Knowledge catalogue
arXiv:2502.04554v2 Announce Type: replace Abstract: Data selection has emerged as a crucial downstream application of data valuation, yet the theoretical foundations for using data values in selection
arXiv:2510.15710v3 Announce Type: replace Abstract: Medical workflows routinely combine reading images with producing visual and textual outputs, making both image understanding and generation central
arXiv:2605.30694v1 Announce Type: new Abstract: Many theories of decision making -- planning, reinforcement learning, causal intervention, online learning, and game-theoretic equilibrium -- turn local
arXiv:2605.30479v1 Announce Type: new Abstract: We consider the problem of universal transductive online classification with a possibly unbounded label space. This setting considers online learning, w
arXiv:2605.30825v1 Announce Type: cross Abstract: Unlearning in diffusion models aims to remove undesirable data or concepts while preserving the utility of pretrained models -- two fundamentally conf
arXiv:2506.01318v4 Announce Type: replace-cross Abstract: Machine unlearning (MU) aims to expunge a designated forget set from a trained model without costly retraining, yet the existing techniques ov
arXiv:2605.31378v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) still struggle with fine-grained translation quality estimation (QE), even with long reasoning chains. We argue that LRMs
arXiv:2605.30920v1 Announce Type: new Abstract: Diffusion-based neural solvers have shown strong promise for combinatorial optimization (CO), but existing methods typically rely on supervised training
arXiv:2605.30370v1 Announce Type: cross Abstract: From their inception in the 1950s, artificial neural networks (ANNs) started using the so-called point neuron model then prevalent in neuroscience, ho
arXiv:2510.09364v2 Announce Type: replace Abstract: 3D Gaussian splatting (3DGS) has demonstrated impressive performance in synthesizing high-fidelity novel views. Nonetheless, its effectiveness criti
arXiv:2602.03639v2 Announce Type: replace Abstract: Sampling-based controllers, such as Model Predictive Path Integral (MPPI) methods, offer substantial flexibility but often suffer from high variance
arXiv:2508.20478v2 Announce Type: replace Abstract: Long-form video understanding, characterized by long-range temporal dependencies and multiple events, remains a challenge. Existing methods often re
arXiv:2512.11561v2 Announce Type: replace Abstract: Generalizing pretrained models to unseen datasets without retraining is a central challenge toward foundation models. Achieving fully inductive infe
arXiv:2605.30561v1 Announce Type: cross Abstract: Vision Language Models (VLMs) enable a unified model to solve various vision tasks through prompting. They have shown promising performance in semanti
arXiv:2605.31466v1 Announce Type: new Abstract: Reconstructing the complete geometry of a scene from a single RGB image remains challenging - especially when inferring hidden structures where visual e
arXiv:2605.31346v1 Announce Type: cross Abstract: Zeroth-order (black-box) optimization is applied when gradients are unavailable and objective evaluations rely on expensive simulations. In many such
arXiv:2601.05770v3 Announce Type: replace-cross Abstract: Algorithm extraction aims to synthesize executable programs directly from models trained on algorithmic tasks, enabling de novo recovery of ex
arXiv:2602.10286v2 Announce Type: replace Abstract: Pairwise preference learning is central to machine learning, with recent applications in aligning language models with human preferences. A typical
arXiv:2605.31564v1 Announce Type: cross Abstract: We present the first systematic study of masked diffusion language models (MDLMs) for graph-to-text generation. We analyze MDLM generation trajectorie
arXiv:2603.09787v2 Announce Type: replace Abstract: Explainable artificial intelligence (XAI) aims to provide human-interpretable insights into the behavior of deep neural networks (DNNs), typically b
arXiv:2605.31504v1 Announce Type: new Abstract: Multimodal models in oncology can produce accurate predictions, but accurate prediction does not reveal whether the model has learned biology that is sh
arXiv:2601.20774v2 Announce Type: replace Abstract: Multitask learning and related frameworks have achieved tremendous success in modern applications. In multitask learning problem, we are given a set
arXiv:2605.31281v1 Announce Type: new Abstract: As wind turbine fleets age, data-driven reliability engineering is essential to optimise their operation and maintenance for service life extension and
arXiv:2605.30362v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) hold promise for demonstrating superior learning and representation capabilities in deep models. Given the tremendous s
arXiv:2605.30573v1 Announce Type: new Abstract: Sampling from high-dimensional, non-log-concave distributions with unnormalized densities remains a fundamental challenge in machine learning, particula
Yann LeCun comments on the 'Magnificent 7' tech companies (likely referring to the largest AI and tech stocks like Apple, Microsoft, Google, etc.), suggesting that one of these prominent companies doe
This has quietly been a miracle month in medicine. In the last 5 weeks we’ve got news on: - retatrutide, the triple agonist GLP-1 from Lilly, basically melting fat and body-wide inflammation at record
Trump’s “little excursion to Iran” is 'universally perceived as a defeat. Almost regardless of the outcome – most likely a return to the…status quo – the war looks ill-conceived, a monument to confuse
Reviews and discussions for all accepted papers at ICML are made public on OpenReview after the reviewing period concludes. Authors of rejected papers may also opt-in to have their reviews and discuss
Bill Gurley: Anthropic Thinks It’s Building God @Jason: It is the ultimate level of narcissism and delusion of grandeur to think you can create God. @bgurley: “Anthropic is a mystery to me. I've never
