Search: “research”

Motion-Robust Deep Reconstruction for Free-Breathing Cardiac Cine MRI

arXiv:2605.20687v1 Announce Type: cross Abstract: Conventional cardiac cine MRI relies on breath-hold Cartesian acquisitions, which are vulnerable to motion artifacts and can be uncomfortable or infea

Multi-Channel Replay Speech Detection using Acoustic Maps

DGX agent

arXiv:2602.16399v2 Announce Type: replace-cross Abstract: Replay attacks remain a critical vulnerability for automatic speaker verification systems, particularly in real-time voice assistant applicati

researcharxiv-cs-lg

21 May 2026

Musical Attention Transformer: Music Generation Using a Music-Specific Attention Model

arXiv:2605.21081v1 Announce Type: cross Abstract: This study aims to enhance the quality of music generation using Transformers by incorporating meta-information. While Transformer-based approaches ar

NeighborDiv: Training-free Zero-shot Generalist Graph Anomaly Detection via Neighbor Diversity

arXiv:2605.20879v1 Announce Type: new Abstract: Graph Anomaly Detection (GAD) is increasingly shifting to Generalist GAD (GGAD) for cross-domain 'one-for-all' detection, but existing GGAD methods pred

Neural Estimation of Pairwise Mutual Information in Masked Discrete Sequence Models

arXiv:2605.20187v1 Announce Type: new Abstract: Understanding dependencies between variables is critical for interpretability and efficient generation in masked diffusion models (MDMs), yet these mode

New VIDEO: From LLM Wikis to LLM Artifacts Shared all my thoughts on why LLM wikis and HTML artifacts are a big deal. Plus, new tools to hel…

New VIDEO: From LLM Wikis to LLM Artifacts Shared all my thoughts on why LLM wikis and HTML artifacts are a big deal. Plus, new tools to help you build wikis and artifacts with agents. Just getting st

researchdair-ai--x

Nonlocal operator learning for fMRI encoding and decoding tasks

arXiv:2605.20389v1 Announce Type: new Abstract: Functional MRI data exhibit high-dimensional spatiotemporal structure, making both prediction and decoding challenging. In this work, we investigate neu

OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization

arXiv:2605.21226v1 Announce Type: new Abstract: The key-value (KV) cache dominates memory bandwidth and footprint in long-context autoregressive inference. Recent rotation-preconditioned codecs (Turbo

On the Cost and Benefit of Chain of Thought: A Learning-Theoretic Perspective

arXiv:2605.21260v1 Announce Type: new Abstract: We develop a learning-theoretic framework for understanding Chain of Thought (CoT). We model CoT as the interaction between an answer map and a chain ru

One Operator to Rule Them All? On Boundary-Indexed Operator Families in Neural PDE Solvers

arXiv:2603.01406v2 Announce Type: replace Abstract: Neural PDE solvers are often described as learning solution operators that map problem data to PDE solutions. In this work, we argue that this inter

OpenSeisML: Open Large-Scale Real Seismic and well-log Dataset for Generative AI

arXiv:2605.20539v1 Announce Type: new Abstract: The advent of machine learning (ML) and computer vision has significantly accelerated seismic inversion workflows by reducing the computational cost of

Optimal Query Allocation in Extractive QA with LLMs: A Learning-to-Defer Framework with Theoretical Guarantees

arXiv:2410.15761v4 Announce Type: replace Abstract: Large Language Models excel in generative tasks but exhibit inefficiencies in structured text selection, particularly in extractive question answeri

Oracle Supervision Transfers for Hyperparameter Prediction in Model-Based Image Denoising

arXiv:2605.20479v1 Announce Type: new Abstract: Hyperparameter prediction is a critical practical bottleneck for model-based image denoisers, ranging from classical TV/TGV variational solvers to moder

Ordering Matters: Rank-Aware Selective Fusion for Blended Emotion Recognition

arXiv:2605.21417v1 Announce Type: new Abstract: Blended emotion recognition is challenging because emotions are often expressed as mixtures of subtle and overlapping multimodal cues rather than a sing

PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generation

arXiv:2602.04876v2 Announce Type: replace Abstract: We introduce PerpetualWonder, a hybrid generative simulator that enables long-horizon, action-conditioned 4D scene generation from a single image. C

