All Research Papers

Speculative generation has emerged as a promising technique to accelerate inference in large language models (LLMs) by leveraging parallelism to verify multiple draft tokens simultaneously. However, t...

The rapid deployment of Large Language Models (LLMs) has created an urgent need for enhanced security and privacy measures in Machine Learning (ML). LLMs are increasingly being used to process untrust...

Ensuring the safety of AI-enabled systems, particularly in high-stakes domains such as autonomous driving and healthcare, has become increasingly critical. Traditional formal verification tools fall s...

Fairness and action smoothness are two crucial considerations in many online optimization problems, but they have yet to be addressed simultaneously. In this paper, we study a new and challenging sett...

Real-time chunking (RTC) enables vision-language-action models (VLAs) to generate smooth, reactive robot trajectories by asynchronously predicting action chunks and conditioning on previously committe...

We consider the fundamental problem of balanced $k$-means clustering. In particular, we introduce an optimal transport approach to alternating minimization called BalLOT, and we show that it delivers ...

In the era of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) architectures are gaining significant attention for their ability to ground language generation in reliable knowledge s...

Accurate real-time waypoints estimation for the UAV-based online Terrain Following during wildfire patrol missions is critical to ensuring flight safety and enabling wildfire detection. However, exist...

Weakly supervised semantic segmentation (WSSS) in histopathology reduces pixel-level labeling by learning from image-level labels, but it is hindered by inter-class homogeneity, intra-class heterogene...

In this work we investigate the relationship between kernel regularity and algorithmic performance in the bandit optimization of RKHS functions. While reproducing kernel Hilbert space (RKHS) methods t...

Users frequently edit camera images post-capture to achieve their preferred photofinishing style. While editing in the RAW domain provides greater accuracy and flexibility, most edits are performed on...

We introduce a simple post-training method that makes transformer attention sparse without sacrificing performance. Applying a flexible sparsity regularisation under a constrained-loss objective, we s...

Modern extensible compiler frameworks-such as MLIR-enable rapid creation of domain-specific language dialects. This flexibility, however, makes correctness harder to ensure as the same extensibility t...

Deep residual networks (ResNets) have demonstrated outstanding success in computer vision tasks, attributed to their ability to maintain gradient flow through deep architectures. Simultaneously, contr...

Spiking neural networks (SNNs), central to computational neuroscience and neuromorphic machine learning (ML), require efficient simulation and gradient-based training. While AI accelerators offer prom...

In context-specific applications such as robotics, telecommunications, and healthcare, artificial intelligence systems often face the challenge of limited training data. This scarcity introduces epist...

While three-dimensional (3D) shape and pose estimation is a highly researched area that has yielded significant advances, the resulting methods, despite performing well for the adult population, gener...

As concerns around data privacy in machine learning grow, the ability to unlearn, or remove, specific data points from trained models becomes increasingly important. While state of the art unlearning ...

Developers are widely using AI code-generation models, aiming to increase productivity and efficiency. However, there are also quality concerns regarding the AI-generated code. The generated code is p...

An associative memory (AM) enables cue-response recall, and it has recently been recognized as a key mechanism underlying modern neural architectures such as Transformers. In this work, we introduce t...

Flow-based generative models have recently demonstrated strong performance, yet sampling typically relies on expensive numerical integration of ordinary differential equations (ODEs). Rectified Flow e...

Achieving fully autonomous driving systems requires learning rational decisions in a wide span of scenarios, including safety-critical and out-of-distribution ones. However, such cases are underrepres...

Diffusion-based image editing has made semantic level image manipulation easy for general users, but it also enables realistic local forgeries that are hard to localize. Existing benchmarks mainly foc...

Machine learning models perform well across domains such as diagnostics, weather forecasting, NLP, and autonomous driving, but their limited uncertainty handling restricts use in safety-critical setti...

Face verification is a significant component of identity authentication in various applications including online banking and secure access to personal devices. The majority of the existing face image ...

Neural network subgrid stress models often have a priori performance that is far better than the a posteriori performance, leading to neural network models that look very promising a priori completely...

