Knowledge catalogue
arXiv:2605.10327v1 Announce Type: cross Abstract: In this paper, we present SCALAR (Symbolic Conjecture and LLM-Assisted Reasoning), a neurosymbolic framework for automated conjecture generation in qu
arXiv:2605.08505v1 Announce Type: cross Abstract: We study the long-context limit of softmax self-attention with a fixed query and a random context of n i.i.d. keys on the sphere, viewing the inverse
arXiv:2605.08124v1 Announce Type: cross Abstract: Mobile agent systems are emerging as a key paradigm for enabling intelligent applications on edge devices and in AIoT ecosystems. However, their scala
arXiv:2605.10119v1 Announce Type: new Abstract: Recent evidence suggests that Adam performs robustly when its momentum parameters are tied, eta_1=eta_2, reducing the optimizer to a single remaining pa
arXiv:2605.10142v1 Announce Type: cross Abstract: Artificial intelligence models are increasingly scaled to improve predictive accuracy, yet it remains unclear whether scale improves the quality of po
arXiv:2509.02372v3 Announce Type: replace-cross Abstract: Large Language Models have become critical to modern software development, but their reliance on uncurated web-scale datasets for training int
arXiv:2605.08528v1 Announce Type: cross Abstract: Autonomous-driving simulators typically trade physical fidelity for scalable parallelism. Physics-based platforms such as CARLA and MetaDrive provide
arXiv:2601.22638v2 Announce Type: replace-cross Abstract: The exponential growth of machine learning submissions has strained the traditional peer review process, resulting in slow feedback loops for
arXiv:2605.10246v1 Announce Type: new Abstract: AI scientist systems are increasingly deployed for autonomous research, yet their academic integrity has never been systematically evaluated. We introdu
arXiv:2604.03687v2 Announce Type: replace Abstract: Long-tailed recognition has benefited from foundation models and fine-tuning paradigms, yet existing studies and benchmarks are mainly confined to n
arXiv:2605.10187v1 Announce Type: new Abstract: Scientific reasoning is a key aspect of human intelligence, requiring the integration of multimodal inputs, domain expertise, and multi-step inference a
arXiv:2604.07383v2 Announce Type: replace Abstract: Cross-city transfer improves prediction in label-scarce cities by leveraging labeled data from other cities, but it becomes challenging when cities
arXiv:2605.09630v1 Announce Type: new Abstract: Tokenizer-free language models eliminate the tokenizer step of the language modeling pipeline by operating directly on bytes; patch-based variants furth
arXiv:2605.05736v2 Announce Type: replace Abstract: Vector quantization (VQ) with autoregressive (AR) token modeling is a widely adopted and highly competitive paradigm for time-series generation. How
arXiv:2605.08322v1 Announce Type: cross Abstract: Sparse MoE models achieve a good balance between capacity and compute by routing each token to a small subset of experts. However, in most MoE archite
arXiv:2603.14889v2 Announce Type: replace-cross Abstract: The rapid evolution of end-to-end spoken dialogue systems demands transcending mere textual semantics to incorporate paralinguistic nuances an
arXiv:2605.09956v1 Announce Type: cross Abstract: High-quality, real-time talking head synthesis remains a fundamental challenge in computer vision. Existing reconstruction- and rendering-based method
arXiv:2602.04811v2 Announce Type: replace-cross Abstract: True self-evolution requires agents to act as lifelong learners that internalize novel experiences to solve future problems. However, rigorous
arXiv:2605.09038v1 Announce Type: new Abstract: Teaching language models to use search tools is not only a question of whether they search, but also of whether they issue good queries. This is especia
arXiv:2605.09039v1 Announce Type: new Abstract: We introduce SeasonScapes framework and a the SeasonScapes dataset: Swiss Sparse-view Mountain Scenes with Seasonal Changes that covers over 50 km x 60
arXiv:2605.08519v1 Announce Type: new Abstract: Learning from scarce labeled data with a larger pool of unlabeled samples, known as semi-supervised few-shot learning (SS-FSL), remains critical for app
arXiv:2605.08382v1 Announce Type: cross Abstract: LLM coding agents now generate code at an unprecedented scale, yet LLM-generated code introduces cybersecurity vulnerabilities into codebases without
arXiv:2605.09721v1 Announce Type: cross Abstract: Tool-enabled AI agents are increasingly deployed in cloud-hosted environments and offered as services, where they perform side-effecting operations th
arXiv:2605.08313v1 Announce Type: cross Abstract: Large language models (LLMs) rely on deterministic pseudorandom number generators (PRNGs) for autoregressive sampling, creating a critical supply-chai
arXiv:2605.09266v1 Announce Type: new Abstract: We introduce SeePhys Pro, a fine-grained modality transfer benchmark that studies whether models preserve the same reasoning capability when critical in
arXiv:2605.10603v1 Announce Type: new Abstract: Despite strong zero-shot performance, SAM is unreliable under domain shift due to Mask-level Confidence Confusion (MCC), where a single IoU-based mask s
arXiv:2407.11906v3 Announce Type: replace Abstract: Surgical data science has seen rapid advancement with the excellent performance of end-to-end deep neural networks (DNNs). Despite their successes,
arXiv:2602.04054v2 Announce Type: replace-cross Abstract: Understanding how neural representations respond to geometric transformations is essential for evaluating whether learned features preserve me
arXiv:2605.09209v1 Announce Type: cross Abstract: We study optimistic bilevel optimization when the lower-level problem has a non-isolated manifold of minimizers. In this setting, the hyper-objective
arXiv:2605.09945v1 Announce Type: new Abstract: Many high-stakes decisions in health care, public policy, and clinical development require committing to a single policy that will be applied uniformly
