All entries

EgoExo-Con: Exploring View-Invariant Video Temporal Understanding

arXiv:2510.26113v2 Announce Type: replace Abstract: Do Video-LLMs have consistent temporal understanding when videos capture the same event from different viewpoints? To study this question, we introd

EgoInfinity: A Web-Scale 4D Hand-Object Interaction Data Engine for Any-View Robot Retargeting and Video-to-Action Robot Learning

DGX agent

arXiv:2606.17385v2 Announce Type: replace Abstract: Internet videos constitute the largest reservoir of embodied human manipulation knowledge, yet converting arbitrary RGB footage into actionable robo

agentsarxiv-cs-ro

23 Jun 2026

Eigenspace-Based Clustering for Personalized System Identification

arXiv:2606.20811v1 Announce Type: cross Abstract: We study the problem of system identification in heterogeneous settings, where different systems may follow distinct underlying dynamics. Existing clu

local-aiarxiv-cs-lg

ELADO: Elliptic PDE Assessment Datasets for Operator Learning

arXiv:2606.20771v1 Announce Type: new Abstract: We introduce ELADO (Elliptic PDE Assessment Datasets for Operator Learning), a systematic benchmark suite constructed to show and quantify failure modes

ELDiff: When Evidential Learning Meets Text-to-Image Diffusion

arXiv:2606.20924v1 Announce Type: new Abstract: In multi-object text-to-image (T2I) diffusion, ensuring semantic consistency between textual prompts and generated visual content is crucial for image s

Elephant alert! AI warning systems aim to avoid deadly clashes

India is home to about 60% of the world’s wild Asian elephants, and around 80% of the animals’ habitat lies outside protected areas, according to the Ministry of Environment, Forest, and Climate Chang

researchmit-tech-review

Hardware

Eli Lilly plans to use its $7.3B cash reserve to fund an 'App Store' for biotech scientists after launching a data center with 1,016 Blackwell chips in 2025 (Patrick Temple-West/Financial Times)

Patrick Temple-West / Financial Times: Eli Lilly plans to use its $7.3B cash reserve to fund an “App Store” for biotech scientists after launching a data center with 1,016 Blackwell chips in 2025 — Mo

hardwaretechmeme

Elon confirms 'Starmind' will be the official name of @SpaceX's AI satellite constellation. Earlier this year, SpaceX filed a request with t…

Elon confirms 'Starmind' will be the official name of @SpaceX's AI satellite constellation. Earlier this year, SpaceX filed a request with the FCC to launch and operate a constellation of 1 million AI

Elon Musk just confirmed that ‘Starmind’ will be the official name of the SpaceX AI satellite constellation

I cannot verify this claim as the URL and tweet ID appear to be fabricated (future date timestamp). No credible reports confirm that SpaceX has announced an 'AI satellite constellation' officially nam

@elonmusk USAID was basically hydra.

@elonmusk USAID was basically hydra. When you read about how USAID was started by ex-CIA people, funneled state department money through NGOs into crazy subterfuge and censorship that no taxpayer woul

@elonmusk Using their logic, you can argue USAID caused 9/11 then murdered 4.7 million people after. https://x.com/MikeBenzCyber/status/2069…

@elonmusk Using their logic, you can argue USAID caused 9/11 then murdered 4.7 million people after. https://x.com/MikeBenzCyber/status/2069304710947881243 USAID funded Osama Bin Laden's Mujahideen, w

@elonmusk We need to rename USAID to 'USCON' to more accurately reflect what the money was being used for.

I can't verify this specific post without access to the URL. However, this appears to be a social media post suggesting a renaming of USAID (U.S. Agency for International Development) with an implied

Embedding Linear Equality Constraints in Probabilistic Neural Networks for Dynamic Modelling

arXiv:2606.21728v1 Announce Type: new Abstract: Machine learning models are increasingly used to model chemical process systems, yet they often lack principled uncertainty quantification and mechanism

EmbodiedUS-FS: Fast Slow Intelligence for Ultrasound Robotics

arXiv:2606.22319v1 Announce Type: cross Abstract: Robotic ultrasound scanning in real clinical environments requires both high-level clinical workflow reasoning and low-level closed-loop execution. Ph

safetyarxiv-cs-cv

EML Trees Are Universal Approximators

arXiv:2606.23179v1 Announce Type: new Abstract: The recently introduced EML (Exp-Minus-Log) function acts as continuous analogue of NAND gates, providing a compositional building block capable of repr

