research

Differential Subgroup Discovery: Characterizing Where Two Populations Differ, and Why

arXiv:2604.27741v1 Announce Type: new Abstract: We study the problem of understanding where two populations differ within a feature space, which we formalize in the concept of a differential subgroup:

Research

Diffusion-OAMP for Joint Image Compression and Wireless Transmission

DGX agent

arXiv:2604.27952v1 Announce Type: cross Abstract: Joint image compression and wireless transmission remain relatively underexplored compared to generic image restoration, despite its importance in pra

researcharxiv-cs-lg

1 May 2026

Do Sparse Autoencoders Capture Concept Manifolds?

arXiv:2604.28119v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are widely used to extract interpretable features from neural network representations, often under the implicit assumption

Dynamic Cluster Data Sampling for Efficient and Long-Tail-Aware Vision-Language Pre-training

arXiv:2604.27932v1 Announce Type: new Abstract: The computational cost of training a vision-language model (VLM) can be reduced by sampling the training data. Previous work on efficient VLM pre-traini

EAG-PT: Emission-Aware Gaussians and Path Tracing for Diffuse Indoor Scene Reconstruction and Editing

arXiv:2601.23065v2 Announce Type: replace-cross Abstract: Recent radiance-field-based reconstruction methods, such as NeRF and 3DGS, achieve high visual fidelity for indoor scenes, but often break dow

Ease of dependency distance minimization in star-like structures

arXiv:2604.28034v1 Announce Type: new Abstract: The syntactic structure of a sentence can be represented as a tree where edges indicate syntactic dependencies between words. When that structure is a s

Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed

arXiv:2512.14067v2 Announce Type: replace-cross Abstract: Diffusion language models (dLMs) have emerged as a promising paradigm that enables parallel, non-autoregressive generation, but their learning

Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing

arXiv:2604.28142v1 Announce Type: cross Abstract: Multivector retrieval models achieve state-of-the-art effectiveness through fine-grained token-level representations, but their deployment incurs subs

EmDT: Embedding Diffusion Transformer for Tabular Data Generation in Fraud Detection

arXiv:2603.13566v2 Announce Type: replace-cross Abstract: Imbalanced datasets pose a difficulty in fraud detection, as classifiers are often biased toward the majority class and perform poorly on rare

Emotion-Aware Clickbait Attack in Social Media

arXiv:2604.27369v1 Announce Type: new Abstract: Clickbait is characterized by disproportionately high emotional intensity relative to informational content, often reinforced by specific structural pat

Enabling Reconfiguration-Communication Overlap for Collective Communication in Optical Networks

arXiv:2510.19322v3 Announce Type: replace-cross Abstract: Collective communication (CC) is critical for scaling distributed machine learning (DML). The predictable traffic patterns of DML present a gr

Entropy-Dominated Temporal Vocal Dynamics as Digital Biomarkers for Depression Detection

arXiv:2604.26998v1 Announce Type: cross Abstract: Automated depression detection often relies on static aggregation of conversational signals, potentially obscuring clinically meaningful behavioral dy

Evaluating Epistemic Guardrails in AI Reading Assistants: A Behavioral Audit of a Minimal Prototype

arXiv:2604.27275v1 Announce Type: cross Abstract: Large language model (LLM) reading assistants are increasingly used in settings that require interpretation rather than simple retrieval. In these con

Evaluating TabPFN for Mild Cognitive Impairment to Alzheimer's Disease Conversion in Data Limited Settings

arXiv:2604.27195v1 Announce Type: new Abstract: Accurate prediction of conversion from Mild Cognitive Impairment (MCI) to Alzheimers Diseases (AD) is essential for early intervention, however, develop

EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory

arXiv:2604.27695v1 Announce Type: cross Abstract: Long-term conversational memory requires retrieving evidence scattered across multiple sessions, yet single-pass retrieval fails on temporal and multi

Explainable Load Forecasting with Covariate-Informed Time Series Foundation Models

arXiv:2604.28149v1 Announce Type: new Abstract: Time Series Foundation Models (TSFMs) have recently emerged as general-purpose forecasting models and show considerable potential for applications in en

