Mirror Mean-Field Langevin Dynamics
arXiv:2505.02621v2 Announce Type: replace Abstract: The mean-field Langevin dynamics (MFLD) minimizes an entropy-regularized nonlinear convex functional on the Wasserstein space over R^d, and has gain
Knowledge catalogue
arXiv:2505.02621v2 Announce Type: replace Abstract: The mean-field Langevin dynamics (MFLD) minimizes an entropy-regularized nonlinear convex functional on the Wasserstein space over R^d, and has gain
arXiv:2507.06384v2 Announce Type: replace-cross Abstract: Objective: Latent diffusion models (LDMs) could mitigate data scarcity challenges affecting machine learning development for medical image int
arXiv:2402.15058v3 Announce Type: replace-cross Abstract: We combine standard persistent homology with image persistent homology to define a novel way of characterizing shapes and interactions between
arXiv:2605.17635v1 Announce Type: cross Abstract: A fast simulation of the detector response is a vital task in high-energy physics (HEP). Traditional Monte-Carlo methods form the backbone of modern p
arXiv:2603.19538v2 Announce Type: replace Abstract: Monocular 3D object understanding has largely been cast as a 2D RoI-to-3D box lifting problem. However, emerging downstream applications require ima
arXiv:2605.18483v1 Announce Type: cross Abstract: Time series classification (TSC) of biological signals has progressed from handcrafted, modality-specific approaches to deep architectures capable of
arXiv:2605.16480v1 Announce Type: cross Abstract: Molecules are graphs, but large language models~(LLMs) are usually asked to reason about them through linear strings. The most popular molecular repre
arXiv:2605.17252v1 Announce Type: new Abstract: Stereoscopic 3D displays adopt a binocular depth cue to provide depth perception. However, users should be equipped with expensive special devices to ap
arXiv:2605.16932v1 Announce Type: new Abstract: Robots deployed in unstructured human environments must frequently execute long-horizon missions, such as find the mug, then the chair, then the printer
arXiv:2502.05462v2 Announce Type: replace Abstract: We propose a real-time implementable motion planning framework for cooperative object transportation by nonholonomic mobile manipulator robots (MMRs
arXiv:2605.16456v1 Announce Type: new Abstract: Understanding how objects relate to each other in space is fundamental to scene understanding, yet most contrastive pre-training approaches only model p
arXiv:2604.00919v2 Announce Type: replace-cross Abstract: Energy-based models provide a natural bridge between statistical physics and machine learning by representing data through structured energy l
arXiv:2605.17624v1 Announce Type: cross Abstract: We investigate the potential of invariant and equivariant semi-supervised learning for addressing the challenges of training multi-task models on part
arXiv:2605.16384v1 Announce Type: cross Abstract: Accurate and effective discrete image tokenization is crucial for long image sequence processing. However, current methods rigidly compress all conten
arXiv:2605.17761v1 Announce Type: cross Abstract: Insider threats often reveal early anomalies through disruptions in behavioral statistics-such as altered recurrence patterns or short-versus long-ter
arXiv:2505.11143v2 Announce Type: replace-cross Abstract: Sparse linear regression is a fundamental tool in data analysis. However, traditional approaches often fall short when covariates exhibit stru
arXiv:2502.20349v3 Announce Type: replace-cross Abstract: How can cognitive science build generalizable theories that span the full scope of natural situations and behaviors? We argue that progress in
arXiv:2510.16814v2 Announce Type: replace-cross Abstract: Archaeological predictive modelling estimates where undiscovered sites are likely to occur by combining known locations with environmental, cu
arXiv:2605.16414v1 Announce Type: new Abstract: We present NERVE (Neuromorphic Vision and Radar Ensemble), a multi-sensor dataset comprising 257 minutes of synchronized recordings from five sensors: t
arXiv:2605.16805v1 Announce Type: new Abstract: LiDARs are widely used for 3D depth reconstruction, but their performance is often limited by inherent hardware constraints that impose trade-offs betwe
arXiv:2510.13068v4 Announce Type: replace-cross Abstract: Biosignals such as electroencephalography (EEG), electrocardiography (ECG), and electromyography (EMG) encode physiological activity across mu
arXiv:2605.18035v1 Announce Type: new Abstract: Hard-thresholding is an important type of algorithm in machine learning that is used to solve ell_0 constrained optimization problems. However, the true
arXiv:2605.16893v1 Announce Type: new Abstract: Recent studies introduce conditional memory modules that decouple knowledge storage from neural computation, enabling more direct knowledge access. Comp
arXiv:2605.16514v1 Announce Type: cross Abstract: Understanding why some sequential planning problems are harder than others requires models that go beyond average performance. They should capture the
arXiv:2605.17390v1 Announce Type: cross Abstract: Context. Metamorphic Testing is recognised in IEEE/ISO software-testing standards and increasingly recommended for AI systems, but its progress is bot
arXiv:2605.18238v1 Announce Type: new Abstract: Digital entities such as AI agents and humanoid robots increasingly operate alongside real humans, yet their identity infrastructure is based on credent
arXiv:2605.16423v1 Announce Type: new Abstract: Network quantization has emerged as one of the most practical model compression techniques, which significantly reduces a model's memory and compute con
arXiv:2605.17340v1 Announce Type: new Abstract: Time series foundation models rely on large-scale pretraining over diverse datasets across domains, yet their heterogeneity in temporal patterns could h
arXiv:2605.17488v1 Announce Type: new Abstract: The landscape of joint audio and video generation has been fundamentally transformed by the advent of powerful foundation models. Despite these strides,