Foundation Models (FMs) are increasingly used in remote sensing (RS) for tasks such as environmental monitoring, disaster assessment, and land-use mapping. These models include unimodal vision encoder...

Recent video generation approaches increasingly rely on planning intermediate control signals such as object trajectories to improve temporal coherence and motion fidelity. However, these methods most...

When performing robot/vehicle localization using ground penetrating radar (GPR) to handle adverse weather and environmental conditions, existing techniques often struggle to accurately estimate distan...

We present a patient-centric architecture for electronic health record (EHR) sharing that separates content storage from authorization and audit. Encrypted FHIR resources are stored off-chain; a publi...

Self-supervised learning (SSL) has recently advanced through non-contrastive methods that couple an invariance term with variance, covariance, or redundancy-reduction penalties. While such objectives ...

Deep learning models are prone to learning shortcut solutions to problems using spuriously correlated yet irrelevant features of their training data. In high-risk applications such as medical image an...

Traditional evaluation metrics for textual and visual question answering, like ROUGE, METEOR, and Exact Match (EM), focus heavily on n-gram based lexical similarity, often missing the deeper semantic ...

We present a differentiable extension of the VEROS ocean model, enabling automatic differentiation through its dynamical core. We describe the key modifications required to make the model fully compat...

The task of dataset distillation aims to find a small set of synthetic images such that training a model on them reproduces the performance of the same model trained on a much larger dataset of real s...

Vision Language Models (VLMs) have achieved impressive performance on spatial reasoning benchmarks, yet these evaluations mask critical weaknesses in understanding object interactions. Current benchma...

We introduce the Bayesian Information-Theoretic Sampling for hierarchical GAussian Process Surrogates (BITS for GAPS) framework to emulate latent components in hybrid physical systems. BITS for GAPS s...

This paper introduces Generative Augmented Reality (GAR) as a next-generation paradigm that reframes augmentation as a process of world re-synthesis rather than world composition by a conventional AR ...

Controllable image generation has attracted increasing attention in recent years, enabling users to manipulate visual content such as identity and style. However, achieving simultaneous control over t...

We study randomized experiments in bipartite systems where only a subset of treatment-side units are eligible for assignment while all units continue to interact, generating interference. We formalize...

Agile methods are characterised by iterative and incremental processes with a strong focus on flexibility and accommodating changing requirements based on either technical, regulatory, or stakeholder ...

We present \textsf{ModularSubsetSelection} (MSS), a new algorithm for locally differentially private (LDP) frequency estimation. Given a universe of size $k$ and $n$ users, our $\varepsilon$-LDP mecha...

Recent text-to-image (T2I) models have made remarkable progress in generating visually realistic and semantically coherent images. However, they still suffer from randomness and inconsistency with the...

We introduce proactive hearing assistants that automatically identify and separate the wearer's conversation partners, without requiring explicit prompts. Our system operates on egocentric binaural au...

Comprehending long visual documents, where information is distributed across extensive pages of text and visual elements, is a critical but challenging task for modern Vision-Language Models (VLMs). E...

Recent advances in generative modeling have substantially enhanced 3D urban generation, enabling applications in digital twins, virtual cities, and large-scale simulations. However, existing methods f...

The evolution of Visual Large Language Models (VLLMs) has revolutionized the automatic understanding of Visually Rich Documents (VRDs), which contain both textual and visual elements. Although VLLMs e...

The "Vision Zero" policy, introduced by the Swedish Parliament in 1997, aims to eliminate fatalities and serious injuries resulting from traffic accidents. To achieve this goal, the use of self-drivin...

Recently, several instances of non-Euclidean SGD, including SignSGD, Lion, and Muon, have attracted significant interest from the optimization community due to their practical success in training deep...

Data attribution for text-to-image models aims to identify the training images that most significantly influenced a generated output. Existing attribution methods involve considerable computational re...

The improving multi-armed bandits problem is a formal model for allocating effort under uncertainty, motivated by scenarios such as investing research effort into new technologies, performing clinical...

