Search: “research”

Which LoRA? An Empirical Study on the Effectiveness of LoRA Techniques During Multilingual Instruction Tuning

arXiv:2606.10428v1 Announce Type: new Abstract: We investigate whether commonly available LoRA variants have an advantage over basic LoRA in multilingual instruction tuning. Experiments involving LoRA

researcharxiv-cs-cl

Research

Whisfusion: Parallel ASR Decoding with Masked Diffusion

DGX agent

arXiv:2508.07048v2 Announce Type: replace-cross Abstract: Autoregressive (AR) encoder-decoder models dominate high-quality multilingual ASR, but their left-to-right decoders make inference latency sca

researcharxiv-cs-ai

10 Jun 2026

Whisper-GPT -- Continuous Discrete Hybrid Representation Language Models For Speech And Music

arXiv:2412.11449v2 Announce Type: replace-cross Abstract: We propose WHISPER-GPT: A generative large language model (LLM) for speech and music that allows us to work with continuous audio representati

Who Wrote the Book? Detecting and Attributing LLM Ghostwriters

arXiv:2603.28054v2 Announce Type: replace Abstract: In this paper, we introduce GhostWriteBench, a dataset for LLM authorship attribution. It comprises long-form texts (50K+ words per book) generated

researcharxiv-cs-cl

WorldKernel: A World Model is the Coupling Kernel of Admissible Possible Worlds

arXiv:2606.10934v1 Announce Type: new Abstract: A common assumption holds that enough observational and interventional data, given to a strong enough predictor, suffices. We report a failure mode that

WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling

arXiv:2512.14614v2 Announce Type: replace Abstract: This paper presents WorldPlay, a streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consist

ZODS-RS -- Zero-training Oriented Detection & Segmentation for Remote Sensing

arXiv:2606.10769v1 Announce Type: new Abstract: Remote-sensing and UAV applications need models that generalize across platforms and viewpoints without task-specific training. Yet training-free pipeli

3D Oral Modelling with Improved Vertex Distribution Using Matching-Based Learning

arXiv:2606.07907v1 Announce Type: cross Abstract: In our previous work, a deep learning-based framework for 3D intraoral reconstruction was proposed. The model directly predicts explicit 3D point clou

A Geometric Measure of Linear Separability for Neural Representations

arXiv:2606.08721v1 Announce Type: new Abstract: Modern neural classifiers commonly rely on linear readouts, yet predictive metrics alone do not characterize the class-wise geometry of the representati

A Geometric Theory of Cognition for Machine Intelligence

arXiv:2512.12225v3 Announce Type: replace Abstract: Developing artificial agents that unify representation, memory, adaptation, and prediction remains a fundamental challenge in artificial intelligenc

A Graphop Analysis of Graph Neural Networks on Sparse Graphs: Generalization and Universal Approximation

arXiv:2602.08785v2 Announce Type: replace Abstract: Generalization and approximation capabilities of message passing graph neural networks (MPNNs) are often studied by defining a compact metric on a s

A Hierarchical Feature Engineering Framework for Automated Classification of Phonotraumatic and Non-Phonotraumatic Vocal Hyperfunction

arXiv:2606.07673v1 Announce Type: cross Abstract: Ambulatory neck-surface acceleration enables non-invasive monitoring of vocal hyperfunction, yet robust biomarkers for its subtypes remain limited. Th

A large-scale nanocrystal database with aligned synthesis and properties enabling generative inverse design

arXiv:2601.02424v2 Announce Type: replace-cross Abstract: The synthesis of nanocrystals has been highly dependent on trial-and-error, due to the complex correlation between synthesis parameters and ph

A Machine Learning-Enhanced Hopf-Cole Formulation for Nonlinear Gas Flow in Porous Media

arXiv:2603.11250v2 Announce Type: replace-cross Abstract: Accurate modeling of gas flow through porous media is critical for many technological applications, including reservoir performance prediction

A Regret Minimization Framework on Preference Learning in Large Language Models

arXiv:2606.09124v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has enabled progress on reasoning-intensive tasks by relying on task-specific verifiers that provi

A Robust widetilde{O}(1/sqrt{T}) Rate for Unprojected TD Learning with Linear Function Approximation

arXiv:2506.01052v3 Announce Type: replace Abstract: We investigate the finite-time convergence properties of Temporal Difference (TD) learning with linear function approximation, a cornerstone of rein

