Knowledge catalogue
arXiv:2605.23243v1 Announce Type: cross Abstract: We evaluate whether frontier LLMs are ready for cybersecurity through a dual-mode benchmark: white-box function-level vulnerability detection (VulnLLM
arXiv:2509.06896v2 Announce Type: replace Abstract: Targeted data poisoning attacks manipulate model predictions on specific test samples by injecting malicious data into training. Yet existing evalua
arXiv:2605.23454v1 Announce Type: new Abstract: Rubric-based rewards offer a promising way to extend reinforcement learning (RL) for large language models beyond tasks with automatically verifiable an
arXiv:2605.23562v1 Announce Type: cross Abstract: Sparse rewards are a major bottleneck in multi-agent reinforcement learning (MARL), where simultaneous learning induces non-stationarity and makes rew
arXiv:2605.23416v1 Announce Type: new Abstract: Acoustic vowel dynamics have some speaker-identifying characteristics, which have been ascribed to individual properties of articulatory strategies: for
arXiv:2605.23147v1 Announce Type: cross Abstract: Role prompts of the form As X, do Y admit a clean linear decomposition at one specific site in the residual stream: the prompt-to-answer transition --
arXiv:2605.23497v1 Announce Type: new Abstract: Large language models are increasingly used for legal research, yet their fixed training cutoffs and reliance on static parametric knowledge are at odds
arXiv:2605.23234v1 Announce Type: new Abstract: Assessing the spatial fairness of predictive models involves establishing whether they are statistically penalizing (favoring) individuals associated wi
arXiv:2605.23591v1 Announce Type: cross Abstract: We introduce a model for neural scaling laws under sparse activations. In the model, test loss is often dominated by rare coordinates that are never o
arXiv:2605.22133v2 Announce Type: replace-cross Abstract: Recent advances in generative modeling show that pretrained representations can improve generation as conditioning features or alignment targe
arXiv:2605.23473v1 Announce Type: cross Abstract: Bayesian optimization is widely employed for optimizing complex black-box functions but struggles with the curse of dimensionality. Random embedding,
arXiv:2601.22324v2 Announce Type: replace Abstract: Modern clinical practice relies on evidence-based guidelines implemented as compact scoring systems composed of a small number of interpretable deci
arXiv:2605.23165v1 Announce Type: cross Abstract: Autonomous robotic exploration of unknown and hazardous environments, a long-standing challenge, can be significantly improved by leveraging the advan
arXiv:2605.23204v1 Announce Type: new Abstract: Scientific research is being reshaped by AI systems that move beyond isolated assistance toward longer-horizon workflows spanning literature grounding,
arXiv:2510.12787v4 Announce Type: replace Abstract: We present Ax-Prover, a multi-agent system for automated theorem proving in Lean that can solve problems across diverse scientific domains and opera
arXiv:2605.23500v1 Announce Type: new Abstract: Segmentation is a fundamental task in computer vision, underpinning pixel-level scene understanding and serving as a cornerstone for applications rangin
arXiv:2602.20102v2 Announce Type: replace-cross Abstract: Despite the strong performance of large language models (LLMs) across diverse tasks, their susceptibility to adversarial attacks and unsafe co
arXiv:2512.20901v2 Announce Type: replace Abstract: With the rapid development of Vision-Language Models (VLMs) and the growing demand for their applications, efficient compression of the image inputs
arXiv:2509.19858v2 Announce Type: replace Abstract: As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipu
arXiv:2605.23618v1 Announce Type: new Abstract: We benchmark Google Embeddings (GE2), a Vertex-AI-hosted bi-encoder with 2,048-token context and explicit task-type conditioning, against five open-sour
arXiv:2605.23780v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) need efficient mechanisms to update knowledge without degrading existing capabilities. While intrinsic multimod
arXiv:2510.00526v3 Announce Type: replace Abstract: Supervised fine-tuning (SFT) is the standard approach for post-training large language models (LLMs), yet it often shows limited generalization. We
arXiv:2605.23231v1 Announce Type: new Abstract: This paper considers a practical few-shot anomaly detection (FSAD) setting, termed discriminative FSAD, where a limited number of both normal and anomal
arXiv:2602.11146v2 Announce Type: replace-cross Abstract: Preference optimization for diffusion and flow-matching models relies on reward functions that are both discriminatively robust and computatio
arXiv:2605.22866v1 Announce Type: new Abstract: Compound AI systems route tasks through hierarchies of specialised components. Attribution is dominated by Shapley-based methods (SHAP), which decompose
arXiv:2605.23032v1 Announce Type: cross Abstract: Brain-LLM alignment is well established in English, yet the brain's language network is neuroanatomically universal across languages. Does alignment a
arXiv:2602.13985v2 Announce Type: replace Abstract: Artificial intelligence (AI) has demonstrated strong potential in clinical diagnostics, often achieving accuracy comparable to or exceeding that of
arXiv:2512.15767v2 Announce Type: replace-cross Abstract: Simulating complex unsteady physical phenomena relies on detailed mathematical models, simulated for instance by using the Finite Element Meth
arXiv:2605.22924v1 Announce Type: new Abstract: Serving personalized content on mobile devices has traditionally required pooling sensitive user data on centralized servers, a practice increasingly at
arXiv:2602.18788v3 Announce Type: replace Abstract: We introduce BURMESE-SAN, the first holistic benchmark that systematically evaluates large language models (LLMs) for Burmese across three core NLP
arXiv:2407.03535v3 Announce Type: replace Abstract: Low-light videos often exhibit spatiotemporally incoherent noise, compromising visibility and degrading performance in computer vision applications.