Although Sentinel-2 based land use and land cover (LULC) classification is critical for various environmental monitoring applications, it is a very difficult task due to some key data challenges (e.g....

Automated emotion detection is widely used in applications ranging from well-being monitoring to high-stakes domains like mental health and hiring. However, models often rely on annotations that refle...

As social robots increasingly enter public environments, their acceptance depends not only on technical reliability but also on ethical integrity, accessibility, and user trust. This paper reports on ...

Large language model (LLM)-based agents struggle to generalize to novel and complex environments, such as unseen websites or new sets of functions, due to a fundamental mismatch between their pre-trai...

To serve global users safely and productively, LLMs need culture-specific knowledge that might not be learned during pre-training. How do we find such knowledge that is (1) salient to in-group users, ...

Semantic segmentation of blood vessels is an important task in medical image analysis, but its progress is often hindered by the scarcity of large annotated datasets and the poor generalization of mod...

We present Contamination Detection via Context (CoDeC), a practical and accurate method to detect and quantify training data contamination in large language models. CoDeC distinguishes between data me...

Previous work has argued that recursive numeral systems optimise the trade-off between lexicon size and average morphosyntatic complexity (Deni\'c and Szymanik, 2024). However, showing that only natur...

Hallucination--defined here as generating statements unsupported or contradicted by available evidence or conversational context--remains a major obstacle to deploying conversational AI systems in set...

Video generation models have progressed tremendously through large latent diffusion transformers trained with rectified flow techniques. Yet these models still struggle with geometric inconsistencies,...

AI agents hold the potential to revolutionize scientific productivity by automating literature reviews, replicating experiments, analyzing data, and even proposing new directions of inquiry; indeed, t...

Geometric data and purpose-built generative models on them have become ubiquitous in high-impact deep learning application domains, ranging from protein backbone generation and computational chemistry...

We introduce a highly expressive yet distinctly tractable family for black-box variational inference (BBVI). Each member of this family is a weighted product of experts (PoE), and each weighted expert...

Constructing comprehensive knowledge graphs requires the use of multiple ontologies in order to fully contextualize data into a domain. Ontology matching finds equivalences between concepts interconne...

Achieving safe, reliable real-world robotic manipulation requires agents to evolve beyond vision and incorporate tactile sensing to overcome sensory deficits and reliance on idealised state informatio...

Post-disaster road assessment (PDRA) is essential for emergency response, enabling rapid evaluation of infrastructure conditions and efficient allocation of resources. Although drones provide a flexib...

Long-horizon reasoning in LLM-based agents often fails not from generative weakness but from insufficient verification of intermediate reasoning. Co-Sight addresses this challenge by turning reasoning...

Retrieval-Augmented Generation (RAG) integrates external knowledge to mitigate hallucinations, yet models often generate outputs inconsistent with retrieved content. Accurate hallucination detection r...

With the widespread adoption of wearable devices in our daily lives, the demand and appeal for remote patient monitoring have significantly increased. Most research in this field has concentrated on c...

Neural networks excel at processing unstructured data but often fail to generalise out-of-distribution, whereas classical algorithms guarantee correctness but lack flexibility. We explore whether pret...

The clinical adoption of biomedical vision-language models is hindered by prompt optimization techniques that produce either uninterpretable latent vectors or single textual prompts. This lack of tran...

Open-Vocabulary Semantic Segmentation (OVSS) assigns pixel-level labels from an open set of categories, requiring generalization to unseen and unlabelled objects. Using vision-language models (VLMs) t...

Tool-augmented large language models (LLMs) are emerging as deep research agents, systems that decompose complex queries, retrieve external evidence, and synthesize grounded responses. Yet current age...

So-called `wicked problems', those involving complex multi-dimensional settings, non-verifiable outcomes, heterogeneous impacts and a lack of single objectively correct answers, have plagued humans th...

Accurate forecasting is critical for reliable power grid operations, particularly as the share of renewable generation, such as wind and solar, continues to grow. Given the inherent uncertainty and va...

Concept Bottleneck Models (CBMs) enhance interpretability by predicting human-understandable concepts as intermediate representations. However, existing CBMs often suffer from input-to-concept mapping...

