Search: “research”

Static Program Slicing Using Language Models With Dataflow-Aware Pretraining and Constrained Decoding

arXiv:2604.26961v1 Announce Type: cross Abstract: Static program slicing is a fundamental software engineering technique for isolating code relevant to specific variables. While recent learning-based

Research

Statistical Channel Fingerprint Construction for Massive MIMO: A Unified Tensor Learning Framework

DGX agent

arXiv:2604.27574v1 Announce Type: cross Abstract: Channel fingerprint (CF) is considered a key enabler for facilitating the acquisition of channel state information (CSI) in massive multiple-input mul

researcharxiv-cs-ai

1 May 2026

Stop Holding Your Breath: CT-Informed Gaussian Splatting for Dynamic Bronchoscopy

arXiv:2604.28179v1 Announce Type: new Abstract: Bronchoscopic navigation relies on registering endoscopic video to a preoperative CT scan, but respiratory motion deforms the airway by 5-20 mm, creatin

Student Classroom Behavior Recognition Based on Improved YOLOv8s

arXiv:2604.27293v1 Announce Type: new Abstract: In classroom teaching, student behavior can reflect their learning state and classroom participation, which is of great significance for teaching qualit

Syntactically-guided Information Maintenance in Sentence Comprehension

arXiv:2604.27468v1 Announce Type: new Abstract: Maintaining information in context is essential in successful real-time language comprehension, but maintenance is cognitively costly and can slow proce

TAFA-GSGC: Group-wise Scalable Point Cloud Geometry Compression with Progressive Residual Refinement

arXiv:2604.28045v1 Announce Type: new Abstract: Scalable compression is essential for bandwidth-adaptive transmission, yet most learned codecs are optimized for a fixed rate-distortion point, making r

Taming Noise-Induced Prototype Degradation for Privacy-Preserving Personalized Federated Fine-Tuning

arXiv:2604.27833v1 Announce Type: new Abstract: Prototype-based Personalized Federated Learning (ProtoPFL) enables efficient multi-domain adaptation by communicating compact class prototypes, but dire

The Download: a new Christian phone network, and debugging LLMs

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. A new US phone network for Christians aims to block porn and g

researchmit-tech-review

The Impact of AI-Generated Text on the Internet

arXiv:2604.26965v1 Announce Type: cross Abstract: The proliferation of AI-generated and AI-assisted text on the internet is feared to contribute to a degradation in semantic and stylistic diversity, f

The Polynomial Stein Discrepancy for Assessing Moment Convergence

arXiv:2412.05135v2 Announce Type: replace-cross Abstract: We propose a novel method for measuring the discrepancy between a set of samples and a desired posterior distribution for Bayesian inference.

TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents

arXiv:2601.02845v2 Announce Type: replace-cross Abstract: Long-horizon conversational agents have to manage ever-growing interaction histories that quickly exceed the finite context windows of large l

TIO-SHACL: Comprehensive SHACL validation for TMF Intent Ontologies

arXiv:2604.27359v1 Announce Type: new Abstract: Intent-based networking promises to revolutionize telecommunications network management by enabling operators to specify high-level goals rather than lo

Model Releases

To Build or Not to Build? Factors that Lead to Non-Development or Abandonment of AI Systems

model-releasesarxiv-cs-ai

arXiv:2604.28053v1 Announce Type: cross Abstract: Responsible AI research typically focuses on examining the use and impacts of deployed AI systems. Yet, there is currently limited visibility into the

To Diff or Not to Diff? Structure-Aware and Adaptive Output Formats for Efficient LLM-based Code Editing

arXiv:2604.27296v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for code editing, yet the prevalent full-code generation paradigm suffers from severe efficiency bo

Toward Personalized Digital Twins for Cognitive Decline Assessment: A Multimodal, Uncertainty-Aware Framework

arXiv:2604.27217v1 Announce Type: new Abstract: Cognitive decline is highly heterogeneous across individuals, which complicates prognosis, trial design, and treatment planning. We present the Personal

Toward Scalable SDN for LEO Mega-Constellations: A Graph Learning Approach

arXiv:2604.27478v1 Announce Type: new Abstract: Terrestrial network limitations drive the integration of non-terrestrial networks (NTNs), notably mega-constellations comprising thousands of low Earth

