newton–Schulz…
arXiv:2606.04511v1 Announce Type: cross Abstract: Sparse attention reduces compute and memory bandwidth for long-context LLM inference. However, two key challenges remain: (1) KV cache capacity still grows with sequence length, and offloading to CPU memory introduces a PCIe transfer bottleneck;…
arXiv:2606.04063v1 Announce Type: new Abstract: Deploying large language models (LLMs) is challenging due to their significant memory and computational requirements. While some methods address this by developing small or tiny language models from scratch, these approaches demand extensive GPU training.…
arXiv:2606.04750v1 Announce Type: cross Abstract: Instilling virtuous behavior in artificial intelligence has seen increasing interest. One of the techniques proposed is known as affinity-based reinforcement learning, which uses policy regularization on the objective function to incentivize virtuous actions without being…
Using technology invented at MIT, Cartesian’s system for locating objects could also find uses in manufacturing, logistics, and robotics.
arXiv:2606.04845v1 Announce Type: cross Abstract: Sequential decision-making problems are often modelled as a Markov decision process (MDP). We focus on the stochastic shortest path (SSP) problem, which is an infinite-horizon undiscounted MDP with absorbing terminal states. We develop a Bayesian…
arXiv:2408.01382v3 Announce Type: replace Abstract: Originating in game theory, Shapley values are widely used for explaining a machine learning model’s prediction by quantifying the contribution of each feature’s value to the prediction. This requires a scalar prediction as in binary…
arXiv:2605.29076v2 Announce Type: replace-cross Abstract: LLMs have advanced text classification, yet existing paradigms face a trade-off: supervised (label only) fine-tuning is scalable but offers limited reasoning on complex text and lacks broader model transparency, while discrete prompt optimization offers human-readable…