Physics-informed convolutional neural networks for fluid flow through porous media

arXiv:2605.20250v1 Announce Type: new Abstract: Accurate simulation of fluid flow in porous media is challenging due to complex pore-space geometries and the computational cost of solving the Navier-S

Platonic Representations in the Human Brain: Unsupervised Recovery of Universal Geometry

arXiv:2605.20496v1 Announce Type: cross Abstract: The Strong Platonic Representation Hypothesis suggests that representational convergence in artificial neural networks can be harnessed constructively

Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy

arXiv:2605.21006v1 Announce Type: cross Abstract: We study the effect of different persona on extbf{sycophancy}: model's agreement with users even when the user is incorrect. The standard mitigation,

Plug-and-Play Spiking Operators: Breaking the Nonlinearity Bottleneck in Spiking Transformers

arXiv:2605.20289v1 Announce Type: new Abstract: ANN-to-SNN conversion offers a practical, training-free route to spiking large language models. However, current pipelines primarily focus on spike-driv

Polynomial-Time Robust Multiclass Linear Classification under Gaussian Marginals

arXiv:2605.21428v1 Announce Type: new Abstract: We study the task of agnostic learning of multiclass linear classifiers under the Gaussian distribution. Given labeled examples (x, y) from a distributi

Praxium: Diagnosing Cloud Anomalies with AI-based Telemetry and Dependency Analysis

arXiv:2603.23890v2 Announce Type: replace-cross Abstract: As the modern microservice architecture for cloud applications grows in popularity, cloud services are becoming increasingly complex and more

PREF: Phasorial Embedding Fields for Compact Neural Representations

arXiv:2205.13524v4 Announce Type: replace Abstract: We present an efficient frequency-based neural representation termed PREF: a shallow MLP augmented with a phasor volume that covers significant bord

PrefixWall: Mitigating Prefix Caching Side Channels in Shared LLM Systems

arXiv:2603.10726v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) rely on optimizations like Automatic Prefix Caching (APC) to accelerate inference. APC works by reusing previousl

Prism: Structural Symmetry Scanning via Duality-Constrained Laplacian Projection

arXiv:2605.20245v1 Announce Type: cross Abstract: We introduce extbf{Prism}, a framework for structural symmetry diagnosis in complex networks. Given a graph Laplacian L and a duality operator P (a sy

Prompt Reinjection: Alleviating Prompt Forgetting in Multimodal Diffusion Transformers

arXiv:2602.06886v3 Announce Type: replace Abstract: Multimodal Diffusion Transformers (MMDiTs) for text-to-image generation maintain separate text and image branches, with bidirectional information fl

ProtoPathway: Biologically Structured Prototype-Pathway Fusion for Multimodal Cancer Survival Prediction

arXiv:2605.21454v1 Announce Type: new Abstract: We introduce ProtoPathway, an interpretable-by-design multimodal framework for cancer survival prediction that unifies whole slide imaging and transcrip

Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine

arXiv:2605.20235v1 Announce Type: new Abstract: Diffusion models generate high-dimensional data with remarkable quality, yet how their training efficiently learns the score function, bypassing the cur

Q-ARVD: Quantizing Autoregressive Video Diffusion Models

arXiv:2605.21072v1 Announce Type: new Abstract: Autoregressive video diffusion models (ARVDs) have emerged as a promising architecture for streaming video generation, paving the way for real-time inte

Q-SYNTH: Hybrid Quantum-Classical Adversarial Augmentation for Imbalanced Fraud Detection

arXiv:2605.21164v1 Announce Type: new Abstract: Credit card fraud detection is fundamentally challenged by extreme class imbalance, where fraudulent transactions are rare yet operationally critical. T

Quantifying the cross-linguistic effects of syncretism on agreement attraction

arXiv:2605.21403v1 Announce Type: new Abstract: Agreement attraction errors, in which a verb erroneously agrees with an intervening noun rather than its grammatical head, are amplified by morphologica

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning

arXiv:2605.21127v1 Announce Type: new Abstract: Explicit reasoning models are trained to produce intermediate reasoning traces before final answers, but downstream fine-tuning is often performed on or

Reinforcement Learning-based Control via Y-wise Affine Neural Networks: Comparative Case Studies for Chemical Processes

arXiv:2605.21211v1 Announce Type: cross Abstract: In this work we present an efficient and practically implementable approach for the application of reinforcement learning (RL)-based control in chemic

