This paper develops a new algorithm for policy optimization in online episodic tabular Markov decision processes with unknown transition kernels, providing data-dependent regret bounds and best-of-bot…

This paper proposes a method to describe dynamical systems using molecular and reaction concepts, making three key decisions: number of places, species determination, and transitions.

This paper establishes the identifiability of latent regimes and regime-dependent causal structures in complex non-stationary time series modeled by Markov Switching Models, even with instantaneous ef…

The paper proposes a Doeblin-anchored contrastive chart to learn valid Markov transition kernels by combining the target transition with a restart law, ensuring the learned object is mathematically so…

This paper analyzes the Bayesian fixed-budget best-arm identification problem with abstention, showing that it induces a phase transition from polynomial to exponential decay of error probability.

The paper analyzes the phase transitions of the noisy transformer model on the unit sphere, proving a sharp global-minimizer dichotomy that depends on the dimension and coupling strength.

JenBridge is a novel, adaptive framework that generates high-fidelity, long-form video soundtracks, significantly improving narrative coherence and naturalness across scene transitions.

This paper investigates the transparency of DiffusionGemma, a model with a larger fraction of computation in a continuous latent space, and shows that it can be made more transparent by mapping inform…

The paper introduces STEP, a self-supervised method that learns interpretable, structured embeddings for progressive time series, allowing the state progression and active mode to be read out using po…

The paper proposes an Entropy Dynamics framework to analyze the stability and failure modes of centralized orchestration in Multi-Agent Systems, identifying a 'Reasoning Trap' where complex reasoning…

Stochastic Lifting is a novel technique that enhances the modeling of stochastic physical systems by introducing independent random labels to state transitions, allowing a single network to generate d…

This paper measures the lower bound for the shortest program generating a sequence, proving a conservation law and providing a deterministic engine to recover generating programs for certain sequences…

This paper studies the probability of a trajectory lying in a designated failure region during training of a model with noisy gradient descent, and derives bounds for this probability.

This paper investigates the necessity of interaction for order-optimal 1-bit mean estimation in nonparametric finite-moment classes.

The paper introduces Singularity-aware Adam (S-Adam), a novel optimizer that stabilizes deep learning training in non-smooth loss landscapes by dynamically damping updates based on local geometric ins…

This paper provides non-asytotic sample complexity guarantees for the Navigate and Stop algorithm in online tabular Reinforcement Learning, identifying additional attributes that affect the overall sa…

The paper challenges the assumption that LLM safety is a binary threshold, proposing that safety failures occur in an 'instability region' and introducing Furina, a transferable attack that exploits t…

The paper introduces Strong Stochastic Flow Maps (SSFMs), a novel framework that directly learns the strong solution map of additive-noise Stochastic Differential Equations (SDEs), enabling few-step s…

The paper proposes methods for detecting training instability in large language models using internal monitors based on the functional role of critical modules and earliest computational sites.