Knowledge catalogue
arXiv:2605.07674v1 Announce Type: cross Abstract: Regulatory audits of AI systems increasingly rely on differential privacy (DP) to protect training data and model internals. We study audit design whe
arXiv:2605.07210v1 Announce Type: cross Abstract: PromptReps showed that an autoregressive language model can be used directly as a retriever by prompting it to generate dense and sparse representatio
arXiv:2605.07503v1 Announce Type: new Abstract: Efficiently aligning large-scale video diffusion models with human intent requires a scalable and trajectory-aware pathway that bridges the inherent dis
arXiv:2601.21951v2 Announce Type: replace-cross Abstract: We develop diffusion-based samplers for target distributions known up to a normalising constant. To this end, we rely on the well-known diffus
arXiv:2605.07494v1 Announce Type: new Abstract: Continual learning enables vision-language models to accumulate knowledge and adapt to evolving tasks without retraining from scratch. However, in multi
arXiv:2605.07221v1 Announce Type: new Abstract: Adapting foundation models to medical segmentation typically requires either backbone fine-tuning or high-capacity task-specific decoders, both of which
arXiv:2508.20909v2 Announce Type: replace Abstract: Foundation models pre-trained on large-scale natural image datasets offer a powerful paradigm for medical image segmentation. However, effectively t
arXiv:2506.13351v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) training of large language models (LLMs) on unverifiable tasks is challenging even when a reasonable-quality refer
arXiv:2602.22831v2 Announce Type: replace-cross Abstract: Moral benchmarks for LLMs typically score models on context-free prompts, implicitly treating the measured choice rate as stable. We test this
arXiv:2412.11194v2 Announce Type: replace-cross Abstract: Security vulnerabilities in software can have severe consequences; however, manual vulnerability detection is costly and does not scale, espec
arXiv:2605.07662v1 Announce Type: new Abstract: Low-precision number formats are widely used in modern machine learning systems due to their efficiency. Accurate direction representation is key to the
arXiv:2605.07551v1 Announce Type: new Abstract: Standard Importance Sampling (IS) collapses under label corruption because high-norm examples, prioritized for variance reduction, are often adversarial
arXiv:2605.07351v1 Announce Type: new Abstract: While Gaussian Splatting-based Feature Fields (GSFFs) have shown promise for visual localization, this paper highlights that photometrically optimized G
arXiv:2506.23875v4 Announce Type: replace-cross Abstract: Sequential computation via autoregressive generation can make difficult tasks learnable, but the generation order of intermediate states stron
arXiv:2602.16928v3 Announce Type: replace-cross Abstract: Much of the advancement in Multi-Agent Reinforcement Learning (MARL) for imperfect-information games has historically depended on the manual,
arXiv:2605.07323v1 Announce Type: new Abstract: Discovering governing differential equations from observational data is a fundamental challenge in scientific machine learning. Existing symbolic regres
arXiv:2605.06785v1 Announce Type: cross Abstract: Inference-time scaling methods rely on Process Reward Models (PRMs), which are often poorly calibrated and overestimate success probabilities. We prop
arXiv:2605.07844v1 Announce Type: new Abstract: Energy-based learning is a powerful framework for generative modelling, but its training is inherently non-convex, leading potentially to sensitivity to
arXiv:2605.07821v1 Announce Type: cross Abstract: Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models. Existing methods mostly focus on regular entangle
arXiv:2511.09117v4 Announce Type: replace Abstract: Kuzushiji, a pre-modern Japanese cursive script, can currently be read and understood by only a few thousand trained experts in Japan. With the rapi
arXiv:2605.07061v1 Announce Type: cross Abstract: Joint audio-video generation models are rapidly approaching professional production quality, raising a central question: do they understand audio-visu
arXiv:2602.16360v2 Announce Type: replace Abstract: Our understanding of the oceans remains limited by sparse and infrequent observations, primarily because current methods are constrained by the high
arXiv:2605.07483v1 Announce Type: cross Abstract: Successful deep neural networks discover salient features of data. We show when and why they fail to learn out-of-distribution (OOD)-relevant represen
arXiv:2605.06673v1 Announce Type: cross Abstract: Aggregate metacognitive quality scores mask within-model variation across MMLU benchmark domains. We administered 1,500 MMLU items (250 per domain, un
arXiv:2605.08036v1 Announce Type: new Abstract: We introduce CUTS-GPR, a new method for performing numerically exact Gaussian process regression (GPR) in high-dimensional settings. The key component o
arXiv:2602.20816v3 Announce Type: replace Abstract: The core learning signal used in language model distillation is the standard Kullback-Leibler (KL) divergence between the student and teacher distri
arXiv:2605.07222v1 Announce Type: new Abstract: How few parameters do we really need to forecast a periodic time series? An hourly electricity series, reshaped as a 24-row matrix with one column per d
arXiv:2605.06885v1 Announce Type: cross Abstract: Diffusion language models (DLMs) have recently demonstrated capabilities that complement standard autoregressive (AR) models, particularly in non-sequ
arXiv:2605.07985v1 Announce Type: cross Abstract: Selecting the optimal LLM inference configuration requires evaluation across hardware, serving engines, attention backends, and model architectures, s
arXiv:2605.07151v1 Announce Type: cross Abstract: Urban spatial evolution is manifested not only through horizontal expansion but also through vertical structural changes. Consequently, jointly captur
arXiv:2605.07041v1 Announce Type: cross Abstract: This paper introduces Dr-BA, a first-of-its-kind radar bundle adjustment (BA) framework that operates directly on 2D spinning radar intensity images.