arXiv:2605.18041v1 Announce Type: new Abstract: Omnimodal large language models (OmniLLMs) have recently gained increasing attention for unified audio-video understanding. However, processing long mul
arXiv:2605.16998v1 Announce Type: cross Abstract: The Quantum Fourier Transform (QFT) is required by hidden subgroup problem (HSP) algorithms, including Shor's algorithm for factoring. The circuit dep
arXiv:2605.17483v1 Announce Type: new Abstract: Facial Expression Recognition faces two core challenges. The first is class imbalance in public datasets, which skews the learning process and weakens g
arXiv:2605.17678v1 Announce Type: cross Abstract: In this paper, we derive rates of convergence in the high-dimensional central limit theorem for Polyak--Ruppert averaged iterates generated by entropy
arXiv:2605.18370v1 Announce Type: cross Abstract: We study sample quantiles of distributions indexed by estimated parameters, with a on Value-at-Risk related to linear projections of financial returns
arXiv:2512.12572v2 Announce Type: replace Abstract: Data attribution aims to explain model predictions by estimating how they would change if certain training points were removed, and is used in a wid
arXiv:2605.17705v1 Announce Type: cross Abstract: Panel data, in which multiple units are repeatedly observed over time, arise throughout science and engineering. Quantifying predictive uncertainty in
arXiv:2605.06088v2 Announce Type: replace Abstract: Understanding open-vocabulary 3D scenes with Gaussian-based representations remains challenging due to fragmented and spatially inconsistent semanti
arXiv:2605.17800v1 Announce Type: cross Abstract: Rearranging densely packed tabletop objects is challenging when parallel-gripper picks are infeasible without sufficient clearance around an object. T
arXiv:2605.17197v1 Announce Type: cross Abstract: Post-disaster damage assessment requires rapid and accurate semantic segmentation of 3D point clouds to identify critical infrastructure such as damag
arXiv:2605.16341v1 Announce Type: new Abstract: Low-rank gradient compression reduces communication in distributed training by representing updates with rank-r factors. Dion is a recent method that ap
arXiv:2605.16421v1 Announce Type: cross Abstract: We present a new algorithm for deciding formula entailment in orthologic (a sound approximation of classical logic) that avoids the costly preprocessi
arXiv:2605.17757v1 Announce Type: cross Abstract: INT2 KV-cache quantization is attractive for long-context LLM serving, but it remains difficult to make both accurate and deployable. Simple rotations
arXiv:2605.17916v1 Announce Type: new Abstract: Generating a consistent whole-house VR tour from a floorplan and style reference requires both photorealistic panoramas and cross-view spatial coherence
arXiv:2605.17108v1 Announce Type: new Abstract: Transformers have become the dominant architecture for sequence modeling by using self-attention to enable expressive and highly parallel processing. Ho
arXiv:2601.09495v3 Announce Type: replace Abstract: With the emergence of massively parallel processing units, parallelization has become a desirable property for new sequence models. The ability to p
arXiv:2509.22849v2 Announce Type: replace-cross Abstract: Neural networks with ReLU activations are a widely used model in machine learning. It is thus important to have a profound understanding of th
arXiv:2605.17719v1 Announce Type: new Abstract: CNN- and Transformer-based architectures have achieved strong performance in medical image segmentation, but CNNs are limited in modeling long-range dep
arXiv:2605.16266v1 Announce Type: cross Abstract: We introduce Patchwork, a new general-purpose shape representation capable of modeling 2D and 3D geometry with a small number of parameters. Patchwork
arXiv:2602.11553v2 Announce Type: replace-cross Abstract: Image denoising aims to remove noise while preserving structural details and perceptual realism, yet distortion-driven methods often produce o
arXiv:2605.17555v1 Announce Type: cross Abstract: Current topology aware diffusion models face an architectural mismatch by using Gaussian noise for corruption while recovering structural features thr
arXiv:2605.16451v1 Announce Type: cross Abstract: Macro placement is a pivotal stage in VLSI physical design, fundamentally determining the overall chip performance. Recent data-driven placement metho
arXiv:2605.18199v1 Announce Type: cross Abstract: The rapid growth of tabular datasets in data lakes, data spaces, and open data portals makes effective dataset search essential for reuse and analysis
arXiv:2605.18735v1 Announce Type: new Abstract: We present PIXLRelight, a feed-forward approach for physically controllable single-image relighting. Existing methods either provide limited lighting co
arXiv:2605.18632v1 Announce Type: cross Abstract: Neural network checkpoints have quietly become a large-scale data resource: millions of trained weight vectors now exist, each encoding task-, domain-
arXiv:2510.10777v3 Announce Type: replace Abstract: Optimization lies at the core of modern deep learning, yet existing methods often face a fundamental trade-off between adapting to problem geometry
arXiv:2605.17989v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) improves factual grounding in large language models but suffers from substantial latency due to synchronous retri
arXiv:2605.16339v1 Announce Type: new Abstract: Preference learning in large language models relies on reward models as proxies for human judgment. However, these models frequently exhibit preference
arXiv:2605.16861v1 Announce Type: cross Abstract: Block Diffusion Models (BDMs) support parallel generation, flexible-length output, and KV caching, making them promising for efficient document parsin
arXiv:2605.17125v1 Announce Type: new Abstract: Optical navigation is a critical component for lunar orbiter and lander missions. Image-based crater identification has emerged as a promising technolog
arXiv:2605.16747v1 Announce Type: new Abstract: We develop a quantitative statistical theory of transformers in the large-context regime by adopting the abstraction of contextual flow maps (CFMs): dyn