Search: “research”

Steering Where to Listen: Instruction-Based Activation Steering Redirects Temporal Attention in Large Audio-Language Models

arXiv:2606.11400v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) excel at audio understanding but expose little about where in an audio signal they attend. We introduce instructio

Research

Structure-Preserving Neural Surrogates with Tractable Uncertainty Quantification

DGX agent

arXiv:2606.11650v1 Announce Type: new Abstract: Recent advances in scientific machine learning provide a means of near-real-time solution to partial differential equations (PDEs), but lack the theoret

researcharxiv-cs-lg

11 Jun 2026

T2S: A Rehearsal-Based Approach for Extraction-Resistant Model Watermarking

arXiv:2606.11698v1 Announce Type: cross Abstract: Model watermarking safeguards AI model intellectual property by embedding distinctive knowledge that induces unique behavioral signatures. The primary

Tabular Foundation Models for Clinical Survival Analysis via Survival-Aware Adaptation

arXiv:2606.12006v1 Announce Type: cross Abstract: Predicting time-to-event outcomes such as mortality is a fundamental task in clinical decision-making, commonly addressed through survival analysis. W

Temporal2Seq: A Unified Framework for Temporal Video Understanding Tasks

arXiv:2409.18478v2 Announce Type: replace Abstract: With the development of video understanding, there is a proliferation of tasks for clip-level temporal video analysis, including temporal action det

Tensor Methods: A Unified and Interpretable Approach for Material Design

arXiv:2602.10392v2 Announce Type: replace Abstract: When designing new materials, it is often necessary to tailor the material design to have some desired properties. As the set of design parameters g

TextHOI-3D: Text-to-3D Hand-Object Interaction via Discrete Multi-View Generation and Joint Mesh Optimization

arXiv:2606.11805v1 Announce Type: cross Abstract: Text-conditioned 3D generation has progressed rapidly for images and isolated objects, but producing a hand-object mesh remains challenging: the outpu

The Dynamics of Human and AI-Generated Language: How Semantics Fluctuates across Different Timescales

arXiv:2606.11371v1 Announce Type: cross Abstract: Spoken language, whether produced by humans or large language models (LLM), unfolds over time with varying semantic content. However, we still lack si

The Latent Color Subspace: Emergent Order in High-Dimensional Chaos

arXiv:2603.12261v2 Announce Type: replace-cross Abstract: Text-to-image generation models have advanced rapidly, yet achieving fine-grained control over generated images remains difficult, largely due

The Long Tail, Not the Front Page: Cold-Start Prediction of Crowd Highlight Salience

arXiv:2606.11654v1 Announce Type: cross Abstract: A social highlighter's most useful signal -- which passages a crowd of readers marks -- exists only for documents people have already read. Can the ag

The Power of Test-Time Training for Approximate Sampling

arXiv:2606.11437v1 Announce Type: cross Abstract: Efficiently sampling from a complex probability distribution is a fundamental problem which has become increasingly pertinent in recent years with the

Time-Conditioned and Multi-Time Survival Prediction from 2D PET/CT Projections in Lung Cancer

arXiv:2606.12140v1 Announce Type: new Abstract: Accurate prediction of overall survival (OS) from positron emission tomography/computed tomography (PET/CT) can support personalized treatment and follo

Towards Deep Learning Surrogate for the Forward Problem in Electrocardiology: A Scalable Alternative to Physics-Based Models

arXiv:2512.13765v2 Announce Type: replace-cross Abstract: The forward problem in electrocardiology, computing body surface potentials from cardiac electrical activity, is traditionally solved using ph

Understanding Cross-Sensor Feature Variations for Generalizable 3D Perception

arXiv:2606.11573v1 Announce Type: new Abstract: Radar-camera BEV perception often suffers from degraded performance when evaluated across datasets, as changes in driving scenes, sensor configurations,

Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders

arXiv:2606.12138v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are widely used to interpret neural network representations, but their utility depends on whether the learned features are

Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery

arXiv:2602.02726v2 Announce Type: replace-cross Abstract: Large language models (LLMs) encode rich semantic information in their hidden states, yet it remains difficult to understand what information

VIA-SD: Verification via Intra-Model Routing for Speculative Decoding

arXiv:2606.12243v1 Announce Type: cross Abstract: Speculative decoding (SD) addresses the high inference costs of LLMs by having lightweight drafters generate candidates for large verifiers to validat

