All entries

Efficient Real-World Dehazing via Physics-Inspired Global-Local Decoupling

arXiv:2606.25732v1 Announce Type: new Abstract: Real-world single image dehazing is highly ill-posed due to spatially and spectrally varying scattering, while practical deployment demands lightweight

Model Releases

Efficient Remote Sensing Instance Segmentation with Linear-Time State Space Distilled Visual Foundation Models

DGX agent

arXiv:2606.25324v1 Announce Type: new Abstract: The computational complexity of Transformers scales quadratically with the number of tokens, which significantly constrains the efficiency of vision mod

model-releasesarxiv-cs-cv

25 Jun 2026

Industry

Elastic announces a ~7% reduction in its workforce, and says 'advances in AI and automation are letting us operate with leaner teams'; ESTC closed down 8.70% (Richard Speed/The Register)

Richard Speed / The Register: Elastic announces a ~7% reduction in its workforce, and says “advances in AI and automation are letting us operate with leaner teams”; ESTC closed down 8.70% — CEO says a

industrytechmeme

Elo-Disentangled Player-Style Embeddings for Human Chess via Rating-Conditioned Residual Move Model

arXiv:2606.25176v1 Announce Type: new Abstract: We study representation learning for individual human chess style: a per-player embedding learned from a player's move history such that inner products

Emcar: Embodied Controller for Animating Robots

arXiv:2606.26008v1 Announce Type: new Abstract: This chapter describes EMCAR, a novel software tool for programming robot motion that leverages the unique affordances of artistic practices such as pup

researcharxiv-cs-ro

Emergent Capabilities Arise Randomly from Learning Sparse Attention Patterns

arXiv:2606.25010v1 Announce Type: cross Abstract: Neural scaling laws for transformer language models predict smooth improvements in pretraining loss with increasing parameters, but downstream capabil

researcharxiv-cs-cl

Local Ai

EmotionAI: A Privacy-Preserving Computational Intelligence Pipeline for Speech-Emotion-Grounded Conversational Analysis

arXiv:2606.24941v1 Announce Type: cross Abstract: Reviewing recorded interviews for affective cues such as composure, hesitation and agitation is slow and subjective, and cloud services that could aut

local-aiarxiv-cs-ai

End-to-End Voice Intent Recognition for Spontaneous Human-Drone Interaction with Naive Users

arXiv:2606.24910v1 Announce Type: cross Abstract: Voice control offers an intuitive alternative to manual drone piloting, yet most existing systems rely on rigid command vocabularies that fail to hand

researcharxiv-cs-ai

Energy-Efficient CNN Acceleration with MSDF Digit-Serial Arithmetic on FPGA

arXiv:2606.25562v1 Announce Type: cross Abstract: This paper presents an energy-efficient hardware acceleration of the convolutional layers in the U-Net architecture for image segmentation, implemente

researcharxiv-cs-cv

Enhancing Brain MRI Anomaly Detection and Reasoning with ROI Rethink and Synthetic Data

arXiv:2606.25894v1 Announce Type: new Abstract: Medical vision-language models typically generate diagnoses through single-pass inference without indicating which image regions support their conclusio

Enhancing Clinician Decision-Making via Uncertainty-Aware Multi-Expert Fusion for Stroke Rehabilitation

arXiv:2606.24960v1 Announce Type: new Abstract: Tailoring stroke rehabilitation requires assessing how movements are organized, not merely if they succeed. Currently, this assessment is a rate-limitin

Enhancing Pathological VLMs with Cross-scale Reasoning

arXiv:2606.17412v3 Announce Type: replace Abstract: Pathological images are inherently multi-scale, requiring pathologists to integrate evidence from global tissue architecture at low magnification to

Entropy-Controlled Flow Matching

arXiv:2602.22265v2 Announce Type: replace-cross Abstract: Modern vision generators transport a base distribution to data through time-indexed measures, implemented as deterministic flows (ODEs) or sto

researcharxiv-cs-cv

Epistemic Bias Injection: Manipulating LLM Opinion via Selective Context Retrieval

arXiv:2512.00804v3 Announce Type: replace-cross Abstract: When answering user queries, LLMs often retrieve knowledge from external sources stored in retrieval-augmented generation (RAG) databases. The

EPTS: Elastic Post-Training Sparsity for Efficient Large Language Model Compression

model-releasesarxiv-cs-lg

arXiv:2606.25285v1 Announce Type: new Abstract: Post-Training Sparsity (PTS) has emerged as a crucial paradigm for compressing Large Language Models to facilitate efficient deployment on resource-cons