arXiv:2605.23139v1 Announce Type: cross Abstract: Multivariate time series anomaly detection has become increasingly important in real-world applications, where labeled data are often scarce. Many exi
arXiv:2605.23580v1 Announce Type: new Abstract: Reliable multi-modal calibration requires identifying which observations truly constrain the extrinsic parameters and which ones mainly add noise or amb
arXiv:2605.22971v1 Announce Type: new Abstract: Employees often struggle to identify ``who knows what,'' leading to organizational productivity losses. We investigate whether Large Language Models (LL
arXiv:2603.06610v2 Announce Type: replace Abstract: Large language model (LLM) post-training enhances latent skills, unlocks value alignment, improves performance, and enables domain adaptation. Unfor
arXiv:2605.23254v1 Announce Type: new Abstract: Learning from real-world data is frequently hindered by the compound challenge of long-tailed class distributions and noisy annotations. Existing method
arXiv:2512.11551v2 Announce Type: replace Abstract: The growing number of road users has significantly increased the risk of accidents in recent years. Vulnerable Road Users (VRUs) are particularly at
arXiv:2601.21513v2 Announce Type: replace Abstract: In distributed applications, such as energy demand forecasting at the substation level or federated learning, a large number of related tasks must b
arXiv:2605.23216v1 Announce Type: new Abstract: Cause-and-effect reasoning in video is a significant challenge for Vision-Language Models (VLMs), as it requires going beyond surface-level perception t
arXiv:2502.07646v3 Announce Type: replace Abstract: Causal additive models provide a tractable yet expressive framework for causal discovery in the presence of hidden variables. When unobserved backdo
arXiv:2605.23471v1 Announce Type: cross Abstract: Aggressive driving is a major cause of traffic accidents and poses a serious threat to road safety. Although deep learning methods have shown promisin
arXiv:2605.22964v1 Announce Type: new Abstract: As state-of-the-art neural networks are deployed on reasoning and algorithmic tasks, exactness guarantees become increasingly important. However, high a
arXiv:2602.15602v2 Announce Type: replace Abstract: Certified machine unlearning can be achieved via noise injection leading to differential privacy guarantees, where noise is calibrated to worst-case
arXiv:2605.23270v1 Announce Type: cross Abstract: Current end-to-end autonomous driving systems are fundamentally limited by a mismatch between temporal causal reasoning and global trajectory consiste
arXiv:2605.23694v1 Announce Type: new Abstract: Chart descriptions are essential for accessibility, cross-modal retrieval, and assisting readers in extracting insights from complex visualizations. As
arXiv:2605.23344v1 Announce Type: cross Abstract: Large Vision-Language Models have shown strong multimodal reasoning capabilities, yet they remain susceptible to object hallucinations when language p
arXiv:2605.23887v1 Announce Type: cross Abstract: Temporal knowledge-graph data marketplaces face three coupled failures in static designs: stale hybrid index shortcuts reduce recall as edges evolve,
arXiv:2605.23453v1 Announce Type: new Abstract: We conducted a reproducibility-oriented re-evaluation of prior migraine classification studies, correcting for data leakage and metric bias. We then int
arXiv:2605.23138v1 Announce Type: cross Abstract: Variational Quantum Algorithms (VQAs) potentially offer a pathway to practical quantum advantage, but their optimization is heavily hindered by barren
arXiv:2605.22858v1 Announce Type: cross Abstract: Diagnosing epilepsy is challenging when routine EEGs lack interictal epileptiform discharges (IEDs). Intermittent photic stimulation (IPS) and hyperve
arXiv:2605.23326v1 Announce Type: new Abstract: We present ClimateChat-300K, a large-scale dataset of 299,329 public Facebook posts about climate change collected between May 2020 and May 2024 through
arXiv:2605.23590v1 Announce Type: new Abstract: ReAct-style agents for search-intensive, multi-step reasoning tasks rely largely on their own internal judgment to decide what evidence to seek, which r
arXiv:2605.23264v1 Announce Type: cross Abstract: Generative priors in Image Super-Resolution (SR) often compromise faithful restoration, we attribute this limitation to a fundamental spectral misalig
arXiv:2605.23449v1 Announce Type: cross Abstract: Variational autoencoders (VAEs) often struggle to represent non-commutative structure in learned latent spaces. Symmetry-aware VAEs commonly address t
arXiv:2605.22996v1 Announce Type: new Abstract: We present CoMoGen, a controllable video generation framework that generates realistic interactive dynamics from a single binary mask sequence condition
arXiv:2605.23893v1 Announce Type: new Abstract: We propose Complete-muE, a framework which targets hyperparameter transfer across dense FFN and any Mixture-of-Experts (MoE) setups in transformer block
arXiv:2605.23523v1 Announce Type: new Abstract: Reconstructing the motion of objects from videos is a key component for embodied AI and robot manipulation. While diverse approaches to object pose trac
arXiv:2605.23178v1 Announce Type: new Abstract: Despite recent progress, text-to-image models still struggle to generate semantically diverse and compositionally accurate multi-person interaction scen
arXiv:2605.22827v1 Announce Type: cross Abstract: In large-scale AI systems, allocating scarce resources such as GPU compute time and bandwidth among multiple agents is a critical challenge. Conventio
arXiv:2402.17888v5 Announce Type: replace-cross Abstract: Post-hoc out-of-distribution (OOD) detection has garnered intensive attention in reliable machine learning. Many efforts have been dedicated t