Towards Accelerated SCF Workflows with Equivariant Density-Matrix Learning and Analytic Refinement

arXiv:2604.27256v1 Announce Type: cross Abstract: We present extsc{dm-PhiSNet}, a physically constrained extsc{PhiSNet}-based equivariant model that predicts one-electron reduced density matrices (1-R

Towards Generalizable Mapping of Hedges and Linear Woody Features from Earth Observation Data: a national Product for Germany

arXiv:2604.27247v1 Announce Type: new Abstract: Hedges and other linear woody features provide valuable ecosystem services, particularly within intensively managed agricultural landscapes. They are ke

Transformer-Empowered Actor-Critic Reinforcement Learning for Sequence-Aware Service Function Chain Partitioning

arXiv:2504.18902v2 Announce Type: replace-cross Abstract: In the forthcoming era of 6G networks, characterized by unprecedented data rates, ultra-low latency, and ubiquitous connectivity, effective ma

TypeBandit: Type-Level Context Allocation and Reweighting for Effective Attribute Completion in Heterogeneous Graph Neural Networks

arXiv:2604.27356v1 Announce Type: cross Abstract: Heterogeneous graphs are widely used to model multi-relational systems, but missing node attributes remain a major bottleneck for downstream learning.

Uncertainty Quantification Framework for Aerial and UAV Photogrammetry through Error Propagation

arXiv:2507.13486v2 Announce Type: replace Abstract: Uncertainty quantification of the photogrammetry process is essential for providing per-point accuracy credentials of the point clouds. Unlike airbo

Understanding and Improving Length Generalization in Hierarchical Sparse Attention Models

arXiv:2510.17196v3 Announce Type: replace-cross Abstract: Effectively processing long contexts is a critical challenge for language models. While standard Transformers are limited by quadratic complex

Uni-HOI:A Unified framework for Learning the Joint distribution of Text and Human-Object Interaction

arXiv:2604.27491v1 Announce Type: new Abstract: Modeling 4D human-object interaction (HOI) is a compelling challenge in computer vision and an essential technology powering virtual and mixed-reality a

Universal statistical laws governing culinary design

arXiv:2604.28021v1 Announce Type: cross Abstract: Cooking is a cultural expression of human creativity that transcends geography and time through the orchestration of ingredients and techniques, much

Unsupervised Electrofacies Classification and Porosity Characterization in the Offshore Keta Basin Using Wireline Logs

arXiv:2604.27126v1 Announce Type: new Abstract: This study presents an unsupervised machine learning workflow for electrofacies analysis in the offshore Keta Basin, Ghana, where core data are scarce.

Unsupervised Machine Learning for Osteoporosis Diagnosis Using Singh Index Clustering on Hip Radiographs

arXiv:2411.15253v2 Announce Type: replace-cross Abstract: Osteoporosis, a prevalent condition among the aging population worldwide, is characterized by diminished bone mass and altered bone structure,

Validating the Clinical Utility of CineECG 3D Reconstructions through Cross-Modal Feature Attribution

arXiv:2604.27017v1 Announce Type: cross Abstract: Deep learning models for 12-lead electrocardiogram (ECG) analysis achieve high diagnostic performance but lack the intuitive interpretability required

Vanishing Contributions: A Unified Framework for Smooth and Iterative Model Compression

arXiv:2510.09696v2 Announce Type: replace-cross Abstract: The increasing scale of Deep Neural Networks (DNNs) increases the need for compression techniques such as pruning, quantization, and low-rank

VibroML: an automated toolkit for high-throughput vibrational analysis and dynamic instability remediation of crystalline materials using machine-learned potentials

arXiv:2604.27685v1 Announce Type: cross Abstract: While machine-learned interatomic potentials (MLIPs) accelerate phonon dispersion calculations, merely identifying dynamical instabilities in computat

VTBench: A Multimodal Framework for Time-Series Classification with Chart-Based Representations

arXiv:2604.27259v1 Announce Type: new Abstract: Time-series classification (TSC) has advanced significantly with deep learning, yet most models rely solely on raw numerical inputs, overlooking alterna

We now know the Iran war price tag is more like $50 billion - hundreds of dollars per household - and counting. It's enough to cover all the…