Despite rapid advances in text-to-video synthesis, generated video quality remains critically dependent on precise user prompts. Existing test-time optimization methods, successful in other domains, s...

Light field images capture multi-view scene information and play a crucial role in 3D scene reconstruction. However, their high-dimensional nature results in enormous data volumes, posing a significan...

We study conformal inference in non-exchangeable environments through the lens of Blackwell's theory of approachability. We first recast adaptive conformal inference (ACI, Gibbs and Cand\`es, 2021) as...

Hip fractures are a major cause of disability, mortality, and healthcare burden in older adults, underscoring the need for early risk assessment. However, commonly used tools such as the DXA T-score a...

We argue that progress toward AGI is theory limited rather than data or scale limited. Building on the critical rationalism of Popper and Deutsch, we challenge the Platonic Representation Hypothesis. ...

Identifying the effects of mechanical ventilation strategies and protocols in critical care requires analyzing data from heterogeneous patient-ventilator systems within the context of the clinical dec...

Reasoning language models such as OpenAI-o1, DeepSeek-R1, and Qwen achieve strong performance via extended chains of thought but often generate unnecessarily long outputs. Maximizing intelligence per ...

Advanced Persistent Threats (APTs) are stealthy cyberattacks that often evade detection in system-level audit logs. Provenance graphs model these logs as connected entities and events, revealing relat...

Widespread LLM adoption has introduced characteristic repetitive phraseology, termed ``slop,'' which degrades output quality and makes AI-generated text immediately recognizable. We present Antislop, ...

Product quantisation (PQ) is a classical method for scalable vector encoding, yet it has seen limited usage for latent representations in high-fidelity image generation. In this work, we introduce PQG...

Partial observability is a notorious challenge in reinforcement learning (RL), due to the need to learn complex, history-dependent policies. Recent empirical successes have used privileged expert dist...

Learning rate warm-up - increasing the learning rate at the beginning of training - has become a ubiquitous heuristic in modern deep learning, yet its theoretical foundations remain poorly understood....

Most existing approaches to referring segmentation achieve strong performance only through fine-tuning or by composing multiple pre-trained models, often at the cost of additional training and archite...

N-gram novelty is widely used to evaluate language models' ability to generate text outside of their training data. More recently, it has also been adopted as a metric for measuring textual creativity...

Recent reinforcement learning (RL) methods have substantially enhanced the planning capabilities of Large Language Models (LLMs), yet the theoretical basis for their effectiveness remains elusive. In ...

Asynchronous patient-clinician messaging via EHR portals is a growing source of clinician workload, prompting interest in large language models (LLMs) to assist with draft responses. However, LLM outp...

We propose a reduced-space formulation for optimizing over trained neural networks where the network's outputs and derivatives are evaluated on a GPU. To do this, we treat the neural network as a "gra...

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in aligning visual inputs with natural language outputs. Yet, the extent to which generated tokens depend on visual m...

Heuristic functions are central to the performance of search algorithms such as A-star, where admissibility - the property of never overestimating the true shortest-path cost - guarantees solution opt...

Deep neural networks and brains both learn and share superficial similarities: processing nodes are likened to neurons and adjustable weights are likened to modifiable synapses. But can a unified theo...

In this paper, we present two effective policy learning algorithms for multi-agent online coordination(MA-OC) problem. The first one, \texttt{MA-SPL}, not only can achieve the optimal $(1-\frac{c}{e})...

Quantum generative models based on instantaneous quantum polynomial (IQP) circuits show great promise in learning complex distributions while maintaining classical trainability. However, current imple...

Spiking neural networks (SNNs) have recently been attracting significant attention for their biological plausibility and energy efficiency, but semi-supervised learning (SSL) methods for SNN-based mod...

Efficiently detecting human intent to interact with ubiquitous robots is crucial for effective human-robot interaction (HRI) and collaboration. Over the past decade, deep learning has gained traction ...