A spectral audit framework reveals task-dependent aperiodic reliance across EEG and ECG deep learning

arXiv:2606.08583v1 Announce Type: new Abstract: Deep learning on physiological time series is interpreted through domain-specific features -- oscillatory rhythms in EEG, morphological complexes in ECG

A Theoretical Analysis of Memory and Overfitting Phenomena in Stochastic Interpolation Models

arXiv:2606.08554v1 Announce Type: new Abstract: This paper provides a theoretical account of memorization in stochastic interpolation models. By leveraging closed-form expressions for the optimal velo

A Unifying View of Attention Sinks: Two Algorithms, Two Solutions

arXiv:2606.08105v1 Announce Type: new Abstract: When attention concentrates on a single token, a sink, what is the model actually computing? Attention sinks are ubiquitous in softmax transformers, yet

A Variability-Based Framework for Interpretable Naming in Formal and Relational Concept Analysis

arXiv:2606.08477v1 Announce Type: new Abstract: Knowledge extraction from symbolic data often produces abstractions that are formally defined but not immediately interpretable by users. Formal Concept

AccioScene: Compositional 3D Scene Generation via Graph Diffusion and Interaction-driven Critics

arXiv:2502.06819v2 Announce Type: replace Abstract: This paper presents a framework for generating 3D indoor scenes from text prompts. Existing methods often formulate scene synthesis as an object lay

Advancements in Machine Learning and Deep Learning for Early Detection and Management of Mental Health Disorder

arXiv:2412.06147v2 Announce Type: replace Abstract: For the early identification, diagnosis, and treatment of mental health illnesses, the integration of deep learning (DL) and machine learning (ML) h

Adversarial Instance Generation and Robust Training for Neural Combinatorial Optimization with Multiple Objectives

arXiv:2601.01665v2 Announce Type: replace-cross Abstract: Deep reinforcement learning (DRL) has shown great promise in addressing multi-objective combinatorial optimization problems (MOCOPs). Neverthe

Airport Terminal Passenger Queue Forecasting for Departure Gates and Security Checkpoints

arXiv:2606.07622v1 Announce Type: new Abstract: Accurate passenger queue forecasting in airport terminals is essential for efficient departure operations, as it enables proactive congestion management

Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regret

arXiv:2606.09668v1 Announce Type: new Abstract: Contextual queueing bandits provide a framework for learning to schedule heterogeneous jobs under unknown context-dependent service rates. Under stochas

All-in-One Augmented Reality Guided Head and Neck Tumor Resection

arXiv:2603.29495v2 Announce Type: replace Abstract: Positive margins are common in head and neck squamous cell carcinoma, yet intraoperative re-resection is often imprecise because margin locations ar

Always back to the basics: LatentMoE was probably inspired by MLA, which was inspired by LoRA, which was inspired by SVD, which was inspired…

researchsebastian-raschka--x

This post traces the historical lineage of machine learning techniques, suggesting that LatentMoE builds upon a chain of progressively developed methods including MLA, LoRA, and SVD, emphasizing how m

An Effective Router for Vision-Language Model Selection

arXiv:2606.08970v1 Announce Type: new Abstract: Vision-language models (VLMs) with varying performance and resource requirements are widely deployed, making it difficult for users to select the most a

An Enhanced Geometric-Spectral Feature Learning Framework for Airborne Multispectral Point Cloud Classification

arXiv:2606.09123v1 Announce Type: cross Abstract: Multispectral point cloud (MPC) is composed of 3D spatial-spectral information, which holds tremendous potential for accurate land-cover classificatio

An Interval Branch-and-Bound-Based Inverse Kinemetics Algorithm Towards Global Optimal Redundancy Resolution

arXiv:2104.12183v2 Announce Type: replace Abstract: The general inverse kinematics (IK) problem of a manipulator, namely that of acquiring the self-motion manifold (SMM) of all admissible joint angles

researcharxiv-cs-ro

An Opticalmechanics Framework for Dynamic Estimation of Multibody Systems

arXiv:2606.09383v1 Announce Type: new Abstract: Conventional dynamics analysis of the human body is often constrained by the need for contact force and torque sensors and controlled laboratory environ

Aperon Technical Report: Hierarchical No-Pointer Tangent-Local Search for High-Dimensional Approximate Nearest Neighbors

arXiv:2606.08813v1 Announce Type: cross Abstract: We present HNTL (Hierarchical No-pointer Tangent-Local), the core vector indexing and candidate generation framework of the Aperon vector memory syste

