research

{Phi}-Noise: Training-Free Temporal Video Conditioning via Phase-Based Noise Manipulation

arXiv:2605.24509v1 Announce Type: cross Abstract: Latent video diffusion models generate videos by progressively transforming Gaussian noise into realistic samples conditioned on text or visual inputs

Research

Phonetic Modeling of Dialectal Variation in Vietnamese Speech

DGX agent

arXiv:2605.24451v1 Announce Type: new Abstract: Vietnamese exhibits substantial dialectal phonetic variation across Northern, Central, and Southern regions, where identical lexical items may be realiz

researcharxiv-cs-cl

26 May 2026

PhySense: Sensor Placement Optimization for Accurate Physics Sensing

arXiv:2505.18190v5 Announce Type: replace-cross Abstract: Physics sensing plays a central role in many scientific and engineering domains, which inherently involves two coupled tasks: reconstructing d

Physics-Guided Concentration Inference from Resistance Transients in a Mixed-Phase SnO-SnO_2 Carbon Monoxide Sensor with p-n Switching

arXiv:2605.23971v1 Announce Type: cross Abstract: This work presents a physics-guided machine-learning framework for carbon monoxide concentration inference from experimentally measured resistance tra

Pixelwise Uncertainty Quantification of Accelerated MRI Reconstruction

arXiv:2601.13236v2 Announce Type: replace-cross Abstract: Parallel imaging techniques reduce magnetic resonance imaging (MRI) scan time but image quality degrades as the acceleration factor increases.

Poisoning the Watchtower: Prompt Injection Attacks Against LLM-Augmented Security Operations Through Adversarial Log Content

arXiv:2605.24421v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as analyst assistants in security operations centers (SOCs), where they ingest log and alert data t

Polymander II: an amphibious salamander-inspired robot with contact and flow sensors

arXiv:2605.24465v1 Announce Type: new Abstract: Robots benefit from sensory information to coordinate body movement, gain robustness against perturbations, and transit between different modes to adapt

researcharxiv-cs-ro

PoseRefer: Pathway-Local Parameters for Semantically Grounded Reference Resolution

arXiv:2605.24622v1 Announce Type: new Abstract: A robot resolving ``put the cup on that one'' must fuse gesture, language, and scene geometry, yet 3D grounding benchmarks only partially capture this r

researcharxiv-cs-ro

Posture Clip: Sit properly or I wont let you work

arXiv:2605.25664v1 Announce Type: cross Abstract: Poor posture is a significant concern due to its detrimental effects on health and productivity. This paper presents a collar-clipped device called Po

PowerFlow: Unlocking the Dual Nature of LLMs via Principled Distribution Matching

arXiv:2603.18363v2 Announce Type: replace-cross Abstract: Unsupervised Reinforcement Learning from Internal Feedback (RLIF) has emerged as a promising paradigm for eliciting the latent capabilities of

PowLU: An Activation Function for Stable Pre-Training of LLMs

arXiv:2605.25704v1 Announce Type: new Abstract: In contemporary large language models (LLMs), the swish-gated linear unit (SwiGLU) activation function is widely adopted to regulate the information flo

Predicting Stock Price Direction on Earnings Announcement Days using Multi-modal Deep Learning

arXiv:2605.25894v1 Announce Type: new Abstract: Predicting stock price movements during Earnings Announcements (EAs) is a significant challenge due to market noise and high-impact price discontinuitie

Prism: Spectral-Aware Block-Sparse Attention

arXiv:2602.08426v2 Announce Type: replace-cross Abstract: Block-sparse attention is promising for accelerating long-context LLM pre-filling, yet identifying relevant blocks efficiently remains a bottl

Proactive for Uncertainty: Cause-Aware Error Diagnosis and Interactive Clarification for Spoken Dialogue Systems

arXiv:2605.25404v1 Announce Type: new Abstract: Cascaded Automatic Speech Recognition -- Large Language Model (ASR-LLM) pipelines remain popular for industrial Spoken Dialogue Systems (SDS), primarily

Probability Distributions Computed by Autoregressive Transformers

arXiv:2510.27118v4 Announce Type: replace Abstract: Most expressivity results for transformers treat them as language recognizers -- devices that accept or reject strings -- rather than as they are us

Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare

arXiv:2509.07961v2 Announce Type: replace Abstract: We develop new experimental paradigms for measuring welfare in language models. We compare verbal reports of models about their preferences with pre

PromptAudit: Auditing Prompt Sensitivity in LLM-Based Vulnerability Detection

arXiv:2605.24171v1 Announce Type: cross Abstract: Large language models are increasingly used for vulnerability detection, yet their reliability under different prompt formulations remains uncharacter

Psychometric Item Validation Using Virtual Respondents with Trait-Response Mediators

arXiv:2507.05890v4 Announce Type: replace-cross Abstract: As psychometric surveys are increasingly used to assess the traits of large language models (LLMs), the need for scalable survey item generati

Qiskit Global Summer School 2026: Registration now open

Qiskit Global Summer School 2026 is an educational program offered by IBM that focuses on quantum computing and the Qiskit framework, with registration now available for interested participants. The s

researchibm-research

Quantifying Empirical Compute-Supervision Tradeoffs in RLVR

arXiv:2605.25252v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training language models, but in practice, verifiers are

RAMBA: 4D Radar Mapping by Bundle Adjustment

arXiv:2605.25041v1 Announce Type: new Abstract: 4D radar is increasingly attractive for robotic mapping because it provides range, azimuth, elevation, and Doppler measurements while remaining robust i

researcharxiv-cs-ro

Random Neural Network Expressivity for Non-Linear Partial Differential Equations

arXiv:2605.25057v1 Announce Type: cross Abstract: Neural networks with randomly generated hidden weights (RaNNs) have been extensively studied, both as a standalone learning method and as an initializ

Rao-Blackwellized Score Matching on Manifolds

arXiv:2605.25567v1 Announce Type: cross Abstract: We study denoising score matching (DSM) when the latent distribution is supported on a smooth embedded manifold M subset R^D. Under ambient Gaussian c

Rapid mixing in positively weighted restricted Boltzmann machines

arXiv:2604.00963v2 Announce Type: replace-cross Abstract: We show polylogarithmic mixing time bounds for the alternating-scan sampler for positively weighted restricted Boltzmann machines. This is don

Re-defining Humor Data Objects for AI Humor Research

arXiv:2605.25171v1 Announce Type: new Abstract: In most existing AI humor research, humor was treated as either 'present' or 'not present.' We explore the concept of humor as a social interaction with

Re-examining Granger Causality with Causal Bayesian Networks and Reichenbachs Principles

arXiv:2501.02672v2 Announce Type: replace-cross Abstract: Characterising cause-effect relationships in complex systems is fundamental to understanding their underlying mechanisms. Granger causality (G

ReactEmbed: A Plug-and-Play Module for Unifying Protein-Molecule Representations Guided by Biochemical Reaction Networks

arXiv:2501.18278v3 Announce Type: replace Abstract: State-of-the-art models represent proteins and molecules in separate embedding manifolds, limiting the modeling of systemic biological processes. We

Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing

arXiv:2605.25902v1 Announce Type: new Abstract: Narrowly finetuned language models memorize implanted content verbatim, but auditing what a deployed model has been taught, without access to its weight

Reinforcement Learning for Reachability: Guaranteeing Asymptotic Optimality

arXiv:2605.24740v1 Announce Type: new Abstract: Reinforcement learning (RL) for reachability specifications is fundamental in sequential decision-making, yet theoretical guarantees remain less explore

Rejoinder: The ICML 2023 Ranking Experiment: Examining Author Self-Assessment in ML/AI Peer Review

arXiv:2605.25172v1 Announce Type: cross Abstract: This article is the rejoinder to ``The ICML 2023 Ranking Experiment: Examining Author Self-Assessment in ML/AI Peer Review,'' to appear in the Journal

Relative Repairability: A Calibration-Based Diagnostic for High-Sparsity Post-Pruning Allocation

arXiv:2605.25508v1 Announce Type: new Abstract: At very high sparsity, neural network pruning does more than decide which weights remain. It also determines where pruning induced damage is placed acro