Vision-Aided Relative State Estimation for Approach and Landing on a Moving Platform with Inertial Measurements

arXiv:2512.19245v2 Announce Type: replace-cross Abstract: This paper tackles the problem of estimating the relative position, orientation, and velocity between a UAV and a planar platform undergoing a

researcharxiv-cs-ro

Vision Transformers for Face Recognition Need More Registers

arXiv:2606.12036v1 Announce Type: new Abstract: Recent advances in Vision Transformers (ViTs) for face recognition (FR) have moved beyond the standard CLS-token paradigm. In this paradigm, a special c

VOID: Defeating Unauthorized Mimicry in Latent Diffusion Models

arXiv:2606.12263v1 Announce Type: new Abstract: While Latent Diffusion Models (LDMs) have revolutionized visual synthesis, they are increasingly exploited for unauthorized mimicry of individuals. Exis

What Limits Does Quantization Place on Dense Top-k Retrieval? A Theoretical Study

arXiv:2606.11780v1 Announce Type: cross Abstract: We establish conditions for embedding a corpus of N documents as d-dimensional vectors such that every k-subset S subseteq [N] is realizable as a resu

When Do Data-Driven Systems Exhibit the Capability to Infer?

arXiv:2606.11769v1 Announce Type: new Abstract: The European AI Act is the first comprehensive regulation of artificial intelligence (AI), setting out extensive obligations, particularly for so-called

When Poison Fails After Retrieval: Revisiting Corpus Poisoning under Chunking and Reranking Pipelines

arXiv:2606.11265v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are vulnerable to corpus poisoning attacks that manipulate downstream model outputs through malicious kno

When Probing Accuracy Saturates, Fragility Resolves: A Complementary Metric for LLM Pre-Training Analysis

arXiv:2606.11375v1 Announce Type: cross Abstract: Standard linear probing declares a property 'encoded' when a classifier on hidden states achieves high accuracy. The protocol works well on a snapshot

Where Do Backdoors Live? A Component-Level Analysis of Backdoor Propagation in Speech Language Models

arXiv:2510.01157v4 Announce Type: replace Abstract: Speech language models (SLMs) are systems of systems: independent components that unite to achieve a common goal. Despite their heterogeneous nature

Why Depth Matters in Parallelizable Sequence Models: A Lie Algebraic View

arXiv:2603.05573v2 Announce Type: replace Abstract: Scalable sequence models, such as Transformer variants and structured state-space models, often trade expressivity power for sequence-level parallel

XPR: An Extensible Cross-Platform Point-Based Differentiable Renderer

arXiv:2606.11529v1 Announce Type: cross Abstract: Point-based differentiable rendering underpins modern 3D reconstruction, novel-view synthesis, and learning-based graphics pipelines, but developing n

A Continuous-Time Markov Chain Framework for Insertion Language Models

arXiv:2606.10199v1 Announce Type: cross Abstract: Insertion Language Models (ILMs) offer several advantages over left-to-right generation and mask-based generation. However, existing formulations of i

A Controlled Audit of Pretraining Contamination in Public Medical Vision-Language Benchmarks

arXiv:2606.10066v1 Announce Type: cross Abstract: Medical vision-language models (VLMs) are evaluated on public benchmarks whose images and question-answer pairs have been freely downloadable for year

A Multimodal RGB and Events Dataset for Hand Detection in First-Person View

arXiv:2606.10790v1 Announce Type: new Abstract: Existing hand detection algorithms work on images and the detection rate is restricted by the frame rate of the camera. In hand detection applications f

A Sketch-and-Project Analysis of Subsampled Natural Gradient Algorithms

arXiv:2508.21022v3 Announce Type: replace Abstract: Subsampled natural gradient descent (SNG) has been used to enable high-precision scientific machine learning, but standard analyses based on stochas

A Spiking Neural Architecture for Coordinating Arm and Locomotor Control

arXiv:2606.11034v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) coupled with neuromorphic hardware offer energy-efficient solutions for humanoid robot control. However, existing SNN-bas

researcharxiv-cs-ro

A Systematic Approach for Selecting Trajectories for Data Augmentation

arXiv:2606.10938v1 Announce Type: new Abstract: Trajectory data augmentation is a promising approach to mitigate data scarcity in machine learning applications, but its utility has been limited by the