Reinforcement learning (RL) is the dominant paradigm for sharpening strategic tool use capabilities of LLMs on long-horizon, sparsely-rewarded agent tasks, yet it faces a fundamental challenge of expl...

We prove that all standard subregular language classes are linearly separable when represented by their deciding predicates. This establishes finite observability and guarantees learnability with simp...

Flow-matching generative models have emerged as a powerful paradigm for continuous data generation, achieving state-of-the-art results across domains such as images, 3D shapes, and point clouds. Despi...

This paper investigates artificial intelligence (AI) methodologies for the synthesis and transpilation of permutation circuits across generic topologies. Our approach uses Reinforcement Learning (RL) ...

When do machine learning systems fail to generalize, and what mechanisms could improve their generalization? Here, we draw inspiration from cognitive science to argue that one weakness of machine lear...

Code translation transforms source code from one programming language (PL) to another. Validating the functional equivalence of translation and repairing, if necessary, are critical steps in code tran...

Designing effective reward functions remains a major challenge in reinforcement learning (RL), often requiring considerable human expertise and iterative refinement. Recent advances leverage Large Lan...

In this work, we present Blind-Spot Guided Diffusion, a novel self-supervised framework for real-world image denoising. Our approach addresses two major challenges: the limitations of blind-spot netwo...

Atomic data determined by analysis of observed atomic spectra are essential for plasma diagnostics. For each low-ionisation open d- and f-subshell atomic species, around $10^3$ fine structure level en...

Evaluating long-form answers in high-stakes domains such as law or medicine remains a fundamental challenge. Standard metrics like BLEU and ROUGE fail to capture semantic correctness, and current LLM-...

We propose an algorithm with improved query-complexity for the problem of hypothesis selection under local differential privacy constraints. Given a set of $k$ probability distributions $Q$, we descri...

A well-known pitfall of molecular generative models is that they are not guaranteed to generate synthesizable molecules. There have been considerable attempts to address this problem, but given the ex...

Neural audio codecs are a fundamental component of modern generative audio pipelines. Although recent codecs achieve strong low-bitrate reconstruction and provide powerful representations for downstre...

With the increasing popularity of large language models (LLMs) and LLM-based agents, reliable and effective code evaluation metrics (CEMs) have become crucial for progress across several software engi...

AI co-writing systems challenge long held ideals about agency and ownership in the creative process, thereby hindering widespread adoption. In order to address this, we investigate conceptions of agen...

Deep learning models are notoriously opaque. Existing explanation methods often focus on localized visual explanations for individual images. Concept-based explanations, while offering global insights...

Plug-and-Play Priors (PnP) is a popular framework for solving imaging inverse problems by integrating learned priors in the form of denoisers trained to remove Gaussian noise from images. In standard ...

Generative adversarial networks (GANs) have demonstrated significant progress in unpaired image-to-image translation in recent years for several applications. CycleGAN was the first to lead the way, a...

Decomposing an image into its intrinsic photometric factors--shading and reflectance--is a long-standing challenge due to the lack of extensive ground-truth data for real-world scenes. Recent methods ...

We present Multipole Semantic Attention (MuSe), an efficient approximation of softmax attention that combines semantic clustering with multipole expansions from computational physics. Our method addre...

Linear systems arise in generating samples and in calculating observables in lattice quantum chromodynamics~(QCD). Solving the Hermitian positive definite systems, which are sparse but ill-conditioned...

Optical Coherence Tomography (OCT) is a vital imaging modality for diagnosing and monitoring retinal diseases. However, OCT images are inherently degraded by speckle noise, which obscures fine details...

Mammography screening is an essential tool for early detection of breast cancer. The speed and accuracy of mammography interpretation have the potential to be improved with deep learning methods. Howe...

Several emerging post-Bayesian methods target a probability distribution for which an entropy-regularised variational objective is minimised. This increased flexibility introduces a computational chal...

Ensuring the resilience of computer-based railways is increasingly crucial to account for uncertainties and changes due to the growing complexity and criticality of those systems. Although their softw...

Recent advances in text-based image editing have enabled fine-grained manipulation of visual content guided by natural language. However, such methods are susceptible to adversarial attacks. In this w...