Erased, but Not Gone: Output Forgetting Is Not True Forgetting

arXiv:2606.25001v1 Announce Type: new Abstract: Machine unlearning (MU) is commonly judged by output forgetting, such as low forget-set accuracy or reduced logit-level membership inference. But if out

Error-Aware TF-IDF Retrieval-Augmented Generation for ASR Error Correction

arXiv:2606.24915v1 Announce Type: new Abstract: End-to-end automatic speech recognition systems frequently hallucinate rare entities and domain-specific terms, especially in low-resource languages. Wh

researcharxiv-cs-cl

Local Ai

ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo Matching

arXiv:2506.21091v2 Announce Type: replace Abstract: Stereo matching has become an increasingly important component of modern autonomous systems. Developing deep learning-based stereo matching models t

local-aiarxiv-cs-cv

Tutorials

ESTANet: Efficient Online Error Detection in Procedural Videos via Prediction Inconsistency

arXiv:2606.25317v1 Announce Type: new Abstract: An efficient and accurate system for detecting errors in procedural tasks is crucial for supporting human needs in daily life, as it can provide instant

tutorialsarxiv-cs-cv

Estimating condition number with Graph Neural Networks

arXiv:2603.10277v3 Announce Type: replace Abstract: In this paper, we propose a fast method for estimating the condition number of sparse matrices using graph neural networks (GNNs). For efficient dep

Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?

arXiv:2602.11988v2 Announce Type: replace-cross Abstract: A widespread practice in software development is to tailor coding agents to repositories using context files, such as AGENTS.md. Although this

agentsarxiv-cs-ai

Evaluating Japanese Dialect Robustness Across Speech and Text-based Large Language Models

arXiv:2606.25436v1 Announce Type: cross Abstract: Dialogue systems based on large language models (LLMs) have advanced significantly in recent years. However, dialectal variation remains a major chall

researcharxiv-cs-cl

Evaluating LLMs on Real-World Software Performance Optimization

model-releasesarxiv-cs-cl

arXiv:2606.25530v1 Announce Type: cross Abstract: Software performance optimization is a notoriously complex and manual task. Despite the growing use of Large Language Models (LLMs) for code refinemen

Evaluating performance and efficiency of the GitHub Copilot agentic harness across models and tasks

Explore how the GitHub Copilot agentic harness delivers strong results across multiple benchmarks and leading token efficiency, while maintaining flexibility to choose among more than 20 models. The p

agentsgithub-ai-blog

Evaluation Protocols and Validation for Cameras in Indoor Healthcare Monitoring

arXiv:2606.25284v1 Announce Type: new Abstract: Camera-based monitoring systems are increasingly adopted in healthcare settings for the continuous assessment of patient movement and activities. Howeve

safetyarxiv-cs-cv

EveLoad: Cognitive Workload Recognition from Event-Based Eye Movements

model-releasesarxiv-cs-lg

arXiv:2606.25177v1 Announce Type: new Abstract: Cognitive workload monitoring is important for adaptive rehabilitation and assistive interfaces, where task difficulty, pacing, and feedback should be a

Event-Adaptive Motion Planning with Distilled Vision-Language Model in Safety-Critical Situations

arXiv:2606.25629v1 Announce Type: new Abstract: Robot navigation in safety-critical scenarios faces significant challenges from unforeseen semantic events, where collisions arise primarily from the un

safetyarxiv-cs-ro

Industry

Every Homo naledi we know of is female, and the implications are fascinating

Analysis of ancient proteins from 23 fossilized teeth belonging to at least 20 Homo naledi individuals revealed no male genetic markers, suggesting the assemblage may represent females only. The findi

industryars-technica

Evidence for feature-specific error correction in LLMs

model-releasesarxiv-cs-lg

arXiv:2606.24964v1 Announce Type: new Abstract: Understanding the features of large language models (LLMs) is a central goal of interpretability. LLMs are commonly assumed to use superposition to repr

Evidential Perfusion Physics-Informed Neural Networks with Residual Uncertainty Quantification

arXiv:2603.09359v2 Announce Type: replace Abstract: Physics-informed neural networks (PINNs) have shown promise in addressing the ill-posed deconvolution problem in computed tomography perfusion (CTP)

excited to be speaking at @aiDotEngineer World Fair next week on Improving Agents, Continual Learning, and why we think a large part of it i…

excited to be speaking at @aiDotEngineer World Fair next week on Improving Agents, Continual Learning, and why we think a large part of it is...Data Mining! Trace Mining is how we understand agent beh

agentsharrison-chase--x

Exclusive: Chainguard extends Repository scanning and policies to Java, Python and containers

