All entries

A Note on TurboQuant and the Earlier DRIVE/EDEN Line of Work

model-releasesarxiv-cs-lg

arXiv:2604.18555v1 Announce Type: new Abstract: This note clarifies the relationship between the recent TurboQuant work and the earlier DRIVE (NeurIPS 2021) and EDEN (ICML 2022) schemes. DRIVE is a 1-

A novel LSTM music generator based on the fractional time-frequency feature extraction

DGX agent

arXiv:2604.17823v1 Announce Type: cross Abstract: In this paper, we propose a novel approach for generating music based on an artificial intelligence (AI) system. We analyze the features of music and

researcharxiv-cs-cl

21 Apr 2026

Tutorials

A Practical Guide to LLM Fine Tuning

This guide from Databricks covers practical techniques and best practices for fine-tuning large language models, including methodologies for adapting pre-trained LLMs to specific tasks and domains. It

tutorialsdatabricks

A Probabilistic Consensus-Driven Approach for Robust Counterfactual Explanations

model-releasesarxiv-cs-lg

arXiv:2604.17494v1 Announce Type: new Abstract: Counterfactual explanations (CFEs) are essential for interpreting black-box models, yet they often become invalid when models are slightly changed. Exis

A proposal for PU classification under Non-SCAR using clustering and logistic model

arXiv:2604.17130v1 Announce Type: cross Abstract: The present study aims to investigate a cluster cleaning algorithm that is both computationally simple and capable of solving the PU classification wh

A Quasi-Experimental Developer Study of Security Training in LLM-Assisted Web Application Development

arXiv:2604.17763v1 Announce Type: cross Abstract: This paper presents a controlled quasi-experimental developer study examining whether a layer-based security training package is associated with impro

safetyarxiv-cs-lg

A Rapid Deployment Pipeline for Autonomous Humanoid Grasping Based on Foundation Models

arXiv:2604.17258v1 Announce Type: new Abstract: Deploying a humanoid robot to manipulate a new object has traditionally required one to two days of effort: data collection, manual annotation, 3D model

agentsarxiv-cs-ro

A Real-Time Bike-Pedestrian Safety System with Wide-Angle Perception and Evaluation Testbed for Urban Intersections

arXiv:2604.17046v1 Announce Type: new Abstract: Collisions between cyclists and pedestrians at urban intersections remain a persistent source of injuries, yet few systems attempt real-time warnings to

safetyarxiv-cs-cv

A Real-World Grasping-in-Clutter Performance Evaluation Benchmark for Robotic Food Waste Sorting

model-releasesarxiv-cs-ro

arXiv:2602.18835v2 Announce Type: replace Abstract: Food waste management is critical for sustainability, yet inorganic contaminants hinder recycling potential. Robotic automation accelerates sorting

A Ridge Too Far: Correcting Over-Shrinkage via Negative Regularization

arXiv:2508.17412v4 Announce Type: replace Abstract: Conventional regularization is designed to control variance, but in small-data regression it can also aggravate underfitting when predictive signal

Industry

A rose by any other name would smell as sweet

A rose by any other name would smell as sweet Marc Andreessen just revealed the Elon Musk philosophy that completely broke his brain: 'The best product in the world shouldn't even need a logo.' We all

industryelon-musk--x

A Scalable Nystrom-Based Kernel Two-Sample Test with Permutations

arXiv:2502.13570v4 Announce Type: replace-cross Abstract: Two-sample hypothesis testing-determining whether two sets of data are drawn from the same distribution-is a fundamental problem in statistics

A Sensitivity Approach to Causal Inference Under Limited Overlap

arXiv:2511.22003v2 Announce Type: replace-cross Abstract: Limited overlap between treated and control groups is a key challenge in observational analysis. Standard approaches like trimming importance

safetyarxiv-cs-lg

A Sugeno Integral View of Binarized Neural Network Inference

arXiv:2604.17967v1 Announce Type: cross Abstract: In this article, we establish a precise connection between binarized neural networks (BNNs) and Sugeno integrals. The advantage of the Sugeno integral

Tutorials

A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions

arXiv:2604.17312v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as a powerful post-training paradigm for enhancing the reasoning capabilities of large language models (LLMs). H

tutorialsarxiv-cs-lg

A Survey of Spatial Memory Representations for Efficient Robot Navigation

arXiv:2604.16482v1 Announce Type: new Abstract: As vision-based robots navigate larger environments, their spatial memory grows without bound, eventually exhausting computational resources, particular

