Stay updated with the latest research and technology news
arXiv:2602.02685v1 Announce Type: new Abstract: Decentralized Diffusion Models (DDMs) route denoising through experts trained independently on disjoint data clusters, which can strongly disagree in their...
arXiv:2602.02686v1 Announce Type: new Abstract: Large language models (LLMs) are known to exhibit brittle behavior under adversarial prompts and jailbreak attacks, even after extensive alignment...
arXiv:2602.02689v1 Announce Type: new Abstract: We propose Eidolon, a practical post-quantum signature scheme based on the NP-complete k-colorability problem. Our construction generalizes the Goldreich-Micali-Wigderson zero-knowledge...
arXiv:2602.02690v1 Announce Type: new Abstract: Repairing system crashes discovered by kernel fuzzers like Syzkaller is a critical yet underexplored challenge in software engineering. While recent...
arXiv:2602.02696v1 Announce Type: new Abstract: The expanding scale of neural networks poses a major challenge for distributed machine learning, particularly under limited communication resources. While...
arXiv:2602.02699v1 Announce Type: new Abstract: Diffusion models have shown remarkable success across a wide range of generative tasks. However, they often suffer from spatially inconsistent...
arXiv:2602.02704v1 Announce Type: new Abstract: Reasoning over ultra-long documents requires synthesizing sparse evidence scattered across distant segments under strict memory constraints. While streaming agents enable...
arXiv:2602.02707v1 Announce Type: new Abstract: Quantization reduces the numerical precision of Transformer computations and is widely used to accelerate inference, yet its effect on expressivity...
arXiv:2602.02708v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is the standard approach for binary classification tasks such as toxicity detection, factuality verification, and causal inference....
arXiv:2602.02709v1 Announce Type: new Abstract: Recent multi-LLM agent systems perform well in prompt optimization and automated problem-solving, but many either keep the solver frozen after...
arXiv:2602.02710v1 Announce Type: new Abstract: Reinforcement learning is the method of choice to train models in sampling-based setups with binary outcome feedback, such as navigation,...
arXiv:2602.02711v1 Announce Type: new Abstract: Large language models (LLM) achieve strong performance in long-horizon decision-making tasks through multi-step interaction and reasoning at test time. While...
arXiv:2602.02712v1 Announce Type: new Abstract: A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, identify...
arXiv:2602.02716v1 Announce Type: new Abstract: We introduce neural probabilistic amplitude shaping, a joint-distribution learning framework for coherent fiber systems. The proposed scheme provides a 0.5...
arXiv:2602.02717v1 Announce Type: new Abstract: Many Intelligent Transportation Systems (ITS) applications require strong privacy guarantees for both users and their data. Homomorphic encryption (HE) enables...
arXiv:2602.02718v1 Announce Type: new Abstract: When creating public data products out of confidential datasets, inferential/posterior-based privacy definitions, such as Pufferfish, provide compelling privacy semantics for...
arXiv:2602.02721v1 Announce Type: new Abstract: Inverse scattering in optical coherence tomography (OCT) seeks to recover both structural images and intrinsic tissue optical properties, including refractive...
arXiv:2602.02722v1 Announce Type: new Abstract: We propose a hierarchical entity-centric framework for offline Goal-Conditioned Reinforcement Learning (GCRL) that combines subgoal decomposition with factored structure to...
arXiv:2602.02724v1 Announce Type: new Abstract: The development of black-box optimization algorithms depends on the availability of benchmark suites that are both diverse and representative of...
arXiv:2602.02725v1 Announce Type: new Abstract: Pharyngeal health plays a vital role in essential human functions such as breathing, swallowing, and vocalization. Early detection of swallowing...
arXiv:2602.02726v1 Announce Type: new Abstract: Deep Learning models encode rich semantic information in their hidden representations. However, it remains challenging to understand which parts of...
arXiv:2602.02727v1 Announce Type: new Abstract: Discrete diffusion models generate sequences by iteratively denoising samples corrupted by categorical noise, offering an appealing alternative to autoregressive decoding...
arXiv:2602.02729v1 Announce Type: new Abstract: This paper presents $\textbf{CAPS}$ (Clock-weighted Aggregation with Prefix-products and Softmax), a structured attention mechanism for time series forecasting that decouples...
arXiv:2602.02730v1 Announce Type: new Abstract: Autonomous racing has advanced rapidly, particularly on scaled platforms, and software stacks must evolve accordingly. In this work, AROLA is...