Given a dataset of finitely many elements $\mathcal{T} = \{\mathbf{x}_i\}_{i = 1}^N$, the goal of dataset condensation (DC) is to construct a synthetic dataset $\mathcal{S} = \{\tilde{\mathbf{x}}_j\}_...

Reinforcement Learning (RL) agents deployed in real-world environments face degradation from sensor faults, actuator wear, and environmental shifts, yet lack intrinsic mechanisms to detect and diagnos...

Contrastive learning is a widely adopted self-supervised pretraining strategy, yet its dependence on cohort composition remains underexplored. We present Contrasting by Patient Augmented Electrocardio...

Inference-time scaling has emerged as a powerful way to improve large language model (LLM) performance by generating multiple candidate responses and selecting among them. However, existing work on dy...

Social robots are increasingly experimented in public and assistive settings, but their accessibility for Deaf users remains quite underexplored. Italian Sign Language (LIS) is a fully-fledged natural...

In this paper we analyze the Gradient-Step Denoiser and its usage in Plug-and-Play algorithms. The Plug-and-Play paradigm of optimization algorithms uses off the shelf denoisers to replace a proximity...

Objective: Deep learning-based deformable image registration has achieved strong accuracy, but remains sensitive to variations in input image characteristics such as artifacts, field-of-view mismatch,...

In-context operator networks (ICON) are a class of operator learning methods based on the novel architectures of foundation models. Trained on a diverse set of datasets of initial and boundary conditi...

Chain-of-thought reasoning, while powerful, can produce unnecessarily verbose output for simpler problems. We present a framework for difficulty-aware reasoning that teaches models to dynamically adju...

Editing complex real-world sound scenes is difficult because individual sound sources overlap in time. Generative models can fill-in missing or corrupted details based on their strong prior understand...

Pre-trained language models have achieved remarkable success across diverse applications but remain susceptible to spurious, concept-driven correlations that impair robustness and fairness. In this wo...

This paper presents a robust model predictive control (MPC) framework that explicitly addresses the non-Gaussian noise inherent in deep learning-based perception modules used for state estimation. Rec...

Federated learning has the potential to unlock siloed data and distributed resources by enabling collaborative model training without sharing private data. As more complex foundational models gain wid...

Technological advances have spurred an increase in data complexity and dimensionality. We are now in an era in which data sets containing thousands of features are commonplace. To digest and analyze s...

Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty. Such "hallucinations" per...

Recent AI work trends towards incorporating human-centric objectives, with the explicit goal of aligning AI models to personal preferences and societal values. Using standard preference elicitation me...

Building reliable LLM agents requires decisions at two levels: the graph (which modules exist and how information flows) and the configuration of each node (models, prompts, tools, control knobs). Mos...

We present an imitation learning approach for spacecraft guidance, navigation, and control(GNC) that achieves high performance from limited data. Using only 100 expert demonstrations, equivalent to 6,...

Multimodal foundation models can process several modalities. However, since the space of possible modalities is large and evolving over time, training a model from scratch to encompass all modalities ...

Vision-language models (VLMs) like CLIP have shown impressive zero-shot and few-shot learning capabilities across diverse applications. However, adapting these models to new fine-grained domains remai...

Nonnegative matrix factorization (NMF) is a known unsupervised data-reduction method. The principle of the common cause (PCC) is a basic methodological approach in probabilistic causality, which seeks...

Estimating scene lighting from a single image or video remains a longstanding challenge in computer vision and graphics. Learning-based approaches are constrained by the scarcity of ground-truth HDR e...

Additive two-tower models are popular learning-to-rank methods for handling biased user feedback in industry settings. Recent studies, however, report a concerning phenomenon: training two-tower model...

Misleading visualizations are a potent driver of misinformation on social media and the web. By violating chart design principles, they distort data and lead readers to draw inaccurate conclusions. Pr...

Bias in medical artificial intelligence is conventionally viewed as a defect requiring elimination. However, human reasoning inherently incorporates biases shaped by education, culture, and experience...