A Survey on the Security of Long-Term Memory in LLM Agents: Toward Mnemonic Sovereignty

arXiv:2604.16548v1 Announce Type: cross Abstract: Research on large language model (LLM) security is shifting from 'will the model leak training data' to a more consequential question: can an agent wi

agentsarxiv-cs-cl

A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the Foundation Model Era

model-releasesarxiv-cs-lg

arXiv:2604.16586v1 Announce Type: new Abstract: Molecular property prediction integrates quantum chemistry, cheminformatics, and deep learning to connect molecular structure with physicochemical and b

A Text-To-Text Alignment Algorithm for Better Evaluation of Modern Speech Recognition Systems

arXiv:2509.24478v2 Announce Type: replace Abstract: Modern neural networks have greatly improved performance across speech recognition benchmarks. However, gains are often driven by frequent words wit

safetyarxiv-cs-cl

A Transformer and Prototype-based Interpretable Model for Contextual Sarcasm Detection

arXiv:2503.11838v2 Announce Type: replace Abstract: Sarcasm detection, with its figurative nature, poses unique challenges for affective systems designed to perform sentiment analysis. While these sys

A Two-Phase Deep Learning Framework for Adaptive Time-Stepping in High-Speed Flow Modeling

arXiv:2506.07969v2 Announce Type: replace Abstract: We consider the problem of modeling high-speed flows using machine learning methods. While most prior studies focus on low-speed fluid flows in whic

A Two-Stage Deep Learning Framework for Segmentation of Ten Gastrointestinal Organs from Coronal MR Enterography

arXiv:2604.17118v1 Announce Type: cross Abstract: Accurate segmentation of gastrointestinal (GI) organs in magnetic resonance enterography (MRE) is critical for diagnosing inflammatory bowel disease (

researcharxiv-cs-cv

A Two-Stage Multi-Modal MRI Framework for Lifespan Brain Age Prediction

arXiv:2604.16655v1 Announce Type: cross Abstract: The accurate quantification of brain age from MRI has emerged as an important biomarker of brain health. However, existing approaches are often restri

researcharxiv-cs-cv

A Unification of Discrete, Gaussian, and Simplicial Diffusion

arXiv:2512.15923v2 Announce Type: replace Abstract: To model discrete sequences such as DNA, proteins, and language using diffusion, practitioners must choose between three major methods: diffusion in

A Unified Compliance Aggregator Framework for Automated Multi-Tool Security Assessment of Linux Systems

arXiv:2604.17256v1 Announce Type: cross Abstract: Assessing the security posture of modern computing systems typically requires the use of multiple specialized tools. These tools focus on different as

A unified convergence theory for adaptive first-order methods in the nonconvex case, including AdaNorm, full and diagonal AdaGrad, Shampoo and Muo

arXiv:2604.17423v1 Announce Type: new Abstract: A unified framework for first-order optimization algorithms fornonconvex unconstrained optimization is proposed that uses adaptivelypreconditioned gradi

A Universal Avoidance Method for Diverse Multi-branch Generation

arXiv:2604.17323v1 Announce Type: new Abstract: Modern generative models still lack human-level creativity, particularly in multi-branch diversity. Prior approaches to address this problem often incur

researcharxiv-cs-cl

Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL

arXiv:2604.17073v1 Announce Type: new Abstract: Reinforcement fine-tuning improves the reasoning ability of large language models, but it can also encourage them to answer unanswerable queries by gues

Access GPT Image 2.0 natively in Hermes Agent Update now to get access - just run `hermes update` and select your image generation tool mode…

Access GPT Image 2.0 natively in Hermes Agent Update now to get access - just run `hermes update` and select your image generation tool model with `hermes tools` Introducing ChatGPT Images 2.0 A state

agentsnous-research--x

Across the enterprise, AI agents have outpaced the infrastructure meant to support them

As open-source platforms scramble to close the infrastructure gap, enterprises are discovering that autonomous operations expose a deeper problem than performance: control. The conversation around ent

agentssiliconangle

Applications

Active World-Model with 4D-informed Retrieval for Exploration and Awareness

arXiv:2604.16733v1 Announce Type: new Abstract: Physical awareness, especially in a large and dynamic environment, is shaped by sensing decisions that determine observability across space, time, and s

applicationsarxiv-cs-cv

Industry

AcuityMD, which provides AI tools that automate sales call recaps, CRM data entry, and more for medtech companies, raised an 80M Series C at a 955M valuation (Brock E.W. Turner/Axios)

