Stay updated with the latest research and technology news
arXiv:2602.00399v1 Announce Type: cross Abstract: In the last decade, Reinforcement Learning (RL) has achieved remarkable success in the control and decision-making of complex dynamical systems....
arXiv:2602.00413v1 Announce Type: cross Abstract: Diffusion models and flow matching have demonstrated remarkable success in text-to-image generation. While many existing alignment methods primarily focus on...
arXiv:2602.00417v1 Announce Type: cross Abstract: We present the first algorithms for generalized linear contextual bandits under shuffle differential privacy and joint differential privacy. While prior...
arXiv:2602.00427v1 Announce Type: cross Abstract: Inferring causal direction from purely observational bivariate data is fragile: many methods commit to a direction even in ambiguous or...
arXiv:2602.00437v1 Announce Type: cross Abstract: Empirical risk minimization (ERM) can be computationally expensive, with standard solvers scaling poorly even in the convex setting. We propose...
arXiv:2602.00464v1 Announce Type: cross Abstract: Handwriting literacy is an important skill for learning and communication in school-age children. In the digital age, handwriting has been...
arXiv:2602.00473v1 Announce Type: cross Abstract: Quantum phase transitions in many-body systems are fundamentally characterized by complex correlation structures, which pose computational challenges for conventional methods...
arXiv:2602.00474v1 Announce Type: cross Abstract: Poisson equations underpin average-reward reinforcement learning, but beyond ergodicity they can be ill-posed, meaning that solutions are non-unique and standard...
arXiv:2602.00483v1 Announce Type: cross Abstract: Video coding standards are essential to enable the interoperability and widespread adoption of efficient video compression technologies. In pursuit of...
arXiv:2602.00498v1 Announce Type: cross Abstract: Predicting favorable protein-peptide binding events remains a central challenge in biophysics, with continued uncertainty surrounding how nonlocal effects shape the...
arXiv:2602.00555v1 Announce Type: cross Abstract: We establish tight connections between entanglement entropy and the approximation error in Trotter-Suzuki product formulas for Hamiltonian simulation. Product formulas...
arXiv:2602.00586v1 Announce Type: cross Abstract: Network topology excels at structural predictions but fails to capture functional semantics encoded in biomedical literature. We present a retrieval-augmented...
arXiv:2602.00590v1 Announce Type: cross Abstract: Understanding structure-property relationships in complex materials requires integrating complementary measurements across multiple length scales. Here we propose an interpretable "multimodal"...
arXiv:2602.00629v1 Announce Type: cross Abstract: Most existing offline RL methods presume the availability of action labels within the dataset, but in many practical scenarios, actions...
arXiv:2602.00634v1 Announce Type: cross Abstract: We develop a deterministic zeroth-order mirror descent framework by replacing gradients with a general vector field, yielding a vector-field-driven mirror...
arXiv:2602.00641v1 Announce Type: cross Abstract: In this paper, we propose a general methodology for sampling from un-normalized densities defined on Riemannian manifolds, with a particular...
arXiv:2602.00648v1 Announce Type: cross Abstract: High-fidelity general audio compression at ultra-low bitrates is crucial for applications ranging from low-bandwidth communication to generative audio-language modeling. Traditional...
arXiv:2602.00716v1 Announce Type: cross Abstract: Classifier-free guidance (CFG) is the de facto standard for conditional sampling in diffusion models, yet it often leads to a...
arXiv:2602.00756v1 Announce Type: cross Abstract: Incorporating Machine Learning (ML) into material property prediction has become a crucial step in accelerating materials discovery. A key challenge...
arXiv:2602.00782v1 Announce Type: cross Abstract: Protein language models (PLMs) have enabled advances in structure prediction and de novo protein design, yet they frequently collapse into...
arXiv:2602.00783v1 Announce Type: cross Abstract: Barren plateaus are typically characterized by vanishing gradients, yet the feasibility of curvature-based optimization fundamentally relies on the statistical resolvability...
arXiv:2602.00790v1 Announce Type: cross Abstract: We detail a novel Fourier-based approach (IterativeFT) for identifying deterministic network structure in the presence of both edge pruning and...
arXiv:2602.00797v1 Announce Type: cross Abstract: Flow-based methods have achieved significant success in various generative modeling tasks, capturing nuanced details within complex data distributions. However, few...
arXiv:2602.00816v1 Announce Type: cross Abstract: Accurate Hessian spectra of foundation models have remained out of reach, leading most prior work to rely on small models...