Relative Translation Invariant Wasserstein Distance

arXiv:2409.02416v2 Announce Type: replace Abstract: Motivated by the Bures distance, we introduce a new family of distances, relative translation invariant Wasserstein distances, denoted by RW_p, as a

Remote sensing data imputation using deep learning for multispectral imagery

arXiv:2605.24003v1 Announce Type: cross Abstract: Remote sensing techniques have been increasingly utilised in aquatic applications in recent years. A common challenge in using optical satellite data

Repeated Sequences Reveal Gaps between Large Language Models and Natural Language

arXiv:2605.24850v1 Announce Type: new Abstract: Evaluating whether large language models (LLMs) capture the structure of natural language beyond local fluency remains an open challenge. Existing evalu

Representation-Guided Discrete Molecular Graph Retrosynthesis

arXiv:2605.24428v1 Announce Type: new Abstract: Stochastic process-based molecular graph generators have become the state of the art for template-free single-step retrosynthesis. However, these models

Rethinking Federated Unlearning via the Lens of Memorization

arXiv:2605.24545v1 Announce Type: cross Abstract: Federated learning (FL) increasingly needs machine unlearning to comply with privacy regulations. However, existing federated unlearning approaches ma

Retrieved In-Context Principles from Previous Mistakes

arXiv:2407.05682v2 Announce Type: replace Abstract: In-context learning (ICL) has been instrumental in adapting Large Language Models (LLMs) to downstream tasks using correct input-output examples. Re

Revisiting Pre-Propagation GNNs: Robust Diffusion Operators and Hidden-State Re-Propagation

arXiv:2605.25111v1 Announce Type: new Abstract: Pre-propagation graph neural networks (PPGNNs) decouple node feature propagation from transformation: graph diffusion is performed once as preprocessing

Riemannian Archetypal Analysis: Interpretable non-linear data analysis on deformed star distributions

arXiv:2605.24113v1 Announce Type: new Abstract: Classical archetypal analysis is appealing for its interpretability, but its linear geometry can limit performance on data with strongly non-linear stru

Robust inference using density-powered Stein operators

arXiv:2511.03963v2 Announce Type: replace-cross Abstract: We introduce a density-power weighted variant for the Stein operator, called the gamma-Stein operator. This is a novel class of operators deri

ROC Analysis for Evaluating Translation Quality Estimation Systems

arXiv:2605.24721v1 Announce Type: new Abstract: The increasing use of automated translation quality estimation (QE) systems calls for practical, decision-oriented methods for evaluating their performa

Routing by Analogy: kNN-Augmented Expert Assignment for Mixture-of-Experts

arXiv:2601.02144v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) architectures scale large language models efficiently by employing a parametric ``router'' to dispatch tokens to a sp

Rubato: Transcribing Piano Music with Timestamps

arXiv:2605.24291v1 Announce Type: cross Abstract: We consider the conversion of musical recordings into human-readable sheet music annotated with timestamps. Such output lets a listener clearly visual

SAE-FD: Sparse Autoencoder Feature Distillation for Continual Learning of Large Language Models

arXiv:2605.25525v1 Announce Type: new Abstract: Continual learning enables large language models to adapt to evolving tasks without retraining from scratch, yet catastrophic forgetting remains a centr

SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness

arXiv:2605.25796v1 Announce Type: cross Abstract: Semantic-level watermarking (SWM) improves robustness against text modifications by treating sentences as the basic unit. However, robustness to parag

Scale When Needed: Adaptive Neuron-level Mixed Precision Quantization Aware Training

arXiv:2605.25054v1 Announce Type: cross Abstract: Deploying deep neural networks on resource-constrained 6G edge devices demands aggressive compression with minimal accuracy loss. Quantization-Aware T

Scaling Natural-Language Graph-Based Test Time Compute for Automated Theorem Proving

arXiv:2503.11657v3 Announce Type: replace Abstract: Large language models have demonstrated remarkable capabilities in natural language processing tasks requiring multi-step logical reasoning capabili

Scheduling LLM Inference with Uncertainty-Aware Output Length Predictions

arXiv:2604.00499v2 Announce Type: replace Abstract: To schedule LLM inference, the extit{shortest job first} (SJF) principle is favorable by prioritizing requests with short output lengths to avoid he