Brock E.W. Turner / Axios: AcuityMD, which provides AI tools that automate sales call recaps, CRM data entry, and more for medtech companies, raised an 80M Series C at a 955M valuation — Medtech softw

industrytechmeme

Hardware

AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation

arXiv:2604.18348v1 Announce Type: new Abstract: Video diffusion transformers (DiTs) suffer from prohibitive inference latency due to quadratic attention complexity. Existing sparse attention methods e

hardwarearxiv-cs-cv

AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation

arXiv:2604.16625v1 Announce Type: new Abstract: Recent large language model (LLM) agents have shown promise in using execution feedback for test-time adaptation. However, robust self-improvement remai

agentsarxiv-cs-cl

Adaptive Forensic Feature Refinement via Intrinsic Importance Perception

arXiv:2604.16879v1 Announce Type: new Abstract: With the rapid development of generative models and multimodal content editing technologies, the key challenge faced by synthetic image detection (SID)

Adaptive Local Frequency Filtering for Fourier-Encoded Implicit Neural Representations

arXiv:2604.02846v2 Announce Type: replace Abstract: Fourier-encoded implicit neural representations (INRs) have shown strong capability in modeling continuous signals from discrete samples. However, c

Adaptive Quantized Planetary Crater Detection System for Autonomous Space Exploration

arXiv:2508.18025v4 Announce Type: replace-cross Abstract: Autonomous planetary exploration demands real-time, high-fidelity environmental perception. Standard deep learning models require massive comp

agentsarxiv-cs-cv

Tutorials

Adaptive receptive field-based spatial-frequency feature reconstruction network for few-shot fine-grained image classification

arXiv:2604.16936v1 Announce Type: new Abstract: Feature reconstruction techniques are widely applied for few-shot fine-grained image classification (FSFGIC). Our research indicates that one of the mai

tutorialsarxiv-cs-cv

Adaptive Text Anonymization: Learning Privacy-Utility Trade-offs via Prompt Optimization

arXiv:2602.20743v2 Announce Type: replace Abstract: Anonymizing textual documents is a highly context-sensitive problem: the appropriate balance between privacy protection and utility preservation var

Tools

Additional security bulletin updates include: • Clarification that account and project deletion do not eliminate environment variable risk •…

Additional security bulletin updates include: • Clarification that account and project deletion do not eliminate environment variable risk • Guidance on multi-factor authentication • Product updates t

toolsvercel--x

Applications

Adjustment of Cluster-Then-Predict Framework for Multiport Scatterer Load Prediction

arXiv:2602.08129v2 Announce Type: replace-cross Abstract: Predicting interdependent load values in multiport scatterers is challenging due to high dimensionality and complex dependence between impedan

applicationsarxiv-cs-lg

Advancing MAPF Toward the Real World: A Scalable Multi-Agent Realistic Testbed (SMART)

arXiv:2503.04798v3 Announce Type: replace Abstract: We present Scalable Multi-Agent Realistic Testbed (SMART), a realistic and efficient software tool for evaluating Multi-Agent Path Finding (MAPF) al

agentsarxiv-cs-ro

Advancing Vision Transformer with Enhanced Spatial Priors

arXiv:2604.18549v1 Announce Type: new Abstract: In recent years, the Vision Transformer (ViT) has garnered significant attention within the computer vision community. However, the core component of Vi

researcharxiv-cs-cv

Adversarial Arena: Crowdsourcing Data Generation through Interactive Competition

arXiv:2604.17803v1 Announce Type: cross Abstract: Post-training Large Language Models requires diverse, high-quality data which is rare and costly to obtain, especially in low resource domains and for

safetyarxiv-cs-lg

Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model Safety

arXiv:2604.18487v1 Announce Type: new Abstract: The Adversarial Humanities Benchmark (AHB) evaluates whether model safety refusals survive a shift away from familiar harmful prompt forms. Starting fro

Adverse-to-the-eXtreme Panoptic Segmentation: URVIS 2026 Study and Benchmark

arXiv:2604.16984v1 Announce Type: new Abstract: This paper presents the report of the URVIS 2026 challenge on adverse-to-extreme panoptic segmentation. As the first challenge of its kind, it attracted

AeroRAG: Structured Multimodal Retrieval-Augmented LLM for Fine-Grained Aerial Visual Reasoning

arXiv:2604.17889v1 Announce Type: new Abstract: Despite recent progress in multimodal large language models (MLLMs), reliable visual question answering in aerial scenes remains challenging. In such sc

AeroScene: Progressive Scene Synthesis for Aerial Robotics

model-releasesarxiv-cs-ro

arXiv:2603.23224v2 Announce Type: replace Abstract: Generative models have shown substantial impact across multiple domains, their potential for scene synthesis remains underexplored in robotics. This