Knowledge catalogue
arXiv:2605.21834v1 Announce Type: new Abstract: Aligned models can misbehave in several ways: they are often sycophantic, fall victim to jailbreaks, or fail to include appropriate safety warnings. Con
arXiv:2602.12506v3 Announce Type: replace Abstract: Reinforcement learning (RL) finetuning has become a key technique for enhancing large language models (LLMs) on reasoning-intensive tasks, motivatin
arXiv:2503.06115v2 Announce Type: replace-cross Abstract: Reinforced random walks (RRWs), including vertex-reinforced random walks (VRRWs) and edge-reinforced random walks (ERRWs), model random walks
arXiv:2605.21763v1 Announce Type: new Abstract: We study risk-sensitive reinforcement learning in finite discounted MDPs, where a generative model of the MDP is assumed to be available. We consider a
arXiv:2605.22297v1 Announce Type: new Abstract: Learning rate configuration is a fundamental aspect of modern deep learning. The prevailing practice of applying a uniform learning rate across all laye
arXiv:2605.22156v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a promising paradigm for scaling reasoning capabilities of Large Language Models (LLMs)
arXiv:2605.21851v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become the standard recipe for improving LLM reasoning, but the dominant algorithm GRPO assigns a sin
arXiv:2605.21938v1 Announce Type: new Abstract: We study black-box auditing for machine learning algorithms that claim R 'enyi differential privacy (RDP) guarantees. We introduce an auditing framework
arXiv:2605.22736v1 Announce Type: cross Abstract: Optimization over the intersection of two manifolds arises in a broad range of applications, but is hindered by the coupled geometry of the feasible r
arXiv:2605.22350v1 Announce Type: new Abstract: Ensembles of neural networks typically outperform individual networks but incur large computational costs, whereas weight aggregation produces less cost
arXiv:2605.21550v1 Announce Type: new Abstract: Electricity load peak forecasting (ELPF), simultaneously predicting peak timing and intensity, is a prerequisite for effective grid scheduling and risk
arXiv:2605.21752v1 Announce Type: new Abstract: Recommender systems trained on user interaction data are susceptible to behavioral intensity imbalance--a systematic distortion arising from heterogeneo
arXiv:2605.21859v1 Announce Type: cross Abstract: Phylogenetic trees are hybrid objects: branch lengths vary continuously, while topologies change discretely through edge contractions and expansions.
arXiv:2605.22338v1 Announce Type: new Abstract: Reconstructing continuous physical fields from sparse measurements is a central inverse problem, but data-driven generative models can produce states th
arXiv:2509.24517v2 Announce Type: replace Abstract: Development of modern deep learning methods has been driven primarily by the push for improving model efficacy (accuracy metrics). This sole focus o
arXiv:2605.22746v1 Announce Type: new Abstract: Real-world sensor-based learning systems require uncertainty estimation that is both reliable and computationally efficient. Evidential Deep Learning (E
arXiv:2605.21765v1 Announce Type: new Abstract: The practical adoption of sampling-based inference (SAI) in Bayesian neural networks (BNNs) remains limited, partly due to persistent misconceptions abo
arXiv:2605.22731v1 Announce Type: new Abstract: Large language model post-training methods such as supervised fine-tuning (SFT), reinforcement learning (RL), and distillation are often analyzed throug
arXiv:2605.22691v1 Announce Type: new Abstract: We show that posterior collapse in eta-VAEs implements automatic spectral pruning. A latent mode collapses if its contribution to reconstruction is belo
arXiv:2605.21515v1 Announce Type: new Abstract: LLM prompting is widely used for naturally stated tasks, yet it is unreliable it may succeed on a few test cases but fail at deployment time. We study p
arXiv:2602.22270v2 Announce Type: replace Abstract: Spatio-temporal epidemic forecasting is critical for public health management, yet existing methods often struggle with insensitivity to weak epidem
arXiv:2502.21194v3 Announce Type: replace-cross Abstract: We study estimation of a class prior for unlabeled target samples which possibly differs from that of source population. Moreover, it is assum
arXiv:2605.21522v1 Announce Type: cross Abstract: Protein-protein interactions (PPIs) govern nearly all cellular processes, yet computational methods for identifying binding partners typically produce
arXiv:2605.22055v1 Announce Type: new Abstract: Time Series Classification (TSC) is a long-standing research problem that has gained increasing attention in recent years with the rapid growth of large
arXiv:2605.21543v1 Announce Type: new Abstract: Benchmark data contamination has become a central challenge in LLM evaluation: when evaluation examples appear in the training data of one or more audit
arXiv:2605.21780v1 Announce Type: new Abstract: Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations, including poisoning attacks via randomized training and
arXiv:2602.00688v2 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) on sensitive datasets raises privacy concerns, as training data extraction (TDE) attacks can expose highly
arXiv:2605.22738v1 Announce Type: new Abstract: Shapley and Banzhaf interactions capture the complex dynamics inherent in modern machine learning applications. However, current estimators for these hi
arXiv:2605.22097v1 Announce Type: cross Abstract: Photonic quantum computing is a promising platform for scalable quantum machine learning, but designing effective hybrid architectures remains challen
arXiv:2605.21745v1 Announce Type: new Abstract: Non-contrast computed tomography calcium scoring (CTCS) is widely recognized as an effective tool for cardiovascular risk stratification. This study aim