Secure software supply chain solution provider Chainguard Inc. today expanded its Chainguard Repository product with malware scanning, policy enforcement and visibility features that now cover Java pa

safetysiliconangle

Exclusive: LucidLink launches MCP server to give AI agents shared access to distributed files

model-releasessiliconangle

LucidLink Corp., the maker of a cloud network-attached storage system based on object storage technology, today extended its distributed file system technology into agentic artificial intelligence wit

Local Ai

Explainable Control Framework (XCF) based on Fuzzy Model-Agnostic Explanation and LLM Agent-Supported Interface

arXiv:2606.25941v1 Announce Type: cross Abstract: Increasing demand for precise and reliable control in complex scenarios has led to the development of increasingly sophisticated controllers, includin

local-aiarxiv-cs-ai

Tools

Explore the catalog: https://replit.com/integrations

Replit's integrations catalog allows developers to browse and discover third-party tools, services, and extensions that can be connected to their Replit projects to enhance functionality and streamlin

toolsreplit--x

Exploring Information Seeking Agent Consolidation

arXiv:2602.00585v2 Announce Type: replace Abstract: Information-seeking agents have emerged as a powerful paradigm for knowledge-intensive tasks, yet today's systems remain specialized for the open we

Expresso-AI: Explainable Video-Based Deep Learning Models for Depression Diagnosis

arXiv:2606.25606v1 Announce Type: new Abstract: Given the widespread prevalence of depression and its consequential impact on individuals and society, it is crucial to obtain objective measures for ea

researcharxiv-cs-cv

ext{DT}^2: Decision-Targeted Digital Twins

arXiv:2606.25923v1 Announce Type: new Abstract: A digital twin (DT) is a virtual model of a real-world system that can assist decision-making by simulating scenarios induced by different policies. How

safetyarxiv-cs-lg

Externalizing Research Synthesis and Validation in AI Scientists through a Research Harness

arXiv:2606.18874v2 Announce Type: replace Abstract: AI systems can increasingly automate scientific workflows, but the reasoning that links prior evidence, generated ideas, experiments and final claim

researcharxiv-cs-ai

ExTra: Exploratory Trajectory Optimization for Language Model Reinforcement Learning

arXiv:2606.24994v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) for language-model reasoning can fail at both extremes of task difficulty: easy prompts often prod

Extreme Meta-Classification for Large-Scale Zero-Shot Retrieval

arXiv:2606.25237v1 Announce Type: cross Abstract: We develop accurate and efficient solutions for large-scale retrieval tasks where novel (zero-shot) items can arrive continuously at a rapid pace. Con

Industry

Facebook brings back Facebook Creator Studio as a stand-alone app with built-in AI chatbot to help creators grow their audiences through personalized guidance (Aisha Malik/TechCrunch)

Aisha Malik / TechCrunch: Facebook brings back Facebook Creator Studio as a stand-alone app with built-in AI chatbot to help creators grow their audiences through personalized guidance — Facebook anno

industrytechmeme

Tutorials

Facebook’s Creator Studio has been revived as an AI companion app

Meta is bringing back the Facebook Creator Studio page manager, now 'reimagined' as a standalone AI companion app. The new app aims to make it easier for creators to connect with their audiences and s

tutorialsthe-verge-ai

FactorLibrary: From Polynomials to Circuits via Recursive Subgoals

arXiv:2606.25394v1 Announce Type: new Abstract: Finding minimal arithmetic circuits for polynomials over finite fields is a combinatorially hard problem central to algebraic complexity theory. We form

agentsarxiv-cs-lg

Failure Modes of Large Language Models on Research-Level Mathematics: A Taxonomy and an Empirical Characterisation

arXiv:2606.24902v1 Announce Type: cross Abstract: The 'First Proof' benchmark [1] posed ten research-level mathematics questions to the strongest publicly available LLMs and found them consistently wr

Falcon: Functional Assembly and Language for Compositional Reasoning in X-ray

arXiv:2606.25701v1 Announce Type: new Abstract: Conventional vision-language models are largely object-centric, focusing on detecting and describing individual entities. In safety-critical X-ray bagga

FAR-LIO: Enabling High-Speed Autonomy through Fast, Accurate, and Robust LiDAR-Inertial Odometry

model-releasesarxiv-cs-ro

arXiv:2606.26010v1 Announce Type: new Abstract: Robust and accurate odometry estimation is essential in modern robotics. In environments characterized by highly dynamic motion and sensor noise, odomet

Applications

fARfetch: Enabling Collocated AR-HRC in Large Visually Diverse Environments with VLM-Driven AR Content Adaptation

arXiv:2606.25162v1 Announce Type: cross Abstract: Augmented Reality (AR) can improve collocated human-robot collaboration by making robot state and intent visible and enabling intuitive control, yet l

applicationsarxiv-cs-cv