Exxon Says We’re Two Weeks From Petrol Armageddon Right. So it turns out closing the world’s most important oil chokepoint has consequences. Who knew. Exxon’s Senior VP Neil Chapman stood up at a Bern
In my Harvard fellowship I study the views of AI accelerationists, safetyists and skeptics. What I have come to realize is that both the Accelerationists and the Safetyists believe that we are creatin
Francois Chollet's post likely expresses a philosophical perspective on existential risk or civilizational decline, suggesting that humanity's downfall would be precipitated by a loss of human values,
arXiv:2605.29416v1 Announce Type: cross Abstract: Vision-Language-Action models have achieved remarkable progress in robotic manipulation, yet they suffer from a critical limitation: a lack of 3D scen
arXiv:2602.03890v2 Announce Type: replace Abstract: Point clouds provide a compact and expressive representation of 3D objects, and have recently been integrated into multimodal large language models
arXiv:2506.20344v3 Announce Type: replace-cross Abstract: Despite its wide range of applications across various domains, the optimization foundations of deep matrix factorization (DMF) remain largely
arXiv:2502.16548v3 Announce Type: replace-cross Abstract: Objective. Heart failure is one of the leading causes of death worldwide, with millions of deaths each year, according to data from the World
arXiv:2605.29088v1 Announce Type: new Abstract: Synthetic Aperture Radar (SAR) imagery enables all-weather, day-and-night Earth observation; however, it remains difficult to interpret due to speckle n
arXiv:2602.11171v2 Announce Type: replace-cross Abstract: Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) offers a resource-efficient way to personalize or specialize. However
arXiv:2511.08548v2 Announce Type: replace Abstract: The evolution of mathematics is shaped importantly by interestingness: researchers choose which problems to pursue, and students choose which proble
arXiv:2605.29698v1 Announce Type: new Abstract: Machine learning for molecular property prediction has focused largely on pure compounds, even though many practical applications depend on mixtures wit
arXiv:2605.29753v1 Announce Type: cross Abstract: Dual-energy CT (DECT) enables virtual monochromatic imaging (VMI) and improved contrast resolution, but its clinical adoption is limited by hardware c
arXiv:2605.29986v1 Announce Type: new Abstract: To guarantee that an LLM's outputs conform to a specified structure, context-free grammar (CFG) decoding engines force the selection of next tokens that
arXiv:2602.03357v2 Announce Type: replace Abstract: This paper proposes FedNMap, a normal map-based method for composite federated learning, where the objective consists of a smooth loss and a possibl
arXiv:2605.30198v1 Announce Type: new Abstract: Always-on edge systems must keep learning as conditions change under tight compute budgets and must detect unreliable predictions. Bayesian binary neura
arXiv:2601.14855v3 Announce Type: replace Abstract: Black-box variational inference (BBVI) with Gaussian mixture families offers a flexible approach for approximating complex posterior distributions w
arXiv:2605.30080v1 Announce Type: new Abstract: Tokenization-free hierarchical models are emerging as a promising alternative to traditional Large Language Models (LLMs), addressing inherent preproces
arXiv:2605.30349v1 Announce Type: new Abstract: Autoregressive video diffusion models generate streaming video by producing frames sequentially, conditioning each chunk on previously generated content
arXiv:2602.11760v2 Announce Type: replace-cross Abstract: Feature-importance methods show promise in transforming machine learning models from predictive engines into tools for scientific discovery. H
arXiv:2605.30250v1 Announce Type: new Abstract: Inverse rendering aims to reconstruct geometry and reflectance of objects from images. Despite recent progress, existing methods often produces inaccura
arXiv:2511.10861v3 Announce Type: replace-cross Abstract: Convolutional Neural Networks (CNNs) pre-trained on large-scale datasets such as ImageNet are widely used as feature extractors to construct h
arXiv:2605.29064v1 Announce Type: new Abstract: We study how persona prompting shapes language generated by multimodal large language models in an urban perception setting. Using 59,808 annotations fr
arXiv:2605.30150v1 Announce Type: new Abstract: LLMs are increasingly used to generate candidate-idea pools for creative tasks where broad exploration is valuable. Parallel inference can be attractive
arXiv:2605.30229v1 Announce Type: new Abstract: We use a mean-field-based transformer model to theoretically investigate how auxiliary variables, such as positional encoding, prevent mode collapse of
arXiv:2605.29488v1 Announce Type: cross Abstract: Conditional human motion generation remains a fundamental challenge in computer vision and robotics. Despite significant progress, current methods are
arXiv:2508.03253v2 Announce Type: replace-cross Abstract: We study the online fair division problem, where indivisible goods arrive sequentially and must be allocated immediately and irrevocably. Prio
arXiv:2605.30311v1 Announce Type: cross Abstract: Digital humans are fundamental to immersive interaction, yet creating a unified model for holistic modalities, including text, audio, motion, and visu
arXiv:2510.04704v4 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown promising potential in scientific research, enabling tasks ranging from knowledge retrieval to propert
arXiv:2605.29351v1 Announce Type: new Abstract: We study minimal attention-only transformers under all-token corruption and show they admit a two-stage empirical Bayes interpretation. A single attenti
arXiv:2510.27663v3 Announce Type: replace-cross Abstract: Modern imaging techniques heavily rely on Bayesian statistical models to address difficult image reconstruction and restoration tasks. This pa