arXiv:2605.07063v1 Announce Type: cross Abstract: Data selection methods address a critical challenge in LLM post-training: effectively leveraging scarce, high-fidelity target data alongside abundant
arXiv:2605.06989v1 Announce Type: cross Abstract: K-means clustering is widely used in psychological and psychometric research to identify profiles, subgroups, and potential typologies, yet its classi
arXiv:2510.00253v2 Announce Type: replace Abstract: Smoothness is a key inductive bias in machine learning and is closely related to generalization. Existing smoothness-inducing methods typically rely
arXiv:2605.07727v1 Announce Type: cross Abstract: We propose Drifting Field Policy (DFP), a non-ODE one-step generative policy built on the drifting model paradigm. We frame the policy update as a rev
arXiv:2605.07699v1 Announce Type: cross Abstract: LLM-based agents are increasingly deployed for routine but consequential tasks in real-world domains, where their behavior is governed by inherently a
arXiv:2512.14263v2 Announce Type: replace-cross Abstract: Preferential Bayesian Optimization (PBO) aims to find a decision-maker's most preferred solution in as few pairwise comparisons as possible. E
arXiv:2605.07011v1 Announce Type: new Abstract: Motivational-interviewing-based health coaching is an effective approach for improving mental health and promoting healthy behavior change. However, the
arXiv:2605.06911v1 Announce Type: new Abstract: Subseasonal-to-seasonal (S2S) temperature forecasts, spanning several weeks to a few months, are critically needed in agriculture practice, energy plann
arXiv:2508.06816v3 Announce Type: replace Abstract: Lesion segmentation, in contrast to natural scene segmentation, requires handling subtle variations in texture and color, frequent imaging artifacts
arXiv:2605.07971v1 Announce Type: new Abstract: We introduce Discrete Voxel Diffusion (DVD), a discrete diffusion framework to generate, assess, and edit sparse voxels for SLat (Structured LATent) bas
arXiv:2605.07556v1 Announce Type: new Abstract: Recent work has shown that contiguous vision transformer (ViT) blocks (a) can be replaced by a linear map and (b) organize into recurrent phases of comp
arXiv:2512.09682v2 Announce Type: replace-cross Abstract: This work studies the application of Multi-Agent Reinforcement Learning (MARL) to decentralized control of unmanned aerial vehicles to relay a
arXiv:2603.14787v2 Announce Type: replace Abstract: Pneumatically-actuated anthropomorphic robots with high degrees of freedom (DOF) offer significant potential for physical human-robot interaction. H
arXiv:2602.06827v2 Announce Type: replace Abstract: In this paper, we introduce DynaRetarget, a complete pipeline for retargeting human motions to humanoid control policies. The core component of Dyna
arXiv:2605.06997v1 Announce Type: new Abstract: Long chain-of-thought reasoning and agentic tool-calling produce traces spanning tens of thousands of tokens, yet Transformer KV caches grow linearly wi
arXiv:2603.00041v2 Announce Type: replace-cross Abstract: Causal machine learning (ML) recovers graphical structures that inform us about potential cause-and-effect relationships. Most progress has fo
arXiv:2605.06714v1 Announce Type: cross Abstract: Edge deep learning, a paradigm change reconciling edge computing and deep learning, facilitates real-time decision making attuned to environmental fac
arXiv:2508.06805v2 Announce Type: replace Abstract: Accurate localization of organ boundaries is critical in medical imaging for segmentation, registration, surgical planning, and radiotherapy. While
arXiv:2605.07457v1 Announce Type: new Abstract: Recent text-guided image editing (TIE) models have made remarkable progress, yet edited images still frequently suffer from fine-grained issues such as
arXiv:2605.07455v1 Announce Type: new Abstract: Visual-prompt-guided edit transfer aims to learn image transformations directly from example pairs, offering more precise and controllable editing than
arXiv:2605.07417v1 Announce Type: cross Abstract: Modern Deep Learning (DL) workloads are increasingly deployed in safety-critical domains, such as automotive systems and hyperscale data centers, wher
arXiv:2605.07488v1 Announce Type: new Abstract: The scaling of Large Multimodal Models (LMMs) is constrained by the quality-quantity trade-off inherent in synthetic data. Previous approaches, such as
arXiv:2605.07757v1 Announce Type: new Abstract: Formal verification of neural control barrier functions (NCBFs) remains challenging, especially for neural networks with nonlinear activations like (anh
arXiv:2605.05674v2 Announce Type: replace-cross Abstract: Vector search systems built on frozen vision encoders face queries from unseen classes at deployment, yet existing adapter training collapses
arXiv:2605.07642v1 Announce Type: new Abstract: Forecasting future 3D hand pose sequences from egocentric video is essential for understanding human intention and enabling embodied applications such a
arXiv:2605.07299v1 Announce Type: cross Abstract: Existing Multimodal Large Language Models (MLLMs) remain primarily reactive, failing to continuously perceive environments or proactively assist users
arXiv:2605.08073v1 Announce Type: cross Abstract: Recent event-based image reconstruction methods predominantly rely on Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) to process c
arXiv:2602.00716v4 Announce Type: replace-cross Abstract: Classifier-free guidance (CFG) is the de facto standard for conditional sampling in diffusion models, yet it often reduces sample diversity. U
arXiv:2602.20338v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting significantly improves reasoning in Large Language Models, yet the temporal dynamics of the underlying representati