arXiv:2605.09345v1 Announce Type: new Abstract: We identify a Selection Plateau phenomenon in one-shot neural network pruning: all rank-monotone weight scorers converge to identical accuracy at fixed
arXiv:2603.26089v2 Announce Type: replace-cross Abstract: The ability to represent oneself and others as agents with knowledge, intentions, and belief states that guide their behavior - Theory of Mind
arXiv:2512.19219v2 Announce Type: replace-cross Abstract: Low-rank adaptation (LoRA) is widely used for parameter-efficient fine-tuning, but its standard all-token, all-head design ignores the heterog
arXiv:2605.10466v1 Announce Type: new Abstract: Large language models (LLMs) exhibit two striking and ostensibly unrelated behaviours: in-context learning (ICL) and repetitive generation. In both, the
arXiv:2605.08145v1 Announce Type: cross Abstract: Current vision language models face hallucination and robustness issues against ambiguous or corrupted modalities. We hypothesize that these issues ca
arXiv:2605.08936v1 Announce Type: new Abstract: Large Reasoning Models possess remarkable capabilities for self-correction in general domain; however, they frequently struggle to recover from unsafe r
arXiv:2605.08874v1 Announce Type: new Abstract: Open-vocabulary semantic segmentation requires adapting image-level vision-language models such as CLIP to dense pixel-level prediction, which is challe
arXiv:2605.08680v1 Announce Type: cross Abstract: LLM code-generation pipelines often sample multiple candidates and select one final answer without access to a complete oracle. Existing pipelines mix
arXiv:2605.09485v1 Announce Type: new Abstract: Latent representations learned by neural networks often exhibit semantic structure, where concept similarity is reflected by geometric proximity in embe
arXiv:2605.09284v1 Announce Type: cross Abstract: Mesh-based simulations provide high-fidelity solutions to partial differential equations (PDEs), but achieving such accuracy typically requires fine m
arXiv:2605.10394v1 Announce Type: new Abstract: The detection of sensational content in media items can be a critical filtering mechanism for identifying check-worthy content and flagging potential di
arXiv:2605.10576v1 Announce Type: cross Abstract: Low-level visual perception underpins reliable remote sensing (RS) image analysis, yet current image quality assessment (IQA) methods output uninterpr
arXiv:2605.09906v1 Announce Type: new Abstract: Audio and vision provide complementary evidence for audio-visual question answering, yet current audio-visual large language models may suffer from cros
arXiv:2506.16234v2 Announce Type: replace Abstract: Causal discovery from observational data typically assumes access to complete data and availability of perfect domain experts. In practice, data oft
arXiv:2605.09746v1 Announce Type: cross Abstract: Landslide detection from satellite imagery has advanced through deep learning, yet most models rely on large, highly correlated spectral-topographic i
arXiv:2602.16596v2 Announce Type: replace Abstract: Modern AI models are not static. They go through multiple updates in their lifecycles. We propose to design Sequential Membership Inference (SeMI) a
arXiv:2605.10571v1 Announce Type: cross Abstract: Quantitative cardiac magnetic resonance imaging (MRI) enables non-invasive myocardial tissue characterization but relies on robust motion correction w
arXiv:2605.10298v1 Announce Type: new Abstract: Accurate next-day active fire forecasts can support early warning, disaster response, forest risk assessment, and downstream estimation of fire-related
arXiv:2605.08302v1 Announce Type: cross Abstract: Real-world digital Parkinson's disease assessment faces challenges such as heterogeneous modalities, cross-device bias, and incomplete labeling. Exist
arXiv:2605.09033v1 Announce Type: cross Abstract: Graph-based agent memory is increasingly used in LLM agents to support structured long-term recall and multi-hop reasoning, but it also creates a new
arXiv:2605.09271v1 Announce Type: new Abstract: Although natural language is the default medium for Large Language Models (LLMs), its limited expressive capacity creates a profound bottleneck for comp
arXiv:2605.08897v1 Announce Type: cross Abstract: Activated PI3K8 Syndrome (APDS) is a rare genetic immune disorder caused by variants in PIK3CD or PIK3R1, with highly heterogeneous symptoms that ofte
arXiv:2605.10395v1 Announce Type: cross Abstract: We study the information-theoretic limits of learning a one-hidden-layer teacher network with hierarchical features from noisy queries, in the context
arXiv:2605.10913v1 Announce Type: new Abstract: We introduce Shepherd, a functional programming model that formalizes meta-agent operations on target agents as functions, with core operations mechaniz
arXiv:2605.09171v1 Announce Type: new Abstract: We present SHIELD, a hierarchical algorithm that reduces both the decision-variable dimension and the constraint set in ell_1-regularized convex program
arXiv:2605.10888v1 Announce Type: cross Abstract: Shielding is a prominent model-based technique to ensure safety of autonomous agents. Classical shielding aims to ensure that nothing bad ever happens
arXiv:2605.08482v1 Announce Type: cross Abstract: Automated ICD-10 coding from clinical discharge summaries requires models that are both accurate on long-tailed multi-label classification tasks and i
arXiv:2601.21061v2 Announce Type: replace Abstract: Generative Flow Networks (GFlowNets; GFNs) are a class of generative models that learn to sample compositional objects proportionally to their a pri
arXiv:2605.10313v1 Announce Type: new Abstract: We study contextual bandits with nonlinear and path-dependent rewards through a novel signature-transform-based approach. Leveraging the universal nonli
arXiv:2605.08784v1 Announce Type: new Abstract: Product poster generation poses distinct challenges beyond general poster design, requiring both faithful preservation of product appearance and precise