Search: “research”

Lossy Common Information in a Learnable Gray-Wyner Network

arXiv:2601.21424v3 Announce Type: replace-cross Abstract: Many computer vision tasks share substantial overlapping information, yet conventional codecs tend to ignore this, leading to redundant and in

LR-SGS: Robust LiDAR-Reflectance-Guided Salient Gaussian Splatting for Self-Driving Scene Reconstruction

DGX agent

arXiv:2603.12647v2 Announce Type: replace-cross Abstract: Recent 3D Gaussian Splatting (3DGS) methods have demonstrated the feasibility of self-driving scene reconstruction and novel view synthesis. H

researcharxiv-cs-ai

11 May 2026

MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference

arXiv:2605.05225v2 Announce Type: replace-cross Abstract: Mixture-of-Experts Multimodal Large Language Models (MoE MLLMs) suffer from a significant efficiency bottleneck during Expert Parallelism (EP)

Making AI Evaluation Deployment Relevant Through Context Specification

arXiv:2603.06811v3 Announce Type: replace Abstract: With many organizations struggling to gain value from AI deployments, pressure to evaluate AI in an informed manner has intensified. Status quo AI e

MAST: A Multi-fidelity Augmented Surrogate model via Spatial Trust-weighting

arXiv:2602.20974v2 Announce Type: replace Abstract: In engineering design and scientific computing, computational cost and predictive accuracy are intrinsically coupled. High-fidelity simulations prov

Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers

arXiv:2605.06169v1 Announce Type: cross Abstract: Scaling Diffusion Transformers (DiTs) to hundreds of layers introduces a structural vulnerability: networks can enter a silent, mean-dominated collaps

Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors

arXiv:2605.07847v1 Announce Type: new Abstract: As user simulators are increasingly used for interactive training and evaluation of AI assistants, it is essential that they represent the diverse behav

Mechanistic Interpretability with Sparse Autoencoder Neural Operators

arXiv:2509.03738v4 Announce Type: replace-cross Abstract: We introduce sparse autoencoder neural operators (SAE-NOs), a new class of sparse autoencoders that operate in function spaces rather than fix

Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models

arXiv:2605.07721v1 Announce Type: cross Abstract: Recurrent LLM architectures have emerged as a promising approach for improving reasoning, as they enable multi-step computation in the embedding space

Minerva: Reinforcement Learning with Verifiable Rewards for Cyber Threat Intelligence LLMs

arXiv:2602.00513v3 Announce Type: replace Abstract: Cyber threat intelligence (CTI) analysts routinely convert noisy, unstructured security artifacts into standardized, automation-ready representation

Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM

arXiv:2605.05927v2 Announce Type: replace Abstract: Speech large language models (SLMs) are typically built from text large language model (TLM) checkpoints, yet they still suffer from a substantial m

Mixture of Masters: Sparse Chess Language Models with Player Routing

arXiv:2602.04447v2 Announce Type: replace-cross Abstract: Modern chess language models are dense transformers trained on millions of games played by thousands of high-rated individuals. However, these

Motion-o: Trajectory-Grounded Video Reasoning

arXiv:2603.18856v2 Announce Type: replace-cross Abstract: Recent video reasoning models increasingly produce spatio-temporal evidence chains that localize objects at specific timestamps. While these t

Multi-Dimensional Evaluation of LLMs for Grammatical Error Correction

arXiv:2605.07635v1 Announce Type: new Abstract: Automated assistants for Grammatical Error Correction are now embedded in educational platforms serving millions of learners, yet three critical gaps re

Multimodal Diffusion Transformer with Memory Bank for Scalable Long-Duration Talking Video Generation

arXiv:2411.16748v5 Announce Type: replace Abstract: Long-duration talking video synthesis faces enduring challenges in achieving high video quality, portrait consistency, temporal coherence, and compu

Multimodal Latent Reasoning via Hierarchical Visual Cues Injection

arXiv:2602.05359v2 Announce Type: replace Abstract: The advancement of multimodal large language models (MLLMs) has enabled impressive perception capabilities. However, their reasoning process often r

Multimodal Stepwise Clinically-Guided Attention Learning for Pathological Complete Response Prediction in Breast Cancer

arXiv:2605.07561v1 Announce Type: new Abstract: Pathological complete response (pCR) is a key prognostic factor in breast cancer patients undergoing neoadjuvant therapy, strongly associated with long-