We now know the Iran war price tag is more like $50 billion - hundreds of dollars per household - and counting. It's enough to cover all the health insurance premium credits that the Republicans got r

researchyann-lecun--x

Why Mean Pooling Works: Quantifying Second-Order Collapse in Text Embeddings

arXiv:2604.27398v1 Announce Type: new Abstract: For constructing text embeddings, mean pooling, which averages token embeddings, is the standard approach. This paper examines whether mean pooling actu

Why Self-Supervised Encoders Want to Be Normal

arXiv:2604.27743v1 Announce Type: cross Abstract: We develop a geometric and information-theoretic framework for encoder-decoder learning built on the Information Bottleneck (IB) principle. Recasting

YOSE: You Only Select Essential Tokens for Efficient DiT-based Video Object Removal

arXiv:2604.27322v1 Announce Type: new Abstract: Recent advances in Diffusion Transformer (DiT)-based video generation technologies have shown impressive results for video object removal. However, thes

ZAYAN: Disentangled Contrastive Transformer for Tabular Remote Sensing Data

arXiv:2604.27606v1 Announce Type: cross Abstract: Learning informative representations from tabular data in remote sensing and environmental science is challenging due to heterogeneity, scarce labels,

2D and 3D Grasp Planners for the GET Asymmetrical Gripper

arXiv:2604.26212v1 Announce Type: new Abstract: In this paper, we introduce GET-2D-1.0, a fast grasp planner for the GET asymmetrical gripper that operates from a single-view RGB-D image, using the Fe

researcharxiv-cs-ro

A Dataset for Automatic Vocal Mode Classification

arXiv:2601.18339v2 Announce Type: replace-cross Abstract: The Complete Vocal Technique (CVT) is a school of singing developed in the past decades by Cathrin Sadolin et al.. CVT groups the use of the v

A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring

arXiv:2602.23163v3 Announce Type: replace Abstract: Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanis

A Diffeomorphism Groupoid and Algebroid Framework for Discontinuous Image Registration

arXiv:2603.11806v2 Announce Type: replace-cross Abstract: In this paper, we propose a novel mathematical framework for piecewise diffeomorphic image registration that involves discontinuous sliding mo

A Dual-Task Paradigm to Investigate Sentence Comprehension Strategies in Language Models

arXiv:2604.26351v1 Announce Type: new Abstract: Language models (LMs) behave more like humans when their cognitive resources are restricted, particularly in predicting sentence processing costs such a

A Multimodal Depth-Aware Method For Embodied Reference Understanding

arXiv:2510.08278v3 Announce Type: replace Abstract: Embodied Reference Understanding requires identifying a target object in a visual scene based on both language instructions and pointing cues. While

A New Semisupervised Technique for Polarity Analysis using Masked Language Models

arXiv:2604.26230v1 Announce Type: new Abstract: I developed a new version of Latent Semantic Scaling (LSS) employing word2vec as a masked language model. Unlike original spatial models, it assigns pol

A Priori Sampling of Transition States with Guided Diffusion

arXiv:2603.25980v2 Announce Type: replace-cross Abstract: Transition states, the first-order saddle points on the potential energy surfaces, govern the kinetics and mechanisms of chemical reactions an

A Quantitative Confirmation of the Currier Language Distinction

arXiv:2604.25979v1 Announce Type: cross Abstract: We present a quantitative analysis of character-pair substitution ratios in the Voynich manuscript, testing whether Currier's A/B language distinction

A Self-Calibrating Framework for Analog Circuit Sizing Using LLM-Derived Analytical Equations

arXiv:2604.07387v2 Announce Type: replace-cross Abstract: We present a design automation framework for analog circuit sizing that produces calibrated, topology-specific analytical equations from raw c

ACPO: Anchor-Constrained Perceptual Optimization for Diffusion Models with No-Reference Quality Guidance

arXiv:2604.26348v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in image generation, yet their training is predominantly driven by full-reference objectives that en

Adaptive Transform Coding for Semantic Compression

arXiv:2604.26492v1 Announce Type: cross Abstract: Visual data compression is shifting from human-centered reconstruction to machine-oriented representation coding. In this setting, an image is often m

Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control

arXiv:2604.26326v1 Announce Type: cross Abstract: Reinforcement learning (RL) has unlocked complex reasoning abilities in large language models (LLMs). However, most RL algorithms suffer from performa