February 2026

arXiv:2602.10314v1 Announce Type: new Abstract: Masked Diffusion Models (MDMs) have emerged as a promising approach for generative modeling in discrete spaces. By generating sequences in any order and allowing for parallel decoding, they enable fast inference and strong performance on non-causal tasks. However, this flexibility comes with a training complexity trade-off: MDMs train on an exponentially large set of masking patterns, which is not only computationally expensive, but also creates a train–test mismatch between the random masks used […]

Ver mais

arXiv:2602.10312v1 Announce Type: new Abstract: R2RAG-Flood is a reasoning-reinforced, training-free retrieval-augmented generation framework for post-storm property damage nowcasting. Building on an existing supervised tabular predictor, the framework constructs a reasoning-centric knowledge base composed of labeled tabular records, where each sample includes structured predictors, a compact natural language text-mode summary, and a model-generated reasoning trajectory. During inference, R2RAG-Flood issues context-augmented prompts that retrieve and condition on relevant reasoning trajectories from nearby geospatial neighbors and canonical class prototypes, enabling the […]

Ver mais

arXiv:2602.10305v1 Announce Type: new Abstract: Reward shaping has been applied widely to accelerate Reinforcement Learning (RL) agents’ training. However, a principled way of designing effective reward shaping functions, especially for complex continuous control problems, remains largely under-explained. In this work, we propose to automatically learn a reward shaping function for continuous control problems from offline datasets, potentially contaminated by unobserved confounding variables. Specifically, our method builds upon the recently proposed causal Bellman equation to learn a tight upper […]

Ver mais

arXiv:2602.10304v1 Announce Type: new Abstract: While cervical arthroplasty using Total Disc Replacement (TDR) implants is an established treatment for persistent neck and arm pain, revision rates limit it from reaching its full potential. To address the underlying complications, we developed finite element simulation-driven design optimizations for a TDR’s bone-implant interface and motion-preservation features. These automated processes explored high-dimensional design spaces iteratively through analysis of design variations interplay with spinal structures. The optimizations were metamodel-based using artificial neural networks […]

Ver mais

arXiv:2602.10301v1 Announce Type: new Abstract: Among the different concepts for wave energy conversion, oscillating surge wave energy converters have been shown to have a high capture width ratio. The primary wave capture structure consists of a flap hinged at the seabed or to a floating platform. Different flap configurations, including single and dual-flap, have been investigated. The separation distance between the oscillating surge wave energy converters can have an impact on their response when deployed in arrays. We […]

Ver mais

arXiv:2602.10300v1 Announce Type: new Abstract: Researchers build scaling laws to forecast the training performance of expensive large-scale runs with larger model size N and data size D. These laws assume that other training hyperparameters are optimally chosen, which can require significant effort and, in some cases, be impossible due to external hardware constraints. To improve predictability across a broader set of hyperparameters and enable simpler tuning at scale, we propose learning a textit{Configuration-to-Performance Scaling Law} (CPL): a mapping […]

Ver mais

arXiv:2602.10299v1 Announce Type: new Abstract: Recent work on network attacks have demonstrated that ML-based network intrusion detection systems (NIDS) can be evaded with adversarial perturbations. However, these attacks rely on complex optimizations that have large computational overheads, making them impractical in many real-world settings. In this paper, we introduce a lightweight adversarial agent that implements strategies (policies) trained via reinforcement learning (RL) that learn to evade ML-based NIDS without requiring online optimization. This attack proceeds by (1) offline […]

Ver mais

arXiv:2602.10298v1 Announce Type: new Abstract: This paper investigates whether LMs recruit shared computational mechanisms for general Theory of Mind (ToM) and language-specific pragmatic reasoning in order to contribute to the general question of whether LMs may be said to have emergent “social world models”, i.e., representations of mental states that are repurposed across tasks (the functional integration hypothesis). Using behavioral evaluations and causal-mechanistic experiments via functional localization methods inspired by cognitive neuroscience, we analyze LMs’ performance across seven […]

Ver mais

arXiv:2602.10296v1 Announce Type: new Abstract: We study the problem of finding an $epsilon$-fixed point of a contraction map $f:[0,1]^kmapsto[0,1]^k$ under both the $ell_infty$-norm and the $ell_1$-norm. For both norms, we give an algorithm with running time $O(log^{lceil k/2rceil}(1/epsilon))$, for any constant $k$. These improve upon the previous best $O(log^k(1/epsilon))$-time algorithm for the $ell_{infty}$-norm by Shellman and Sikorski [SS03], and the previous best $O(log^k (1/epsilon ))$-time algorithm for the $ell_{1}$-norm by Fearnley, Gordon, Mehta and Savani [FGMS20].

Ver mais

arXiv:2602.10295v1 Announce Type: new Abstract: ECHO (Evaluation of Chat, Human behavior, and Outcomes) is an open research platform designed to support reproducible, mixed-method studies of human interaction with both conversational AI systems and Web search engines. It enables researchers from varying disciplines to orchestrate end-to-end experimental workflows that integrate consent and background surveys, chat-based and search-based information-seeking sessions, writing or judgment tasks, and pre- and post-task evaluations within a unified, low-coding-load framework. ECHO logs fine-grained interaction traces and […]

Ver mais