Best-of-n sampling improves the accuracy of large language models (LLMs) and large reasoning models (LRMs) by generating multiple candidate solutions and selecting the one with the highest reward. The...

Planning with pretrained diffusion models has emerged as a promising approach for solving test-time guided control problems. However, standard gradient guidance typically performs optimally under conv...

We propose a realistic scenario for the unsupervised video learning where neither task boundaries nor labels are provided when learning a succession of tasks. We also provide a non-parametric learning...

Healthcare systems generate diverse multimodal data, including Electronic Health Records (EHR), clinical notes, and medical images. Effectively leveraging this data for clinical prediction is challeng...

Supervised fine-tuning (SFT) is a pivotal approach to adapting large language models (LLMs) for downstream tasks; however, performance often suffers from the ``seesaw phenomenon'', where indiscriminat...

Artificial intelligence (AI)-based computer perception (CP) technologies use mobile sensors to collect behavioral and physiological data for clinical decision-making. These tools can reshape how clini...

Accurate interpretation of clinical narratives is critical for patient care, but the complexity of these notes makes automation challenging. While Large Language Models (LLMs) show promise, single-mod...

As privacy regulations such as the GDPR and HIPAA and responsibility frameworks for artificial intelligence such as the AI Act gain traction, the ethical and responsible use of real-world data faces i...

Electrocardiogram (ECG) analysis is foundational for cardiovascular disease diagnosis, yet the performance of deep learning models is often constrained by limited access to annotated data. Self-superv...

Understanding the nuanced performance of machine learning models is essential for responsible deployment, especially in high-stakes domains like healthcare and finance. This paper introduces a novel f...

Diabetic Retinopathy (DR) is a major cause of global blindness, necessitating early and accurate diagnosis. While deep learning models have shown promise in DR detection, their black-box nature often ...

Extracting meaning from uncertain, noisy data is a fundamental problem across time series analysis, pattern recognition, and language modeling. This survey presents a unified mathematical framework th...

Generative video modeling has made significant strides, yet ensuring structural and temporal consistency over long sequences remains a challenge. Current methods predominantly rely on RGB signals, lea...

E-commerce platforms are rich in multimodal data, featuring a variety of images that depict product details. However, this raises an important question: do these images always enhance product understa...

This paper argues that a techno-philosophical reading of the EU AI Act provides insight into the long-term dynamics of data in AI systems, specifically, how the lifecycle from ingestion to deployment ...

Modeling feature interactions in tabular data remains a key challenge in predictive modeling, for example, as used for insurance pricing. This paper proposes the Tree-like Pairwise Interaction Network...

Effective modeling of heterogeneous subpopulations presents a significant challenge due to variations in individual characteristics and behaviors. This paper proposes a novel approach to address this ...

Artificial intelligence (AI)-based models are revolutionizing weather forecasting and have surpassed leading numerical weather prediction systems on various benchmark tasks. However, their ability to ...

Visual diffusion models achieve remarkable progress, yet they are typically trained at limited resolutions due to the lack of high-resolution data and constrained computation resources, hampering thei...

Accurate and efficient simulation of modern robots remains challenging due to their high degrees of freedom and intricate mechanisms. Neural simulators have emerged as a promising alternative to tradi...

We present several advances to the physics and equality constrained artificial neural networks (PECANN) framework that substantially improve its capability to learn solutions of canonical partial diff...

Modest statistical differences between the sampling performances of the D-Wave quantum annealer (QA) and the classical Markov Chain Monte Carlo (MCMC), when applied to Restricted Boltzmann Machines (R...

We present NiceWebRL, a research tool that enables researchers to use machine reinforcement learning (RL) environments for online human subject experiments. NiceWebRL is a Python library that allows a...

Commonsense validation evaluates whether a sentence aligns with everyday human understanding, a critical capability for developing robust natural language understanding systems. While substantial prog...

Watermarking has recently emerged as an effective strategy for detecting the generations of large language models (LLMs). The strength of a watermark typically depends strongly on the entropy afforded...