Reliable Automated Triage in Spanish Clinical Notes: A Hybrid Framework for Risk-Aware HIV Suspicion Identification

arXiv:2605.21256v1 Announce Type: new Abstract: Standard clinical Natural Language Processing (NLP) benchmarks often yield inflated metrics by forcing deterministic classification on ambiguous instanc

RelWitness: Open-Vocabulary 3D Scene Graph Generation with Visual-Geometric Relation Witnesses

arXiv:2605.20823v1 Announce Type: new Abstract: Open-vocabulary 3D scene graph generation seeks to describe object instances and their relations with flexible natural-language predicates. The central

ReMATF: Recurrent Motion-Adaptive Multi-scale Turbulence Mitigation for Dynamic Scenes

arXiv:2605.21440v1 Announce Type: new Abstract: Atmospheric turbulence severely degrades video quality by introducing distortions such as geometric warping, blur, and temporal flickering, posing signi

ResNet-50 with Class Reweighting and Anatomy-Guided Temporal Decoding for Gastrointestinal Video Analysis

arXiv:2603.17784v2 Announce Type: replace Abstract: We developed a multi-label gastrointestinal video analysis pipeline based on a ResNet-50 frame classifier followed by anatomy-guided temporal event

Retrospective Sparse Attention for Efficient Long-Context Generation

arXiv:2508.09001v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed in long-context tasks such as reasoning, code generation, and multi-turn dialogue. However, i

ReversedQ: Opportunities for Faster Q-Learning in Episodic Online Reinforcement Learning

arXiv:2605.20592v1 Announce Type: new Abstract: We study model-free Q-learning in finite-horizon episodic Markov Decision Processes (MDPs) with stationary dynamics across episodes. We identify a centr

Reviving Error Correction in Modern Deep Time-Series Forecasting

arXiv:2605.21088v1 Announce Type: new Abstract: Modern deep-learning models have achieved remarkable success in time-series forecasting. Yet, their performance degrades in long-term prediction due to

Riemannian MeanFlow for One-Step Generation on Manifolds

arXiv:2603.10718v2 Announce Type: replace Abstract: Flow Matching enables simulation-free training of generative models on Riemannian manifolds, yet sampling typically still relies on numerically inte

RISE: Reliable Improvement in Self-Evolving Vision-Language Models

arXiv:2605.20914v1 Announce Type: new Abstract: Vision-language models (VLMs) have achieved strong multimodal reasoning capabilities, but further improving them still relies heavily on large-scale hum

RoadTones: Tone Controllable Text Generation from Road Event Videos

arXiv:2605.21411v1 Announce Type: new Abstract: Existing video-language models can generate factual descriptions of road events but lack control over how these events are expressed: their tone, urgenc

ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation

arXiv:2605.21121v1 Announce Type: new Abstract: Single-image-to-3D generative models can now produce high-quality geometry, yet conditioning on a single view inevitably introduces ambiguity about unse

Robust Subspace-Constrained Quadratic Models for Low-Dimensional Structure Learning

arXiv:2605.20300v1 Announce Type: new Abstract: In this paper, we propose a robust subspace-constrained quadratic model (SCQM) for learning low-dimensional structure from high-dimensional data. Buildi

RoPeSLR: 3D RoPE-driven Sparse-LowRank Attention for Efficient Diffusion Transformers

arXiv:2605.20659v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) have revolutionized high-fidelity video generation, yet their O(L^2) attention complexity poses a formidable bottleneck fo

Model Releases

roto 2.0: The Robot Tactile Olympiad

model-releasesarxiv-cs-lg

arXiv:2605.21429v1 Announce Type: cross Abstract: Tactile-based reinforcement learning (RL) is currently hindered by fragmented research and a focus on over-saturated orientation tasks. We introduce v

Same Target, Different Basins: Hard vs. Soft Labels for Annotator Distributions

arXiv:2605.20642v1 Announce Type: new Abstract: When annotators disagree, that disagreement can reflect epistemic uncertainty rather than simple label noise. We study hard-label delivery as an alterna

Sample Complexity of Transfer Learning: An Optimal Transport Approach

arXiv:2605.20545v1 Announce Type: cross Abstract: Transfer learning is an essential technique for many machine learning/AI models of complex structures such as large language models and generative AI.