Exploring the Adoption Intention in Using AI-Enabled Educational Tools Among Preservice Teachers in the Philippines: A Partial-Least Square Modeling

arXiv:2604.27346v1 Announce Type: cross Abstract: This study examines the factors influencing pre-service teachers' behavioral intention to use AI-enabled educational tools during their practicum, usi

Exponential families from a single KL identity

arXiv:2604.28036v1 Announce Type: new Abstract: Exponential families encompass the distributions central to modern machine learning -- softmax, Gaussians, and Boltzmann distributions -- and underlie t

Faster 3D Gaussian Splatting Convergence via Structure-Aware Densification

arXiv:2604.28016v1 Announce Type: new Abstract: 3D Gaussian Splatting has emerged as a powerful scene representation for real-time novel-view synthesis. However, its standard adaptive density control

Fitting Horn DL Ontologies to ABox and Query Examples: A Tale of Simulation Quantifiers and Finite Models

arXiv:2604.26976v1 Announce Type: cross Abstract: We study the problem of fitting a description logic (DL) ontology to a given set of positive and negative examples that take the form of an ABox and a

FMCL: Class-Aware Client Clustering with Foundation Model Representations for Heterogeneous Federated Learning

arXiv:2604.27510v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative model training across distributed clients without sharing raw data, yet its performance deteriorates und

Focal Modulation and Bidirectional Feature Fusion Network for Medical Image Segmentation

arXiv:2510.20933v2 Announce Type: replace-cross Abstract: Medical image segmentation is essential for clinical applications such as disease diagnosis, treatment planning, and disease development monit

Frequency-Adaptive Discrete Cosine-ViT-ResNet Architecture for Sparse-Data Vision

arXiv:2505.22701v3 Announce Type: replace Abstract: A major challenge in rare animal image classification is the scarcity of data, as many species usually have only a small number of labeled samples.

From Coarse to Fine: Benchmarking and Reward Modeling for Writing-Centric Generation Tasks

arXiv:2604.27453v1 Announce Type: new Abstract: Large language models have achieved remarkable progress in text generation but still struggle with generative writing tasks. In terms of evaluation, exi

From Competition to Collaboration: Designing Sustainable Mechanisms Between LLMs and Online Forums

arXiv:2602.04572v2 Announce Type: replace Abstract: While Generative AI (GenAI) systems draw users away from (Q&A) forums, they also depend on the very data those forums produce to improve their perfo

FUN: A Focal U-Net Combining Reconstruction and Object Detection for Snapshot Spectral Imaging

arXiv:2604.27653v1 Announce Type: new Abstract: Conventional push-broom hyperspectral imaging suffers from slow acquisition speeds, precluding real-time object detection; in contrast, snapshot spectra

General Uncertainty Estimation with Delta Variances

arXiv:2502.14698v2 Announce Type: replace-cross Abstract: Decision makers may suffer from uncertainty induced by limited data. This may be mitigated by accounting for epistemic uncertainty, which is h

Generative Human Geometry Distribution

arXiv:2503.01448v5 Announce Type: replace Abstract: Realistic human geometry generation is an important yet challenging task, requiring both the preservation of fine clothing details and the accurate

Generative structure search for efficient and diverse discovery of molecular and crystal structures

arXiv:2604.27636v1 Announce Type: new Abstract: Predicting stable and metastable structures is central to molecular and materials discovery, but remains limited by the cost of searching high-dimension

Geometry-Calibrated Conformal Abstention for Language Models

arXiv:2604.27914v1 Announce Type: new Abstract: When language models lack relevant knowledge for a given query, they frequently generate plausible responses that can be hallucinations, rather than adm

Graph-Based Biomarker Discovery and Interpretation for Alzheimer's Disease

arXiv:2411.18796v2 Announce Type: replace Abstract: Early diagnosis and discovery of therapeutic drug targets are crucial objectives for effective management of Alzheimer's Disease (AD). Current appro

GRASP: group-Shapley feature selection for patients

arXiv:2602.11084v2 Announce Type: replace-cross Abstract: Feature selection remains a major challenge in medical prediction, where existing approaches such as LASSO often lack robustness and interpret

GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow

arXiv:2603.26571v3 Announce Type: replace-cross Abstract: At ultra-low bitrates, high-fidelity reconstruction requires sampling plausible videos from the posterior rather than regressing to oversmooth

HATS: An Open data set Integrating Human Perception Applied to the Evaluation of Automatic Speech Recognition Metrics

arXiv:2604.27542v1 Announce Type: new Abstract: Conventionally, Automatic Speech Recognition (ASR) systems are evaluated on their ability to correctly recognize each word contained in a speech signal.