A Unified Adaptive Feature Composition Framework for Multi-Task Generalization in Wireless Foundation Models

arXiv:2606.10277v1 Announce Type: new Abstract: Though wireless foundation models (WFMs) have shown strong potential in learning universal channel representations, their adaptation to various downstre

A Unified Siamese Learning Framework for Zero-Day Anomaly Detection and Classification in Optical Networks

arXiv:2606.10827v1 Announce Type: cross Abstract: A multi-similarity Siamese neural network unifies zero-day anomaly detection and one-shot classification in optical networks, achieving over 99% accur

Accelerating NeurASP with vectorization and caching

arXiv:2606.10787v1 Announce Type: new Abstract: Neurosymbolic AI combines neural networks with symbolic programs to create robust and explainable predictions. One such framework is NeurASP, which trai

Accelerating SAV-based optimization via randomized low-rank Hessian approximation

arXiv:2606.10562v1 Announce Type: cross Abstract: We propose a new optimization method, the Nystrom-enhanced relaxed scalar auxiliary variable method (N-RSAV), which incorporates curvature information

Adaptive Sliding Mode Control for Vehicle Platoons with State-Dependent Friction Uncertainty

arXiv:2601.10724v3 Announce Type: replace Abstract: Multi-robot formation control has various applications in domains such as vehicle troops, platoons, payload transportation, and surveillance. Mainta

researcharxiv-cs-ro

Advancing Wood Identification in the Philippines: Utilizing the Xylorix Platform for Efficient AI Model Development and Deployment for Five Key Species

arXiv:2606.10876v1 Announce Type: new Abstract: Illegal logging and timber trade continue to pose significant challenges in the Philippines, where accurate wood species identification is essential for

AI Application Gives Users Real-Time Feedback on the Level of Peace in the Social Media Videos They Watch

arXiv:2601.05232v3 Announce Type: replace Abstract: Most people now get their news from videos on social media, such as YouTube and Facebook, rather than through curated journalism. 'We become what we

Algorithmic and Minimax Complexities in Kernel Bandits

arXiv:2606.11171v1 Announce Type: new Abstract: Gaussian-process upper confidence bound (GP-UCB) and decision-estimation-coefficient (DEC) methods may appear, at first sight, to belong to different th

Ambiguous Strategic Classification

arXiv:2606.10137v1 Announce Type: new Abstract: A common assumption in strategic classification is that the classifier is public knowledge. However, it remains unclear whether, and why, a system would

An (epsilon,elta)-accurate level set estimation with a stopping criterion

arXiv:2503.20272v2 Announce Type: replace-cross Abstract: The level set estimation problem seeks to identify regions within a set of candidate points where an unknown and costly to evaluate function's

An Uncertainty Estimation Framework for Dose Accumulation in Adaptive Radiotherapy: Application to CBCT-Guided Radiotherapy for Cervical Cancer

arXiv:2606.11012v1 Announce Type: new Abstract: Background and purpose: oART enables daily plan adaptation to interfraction anatomical variations, but cumulative dose estimation remains limited by DIR

ANCHOR: Autoregressive Non-intrusive Chunk-Ordered Refinement for Joint Multi-Resolution Speech Quality Modeling

arXiv:2606.10233v1 Announce Type: cross Abstract: While speech quality is typically assessed on complete utterances, streaming and generative systems require incremental estimation from partial audio.

AnimeScore: A Preference-Based Dataset and Framework for Evaluating Anime-Like Speech Style

arXiv:2603.11482v2 Announce Type: replace-cross Abstract: Evaluating 'anime-like' voices currently relies on costly subjective judgments, yet no standardized objective metric exists. A key challenge i

ArabiGEE: A Hierarchical Taxonomy for Arabic Grammatical Error Explanation

arXiv:2606.10765v1 Announce Type: new Abstract: We introduce ArabiGEE, the first comprehensive Arabic grammatical error explanation (GEE) taxonomy grounded in explicit error types. Unlike existing GEE

Are We Evaluating Knowledge or Phrasing? Mitigating MCQA Sensitivity with ParaEval

arXiv:2606.10657v1 Announce Type: new Abstract: Multiple-choice (MCQA) benchmarks are the standard for evaluating pretrained large language models, but their reliance on log-likelihood scoring makes t