arXiv:2605.22041v1 Announce Type: cross Abstract: While RAG systems are increasingly deployed in dynamic web search, temporal volatility amplifies their vulnerability to adversarial attacks. Existing
arXiv:2603.03454v2 Announce Type: replace Abstract: Offline Reinforcement Learning (RL) is an emerging field of RL in which policies are learned solely from demonstrations. Within offline RL, some env
arXiv:2605.22719v1 Announce Type: new Abstract: We report a small, reproducible audit of which sparse-autoencoder (SAE) features of GPT-2 small fire differently on failed versus successful trials of t
arXiv:2605.21975v1 Announce Type: new Abstract: Financial markets are characterized by extreme non-stationarity, low signal-to-noise ratios, and strong dependence on external information such as news,
arXiv:2605.22561v1 Announce Type: new Abstract: Bayesian optimization (BO) is a widely used iterative black-box optimization method that utilizes Gaussian process (GP) surrogate models. In practice, B
arXiv:2605.22195v1 Announce Type: new Abstract: Graph of Thoughts (GoT), a generalized form of recent prompting paradigms for large language models (LLMs), has been shown to be useful for elaborate pr
arXiv:2605.22463v1 Announce Type: cross Abstract: Scalable trapped-ion quantum computing is commonly realized with modular chips that feature distinct zones with specific functionalities, such as stor
arXiv:2605.22532v1 Announce Type: new Abstract: Linear properties are ubiquitous in the representations of language models; however, testing them experimentally remains a challenging task. This work f
arXiv:2507.20268v3 Announce Type: replace Abstract: Wireless indoor localization using predictive models with received signal strength information (RSSI) requires proper calibration for reliable posit
arXiv:2605.22814v1 Announce Type: new Abstract: Exploration is a prerequisite for learning useful behaviors in sparse-reward, long-horizon tasks, particularly within 3D environments. Curiosity-driven
arXiv:2605.21692v1 Announce Type: new Abstract: Characterizing precisely the asymptotic generalization error of neural networks using parameters that can be estimated efficiently is a crucial problem
arXiv:2605.22488v1 Announce Type: new Abstract: Structured prompts require integrating components according to task-relevant relations. How a network implements this integration is often hard to judge
arXiv:2604.02889v2 Announce Type: replace-cross Abstract: Data assimilation is the process of estimating the state of a dynamical system over time by combining model predictions with measurements. Thi
arXiv:2602.10894v2 Announce Type: replace Abstract: Two-player games such as board games have long been used as traditional benchmarks for reinforcement learning. This work revisits a policy optimizat
arXiv:2602.07340v2 Announce Type: replace Abstract: Safety alignment of large language models remains brittle under domain shift and noisy preference supervision. Most existing robust alignment method
arXiv:2602.01279v2 Announce Type: replace Abstract: Bayesian Last Layers (BLLs) provide a convenient and computationally efficient way to estimate uncertainty in neural networks. However, they underes
arXiv:2605.22334v1 Announce Type: new Abstract: Correlation matrices are fundamental summaries of functional brain networks, yet standard analyses often treat entries independently, ignoring the curve
arXiv:2605.22083v1 Announce Type: cross Abstract: While flow-matching text-to-speech (TTS) achieves strong zero-shot speaker similarity and naturalness, it remains susceptible to content fidelity issu
arXiv:2603.21610v2 Announce Type: replace Abstract: Compliance monitoring in rule-governed domains (tax administration, clinical protocol adherence, environmental regulation) faces three structural ob
arXiv:2605.21803v1 Announce Type: new Abstract: Scaling laws have made language-model performance predictable from model size, data, and compute, but they typically treat the optimizer as a fixed trai
arXiv:2605.21557v1 Announce Type: cross Abstract: Conventional wisdom holds that large-batch training is fundamentally incompatible with Reinforcement Learning (RL) - beyond a modest threshold, increa
arXiv:2605.21948v1 Announce Type: new Abstract: LLM-based ranking systems are vulnerable to Generative Engine Optimization (GEO) attacks, where adversaries inject semantic signals into product descrip
arXiv:2605.22776v1 Announce Type: new Abstract: Survival analysis aims to estimate a time-to-event distribution from data with censored observations. Many existing methods either impose structural ass
arXiv:2505.22749v2 Announce Type: replace-cross Abstract: Attractor dynamics are a hallmark of many complex systems, including the brain. Understanding how such self-organizing dynamics emerge from fi
arXiv:2605.22112v1 Announce Type: cross Abstract: We present a framework for detecting transient gamma-ray phenomena in a controlled environment by combining end-to-end simulations of the Fermi-LAT sk
arXiv:2605.22331v1 Announce Type: new Abstract: Despite strong predictive results in the clinical machine learning literature, the translation of these models into bedside use remains limited by syste
arXiv:2605.22743v1 Announce Type: new Abstract: Parameter-efficient fine-tuning enables fast personalization of text-to-image diffusion models, but composing multiple custom concepts remains challengi
arXiv:2605.22142v1 Announce Type: new Abstract: Reinforcement learning under partial observability requires deciding what information to retain, yet most memory-based approaches do not explicitly mode
arXiv:2605.22205v1 Announce Type: cross Abstract: Large language models increasingly require specialization across diverse domains, yet existing approaches struggle to balance multi-domain capacities
arXiv:2601.11079v2 Announce Type: replace Abstract: This paper proposes the soft Bayesian context tree model (Soft-BCT), which is a novel BCT model for real-valued time series. The Soft-BCT considers