Multispectral Indices for Wildfire Management

arXiv:2309.01751v3 Announce Type: replace-cross Abstract: The increasing frequency and severity of wildfires necessitates advanced methods for effective surveillance and management, as traditional gro

Muon with Nesterov Momentum: Heavy-Tailed Noise and (Randomized) Inexact Polar Decomposition

arXiv:2605.06884v1 Announce Type: cross Abstract: Most first-order optimizers treat matrix-valued parameters as vectors, ignoring the intrinsic geometry of hidden-layer weights in neural networks. Muo

Neurosymbolic Imitation Learning with Human Guidance: A Privileged Information Approach

arXiv:2605.07166v1 Announce Type: new Abstract: Imitation learning is widely used for learning to act in complex environments. While pure neural-based methods handle high dimensional data effectively,

News organizations are increasingly blocking the Wayback Machine even as their reporters still depend on it 📰 In PRESERVING THE WEB IN THE …

News organizations are increasingly blocking the Wayback Machine even as their reporters still depend on it 📰 In PRESERVING THE WEB IN THE AGE OF AI, Mark Graham, Director of the Wayback Machine at th

researchyann-lecun--x

Normalized Maximum Likelihood Code-Length on Riemannian Data Spaces

arXiv:2508.21466v2 Announce Type: replace Abstract: In recent years, with the large-scale expansion of graph data, there has been an increased focus on Riemannian manifold data spaces other than Eucli

Normalizing Trajectory Models

arXiv:2605.08078v1 Announce Type: new Abstract: Diffusion-based models decompose sampling into many small Gaussian denoising steps -- an assumption that breaks down when generation is compressed to a

Not All Tokens Need 40 Steps: Heterogeneous Step Allocation in Diffusion Transformers for Efficient Video Generation

arXiv:2605.06892v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) have achieved state-of-the-art video generation quality, but they incur immense computational cost because standard infere

NSPOD: acceleratingthe convergence ofKrylov-based iterative linearsolvers via approximated PODs

arXiv:2605.07828v1 Announce Type: cross Abstract: The convergence of Krylov-based linear iterative solvers applied to parametric partial differential equations (PDEs) is often highly sensitive to the

Nurnberg NLP at PsyDefDetect: Multi-Axis Voter Ensembles for Psychological Defence Mechanism Classification

arXiv:2605.07606v1 Announce Type: cross Abstract: Detecting levels of psychological defence mechanisms in supportive conversations is inherently ambiguous. In the PsyDefDetect shared task at BioNLP 20

On Privacy Leakage in Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics

arXiv:2605.06835v1 Announce Type: cross Abstract: Tabular data plays an important role in many fields and industries, including those with elevated privacy considerations and risks. As such, there is

On the Complexity of the Matching Problem of Regular Expressions with Backreferences

arXiv:2605.07289v1 Announce Type: cross Abstract: ReDoS is a well-known type of algorithmic complexity attack, where an adversary supplies maliciously crafted strings to a regular expression matching

On the Divergence of Differential Temporal Difference Learning without Local Clocks

arXiv:2605.06874v1 Announce Type: new Abstract: Learning rate is a critical component of reinforcement learning (RL). This work uses global and local clocks to distinguish two types of learning rates.

On the Robustness of Distribution Support under Diffusion Guidance

arXiv:2605.07220v1 Announce Type: new Abstract: Diffusion guidance is a powerful technique that enables controllable and high-fidelity sample generation with diffusion models. At a high level, it modi

On the Role of Strain and Vorticity in Numerical Integration Error for Flow Matching

arXiv:2605.06680v1 Announce Type: cross Abstract: Flow matching generates data by integrating a learned velocity field, where the number of integration steps (NFE) directly determines inference cost.