Reconstructing complete and interactive 3D scenes remains a fundamental challenge in computer vision and robotics, particularly due to persistent object occlusions and limited sensor coverage. Multivi...

Anatomic tracer studies are critical for validating and improving diffusion MRI (dMRI) tractography. However, large-scale analysis of data from such studies is hampered by the labor-intensive process ...

Programmable structures are systems whose undeformed geometries and material property distributions are deliberately designed to achieve prescribed deformed configurations under specific loading condi...

We propose a two-stage multimodal framework that enhances disease classification and region-aware radiology report generation from chest X-rays, leveraging the MIMIC-Eye dataset. In the first stage, w...

Developing large language models is expensive and involves making decisions with small experiments, typically by evaluating on large, multi-task evaluation suites. In this work, we analyze specific pr...

We present 4DNeX, the first feed-forward framework for generating 4D (i.e., dynamic 3D) scene representations from a single image. In contrast to existing methods that rely on computationally intensiv...

Thinking LLMs solve complex tasks at the expense of increased compute and overthinking on simpler problems, while non-thinking LLMs are faster and cheaper but underthink on harder reasoning problems. ...

Calibration requires that predictions are conditionally unbiased and, therefore, reliably interpretable as probabilities. Calibration measures quantify how far a predictor is from perfect calibration....

Foundational modelling of multi-dimensional time-series data in industrial systems presents a central trade-off: channel-dependent (CD) models capture specific cross-variable dynamics but lack robustn...

In classical AI, perception relies on learning state-based representations, while planning, which can be thought of as temporal reasoning over action sequences, is typically achieved through search. W...

Mobile manipulation in dynamic environments is challenging due to movable obstacles blocking the robot's path. Traditional methods, which treat navigation and manipulation as separate tasks, often fai...

This work introduces an automated testing approach that employs agents controlling game characters to detect potential bugs within a game level. Harnessing the power of Bayesian Optimization (BO) to e...

Diffusion language models, as a promising alternative to traditional autoregressive (AR) models, enable faster generation and richer conditioning on bidirectional context. However, they suffer from a ...

Multi-modal models have achieved remarkable progress in recent years. Nevertheless, they continue to exhibit notable limitations in spatial understanding and reasoning, which are fundamental capabilit...

Cone-beam computed tomography (CBCT) has become an invaluable imaging modality in dentistry, enabling 3D visualization of teeth and surrounding structures for diagnosis and treatment planning. Automat...

This work studies the challenge of transfer animations between characters whose skeletal topologies differ substantially. While many techniques have advanced retargeting techniques in decades, transfe...

Being able to effectively read scientific plots, or chart understanding, is a central part toward building effective agents for science. However, existing multimodal large language models (MLLMs), esp...

We introduce the multivariate fields of experts, a new framework for the learning of image priors. Our model generalizes existing fields of experts methods by incorporating multivariate potential func...

Humans communicate with increasing efficiency in multi-turn interactions, by adapting their language and forming ad-hoc conventions. In contrast, prior work shows that LLMs do not naturally show this ...

Recent approaches for 3D relighting have shown promise in integrating 2D image relighting generative priors to alter the appearance of a 3D representation while preserving the underlying structure. Ne...

Urbanization, climate change, and agricultural stress are increasing the demand for precise and timely environmental monitoring. Land Surface Temperature (LST) is a key variable in this context and is...

Segmentation of lesions on CT enables automatic measurement for clinical assessment of chronic diseases (e.g., lymphoma). Integrating large language models (LLMs) into the lesion segmentation workflow...

Blockchain-enabled federated learning (BCFL) addresses fundamental challenges of trust, privacy, and coordination in collaborative AI systems. This chapter provides comprehensive architectural analysi...

Achieving precise control over a molecule's biological activity-encompassing targeted activation/inhibition, cooperative multi-target modulation, and off-target toxicity mitigation-remains a critical ...

Haptic captioning is the task of generating natural language descriptions from haptic signals, such as vibrations, for use in virtual reality, accessibility, and rehabilitation applications. While pre...

We present GLM-4.5, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters, featuring a hybrid reasoning method that supports both thinkin...