HAVEN: Hybrid Automated Verification ENgine for UVM Testbench Synthesis with LLMs

arXiv:2604.27643v1 Announce Type: cross Abstract: Integrated Circuit (IC) verification consumes nearly 70% of the IC development cycle, and recent research leverages Large Language Models (LLMs) to au

HiMix: Hierarchical Artifact-aware Mixup for Generalized Synthetic Image Detection

arXiv:2604.27903v1 Announce Type: new Abstract: The rapid evolution of generative models has enabled the creation of highly realistic and diverse synthetic images, posing significant challenges to rel

Hypencoder Revisited: Reproducibility and Analysis of Non-Linear Scoring for First-Stage Retrieval

arXiv:2604.27037v1 Announce Type: cross Abstract: The Hypencoder, proposed by Killingback et al., is a retrieval framework that replaces the fixed inner-product scoring function used in standard bi-en

Hyper-Dimensional Fingerprints as Molecular Representations

arXiv:2604.27810v1 Announce Type: new Abstract: Computational molecular representations underpin virtual screening, property prediction, and materials discovery. Conventional fingerprints are efficien

Hyperspectral Image Classification via Efficient Global Spectral Supertoken Clustering

arXiv:2604.27364v1 Announce Type: new Abstract: Hyperspectral image classification demands spatially coherent predictions and precise boundary delineation. Yet prevailing superpixel-based methods face

Hypnopaedia-Aware Machine Unlearning via Psychometrics of Artificial Mental Imagery

arXiv:2410.05284v2 Announce Type: replace-cross Abstract: Neural backdoors represent insidious cybersecurity loopholes that render learning machinery vulnerable to unauthorised manipulations, potentia

I think the expression is “pulling the ladder”! All labs trained their models by distilling (at the very least distilling the web) which all…

I think the expression is “pulling the ladder”! All labs trained their models by distilling (at the very least distilling the web) which allowed them to become the fastest growing businesses in the hi

researchyann-lecun--x

If you want to help the world make sense of AGI and accelerate its arrival, consider joining the ARC Prize foundation. Two roles currently o…

researchfrancois-chollet--x

If you want to help the world make sense of AGI and accelerate its arrival, consider joining the ARC Prize foundation. Two roles currently open: Game Platform Engineering Lead, and Model Testing & Ana

IKSPARK: Obstacle-Aware Inverse Kinematics via Convex Optimization

arXiv:2403.12235v2 Announce Type: replace Abstract: Inverse kinematics (IK) is central to robot control and motion planning, yet its nonlinear kinematic mapping makes it inherently nonconvex and parti

researcharxiv-cs-ro

In-Context Examples Suppress Scientific Knowledge Recall in LLMs

arXiv:2604.27540v1 Announce Type: new Abstract: Scientific reasoning rarely stops at what is directly observable; it often requires uncovering hidden structure from data. From estimating reaction cons

In Line with Context: Repository-Level Code Generation via Context Inlining

arXiv:2601.00376v2 Announce Type: replace-cross Abstract: Repository-level code generation has attracted growing attention in recent years. Unlike function-level code generation, it requires the model

Inexpensive seafloor-hopping submersibles could stoke deep-sea science—and mining

Smack dab between Australia and South America, the US National Oceanic and Atmospheric Administration (NOAA) research vessel Rainier is currently on a mission to map more than 8,000 square nautical mi

researchmit-tech-review

Instruction-Guided Poetry Generation in Arabic and Its Dialects

arXiv:2604.27766v1 Announce Type: cross Abstract: Poetry has long been a central art form for Arabic speakers, serving as a powerful medium of expression and cultural identity. While modern Arabic spe

InterPartAbility: Text-Guided Part Matching for Interpretable Person Re-Identification

arXiv:2604.27122v1 Announce Type: new Abstract: Text-to-image person re-identification (TI-ReID) relies on natural-language text description to retrieve top matching individuals from a large gallery o