Online Goal Recognition using Path Signature and Dynamic Time Warping

arXiv:2605.07736v1 Announce Type: new Abstract: Online goal recognition in continuous domains poses two central challenges: efficiently encoding large trajectories and effectively comparing them. Rece

Online Localized Conformal Prediction

arXiv:2605.05497v2 Announce Type: replace Abstract: Conformal prediction is a framework that provides valid uncertainty quantification for general models with exchangeable data. However, in the online

Safety

Operating Within the Operational Design Domain: Zero-Shot Perception with Vision-Language Models

arXiv:2605.07649v1 Announce Type: cross Abstract: Over the last few years, research on autonomous systems has matured to such a degree that the field is increasingly well-positioned to translate resea

safetyarxiv-cs-ai

OphEdit: Training-Free Text-Guided Editing of Ophthalmic Surgical Videos

arXiv:2605.07695v1 Announce Type: new Abstract: High-fidelity surgical video generation can greatly improve medical training and the development of AI, adapting these generative models for precise vid

Optimising MFCC parameters for the automatic detection of respiratory diseases

arXiv:2408.07522v2 Announce Type: replace-cross Abstract: Voice signals originating from the respiratory tract are utilized as valuable acoustic biomarkers for the diagnosis and assessment of respirat

Overview of the TREC 2025 RAGTIME Track

arXiv:2602.10024v2 Announce Type: replace-cross Abstract: The principal goal of the RAG TREC Instrument for Multilingual Evaluation (RAGTIME) track at TREC is to study report generation from multiling

Parallel Lifted Planning via Semi-Naive Datalog Evaluation

arXiv:2605.07584v1 Announce Type: new Abstract: Lifted classical planners operate directly on first-order planning tasks to avoid the computationally demanding grounding step. However, lifted planning

Penalty-Based First-Order Methods for Bilevel Optimization with Minimax and Constrained Lower-Level Problems

arXiv:2605.08006v1 Announce Type: cross Abstract: We study a class of bilevel optimization problems in which both the upper- and lower-level problems have minimax structures. This setting captures a b

PersonaGest: Personalized Co-Speech Gesture Generation with Semantic-Guided Hierarchical Motion Representation

arXiv:2605.07252v1 Announce Type: cross Abstract: Co-speech gesture generation aims to synthesize realistic body movements that are semantically coherent with speech and faithful to a user-specified g

PET-Adapter: Test-Time Domain Adaptation for Full and Limited-Angle PET Image Reconstruction

arXiv:2605.08030v1 Announce Type: new Abstract: Positron Emission Tomography (PET) image reconstruction is inherently challenged by Poisson noise and physical degradation factors, which are further ex

Physics-based Digital Twins for Integrated Thermal Energy Systems Using Active Learning

arXiv:2605.06756v1 Announce Type: new Abstract: Real-time supervisory control of thermal energy distribution systems requires digital twins that are accurate, interpretable, and uncertainty-aware, yet

Physics-Informed Reduced-Order Operator Learning for Hyperelasticity in Continuum Micromechanics

arXiv:2605.07738v1 Announce Type: cross Abstract: Physics-informed operator learning is an attractive candidate for surrogate modeling of microstructures, especially in multiscale finite-element simul

PicoEyes: Unified Gaze Estimation Framework for Mixed Reality with a Large-Scale Multi-View Dataset

arXiv:2605.07188v1 Announce Type: new Abstract: We present PicoEyes, a unified gaze estimation framework that directly predicts all key attributes of gaze, including 3D eye parameters, eye-region segm

PISTO: Proximal Inference for Stochastic Trajectory Optimization

arXiv:2605.07215v1 Announce Type: new Abstract: Stochastic trajectory optimization methods like STOMP enable planning with non-differentiable costs, offering substantial flexibility over gradient-base

researcharxiv-cs-ro

PolarAdamW: Disentangling Spectral Control and Schur Gauge-Equivariance in Matrix Optimisation

arXiv:2605.07067v1 Announce Type: new Abstract: Muon's matrix-level update couples two distinct effects: spectral control via a polar map, and equivariance under orthogonal changes of multiplicity-spa

PolySQL: Scaling Text-to-SQL Evaluation Across SQL Dialects via Automated Backend Isomorphism

arXiv:2605.07796v1 Announce Type: new Abstract: SQL dialects vary in syntax, types, and functions across database engines. Text-to-SQL benchmarks, however, predominantly support only SQLite. This crea

PPI-Net connects molecular protein interactions to functional processes in disease

arXiv:2605.07838v1 Announce Type: cross Abstract: Understanding how molecular alterations propagate across biological systems to drive disease remains a central challenge. Although high-throughput pro