AQIFormer: A Transformer-Based Multi-View Architecture for Cross-City Air Quality Classification

arXiv:2606.07648v1 Announce Type: cross Abstract: Air pollution represents one of the most critical environmental and public health challenges globally, with traditional sensor-based monitoring system

Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscape

arXiv:2403.06013v2 Announce Type: replace-cross Abstract: This paper delves into the critical area of deep learning robustness, challenging the conventional belief that classification robustness and e

Are Two Datasets Close Enough With Statistical Significance? A Kernel Distributional Closeness Testing Approach

arXiv:2507.12843v3 Announce Type: replace Abstract: Are two distributions close to each other with statistical significance? Distribution closeness testing (DCT) formalizes this question by testing wh

Model Releases

ArtiFact: A Large-Scale Multi-Modal Cultural Heritage Dataset

model-releasesarxiv-cs-ai

arXiv:2606.09648v1 Announce Type: cross Abstract: Multi-modal data management has emerged as a central research topic in the database community, spanning data integration, semantic query processing, a

Assessing Sample Quality in Conditional Generation under Compositional Shift

arXiv:2606.09601v1 Announce Type: new Abstract: Conditional generators provide a natural tool for controllable generation, including settings where the desired condition is a new composition of observ

Astro, I'm Home! Investigating Factors that Influence the Acceptance of Home Robots Using Supervised Machine Learning

arXiv:2606.07551v1 Announce Type: cross Abstract: The use of social robots in home environments is on the rise. This exploratory study applies regularization techniques (e.g., Lasso and Ridge regressi

researcharxiv-cs-ro

Asymptotic Optimality of Thompson Sampling for Risk-Averse Bandits with Sub-Gaussian Rewards

arXiv:2606.09191v1 Announce Type: new Abstract: We prove that rhoext{-}NPTS_{SG}, an anchor-free nonparametric Thompson Sampling algorithm for risk-averse bandits, achieves regret matching the instanc

ATM: Action-Consistency Transfer Matrix for Diagnosing and Improving Latent World Models

arXiv:2606.09028v1 Announce Type: cross Abstract: Latent world models are increasingly used for control and goal-conditioned planning, yet assessing whether their learned representations are useful fo

Attention at the Theoretical Minimum: A Mathematics of Arrays Framework for Memory-Optimal Transformer Kernels

arXiv:2606.07713v1 Announce Type: cross Abstract: The attention mechanism is the dominant computational bottleneck in modern transformer-based AI. Its standard implementation incurs quadratic memory t

AttentionCap: Transformer Based Capacitance Matrix Learning Toward Full-Chip Extraction

arXiv:2606.08161v1 Announce Type: new Abstract: As capacitance extraction accuracy of rule-based pattern matching becomes difficult to sustain at advanced nodes, a growing trend emerges to develop dee

AUCp: Pseudo-AUC for Inference Model Selection with Unlabeled Validation Data in Abnormality Detection

arXiv:2606.08742v1 Announce Type: new Abstract: Abnormality detection is a crucial yet challenging task in medical image analysis. Distinguishing abnormalities from normal data by learning to reconstr

Audio-FLAN: An Instruction-Following Dataset for Unified Audio Understanding and Generation of Speech, Music, and Sound

arXiv:2502.16584v2 Announce Type: replace-cross Abstract: Recent advancements in audio tokenization have significantly enhanced the integration of audio capabilities into large language models (LLMs).

Automating the Expert Eye: A System-Agnostic Deep Learning Framework for Rare Event Discovery in Imbalanced Force Spectroscopy

arXiv:2606.09541v1 Announce Type: cross Abstract: Single-Molecule Force Spectroscopy (SMFS) provides unprecedented insights into biomolecular mechanics, yet the high-throughput generation of force-ext

Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection

arXiv:2603.21511v2 Announce Type: replace Abstract: Zero-shot (ZS) 3D anomaly detection is crucial for reliable industrial inspection, as it enables detecting and localizing defects without requiring

Backward Coherence and Hidden-State Stability in Recurrent Neural Networks: A Quasi-Reverse-Martingale Theory

arXiv:2606.08934v1 Announce Type: new Abstract: Recurrent neural networks maintain a hidden state h_t, but its probabilistic meaning is often unclear. We study hidden-state stability through backward

Balancing Real and Synthetic Data for CNN-based Masonry Crack Detection

arXiv:2606.08033v1 Announce Type: new Abstract: Cracks are a critical indicator of building health, and early stage identification is fundamental to prevent harmful damages. Advances in deep learning