Empowering Embodied AI in 6G Networks: Architecture, Enablers, and Open Challenges

arXiv:2606.20592v1 Announce Type: cross Abstract: Embodied artificial intelligence (AI) is emerging as a key driver of the sixth-generation (6G) wireless networks by enabling agents that continuously

agentsarxiv-cs-lg

Enabling Cloud-Level Accuracy in Edge AI through IoT Data Preprocessing

arXiv:2606.22496v1 Announce Type: cross Abstract: Large language models (LLMs) offer a natural-language interface for interpreting Internet of Things (IoT) sensor data in smart environments; however,

local-aiarxiv-cs-lg

Encoder-Decoder Manifold Alignment for Idempotent Generation

arXiv:2606.22304v1 Announce Type: new Abstract: Recently, several learning paradigms have been introduced to enforce idempotency in generative models. The goal is to ensure that repeated application o

safetyarxiv-cs-lg

End-to-End RAG Workflow: How Retrieval Augmented Generation Works

Retrieval Augmented Generation (RAG) is a technique that combines information retrieval with generative AI to enhance model outputs by fetching relevant external documents or data before generating re

industrydatabricks

Energy-based Compositional Diffusion Planning

arXiv:2606.21646v1 Announce Type: new Abstract: Compositional diffusion planners aim to solve long-horizon robotic tasks using short training trajectories. Yet, current approaches often rely on the he

local-aiarxiv-cs-ro

Energy Injection Identification enabled Disaggregation with Deep Multi-Task Learning

arXiv:2508.14600v4 Announce Type: replace Abstract: Non-Intrusive Load Monitoring (NILM) offers a cost-effective method to obtain fine-grained appliance-level energy consumption in smart homes and bui

Engineered “mini livers” could be injected as an alternative to transplantation

A technology developed by Professor Sangeeta Bhatia, SM ’93, PhD ’97, and colleagues could offer new hope to the thousands of Americans with chronic liver disease who are waiting for an organ transpla

researchmit-tech-review

Enhancing Cognitive Workload Classification Using Integrated LSTM Layers and CNNs for fNIRS Data Analysis

arXiv:2407.15901v2 Announce Type: replace Abstract: Functional near-infrared spectroscopy (fNIRS) is employed as a non-invasive method to monitor functional brain activation by capturing changes in th

Enhancing Creativity in 3D Generative Design via a TRIZ-Inspired Text-to-CAD Framework

arXiv:2606.21378v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have demonstrated significant potential in supporting engineering design tasks, including computer-aided

agentsarxiv-cs-lg

Enhancing Differentially Private Mechanisms via Empirical Bayes

arXiv:2606.21107v1 Announce Type: new Abstract: Differential privacy (DP) has become the gold standard for ensuring the privacy protection of machine learning and statistical algorithms in recent deca

Enhancing IMU-Based Online Handwriting Recognition via Contrastive Learning with Zero Inference Overhead

arXiv:2602.07049v2 Announce Type: replace Abstract: Online handwriting recognition using inertial measurement units opens up handwriting on paper as input for digital devices. Doing it on edge hardwar

safetyarxiv-cs-cv

Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation

arXiv:2606.22429v1 Announce Type: new Abstract: Graph neural networks (GNNs) tightly couple their input-output parameters to dataset-specific feature spaces and target sets, exhibiting limited transfe

safetyarxiv-cs-lg

Enhancing Protein Representation Learning via Manifold Restore Mixing

arXiv:2606.22307v1 Announce Type: new Abstract: Data augmentation (DA) has been proven to be an effective means for improving protein representation learning (PRL) by generating additional training sa

Enhancing Road Safety: An IoT-Based Accident Detection and Prevention Mechanism

arXiv:2606.22381v1 Announce Type: cross Abstract: Road traffic accidents remain a critical global crisis, consistently serving as a primary driver of preventable mortality and severe injury. These inc

safetyarxiv-cs-cv

Applications

Enhancing Symbolic Regression and Universal Physics-Informed Neural Networks with Dimensional Analysis

arXiv:2411.15919v2 Announce Type: replace Abstract: In engineering and applied mathematics, developing accurate mathematical models to predict and understand real-world phenomena is of utmost importan

applicationsarxiv-cs-lg

Enlight: Fast Low-Light Image Enhancement via Multi-Objective Optimization and Shadow-Aware Refinement

arXiv:2606.21674v1 Announce Type: new Abstract: We present ENLIGHT, a fast and training free framework for low-light image enhancement based on direct optimization of a perceptual objective. Unlike de

local-aiarxiv-cs-cv

EnTrust: Modeling Inter-Modal Conflict for Trustworthy Multimodal Medical Image Analysis

arXiv:2606.21384v1 Announce Type: new Abstract: Multimodal medical imaging fuses complementary anatomical and functional information, yet modalities frequently disagree in pathologically heterogeneous

local-aiarxiv-cs-cv

ENVS: Environment-Native Verified Search for Long-Horizon GUI Agents

arXiv:2606.22948v1 Announce Type: cross Abstract: As multimodal agents move from interface understanding to real software control, successful trajectory discovery in live desktop environments becomes

EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors

arXiv:2602.21218v2 Announce Type: replace-cross Abstract: High-quality data is essential for modern machine learning, yet many valuable corpora are sensitive and cannot be freely shared. Synthetic dat

safetyarxiv-cs-lg

Equilibrium with Internal Transfers

arXiv:2606.20960v1 Announce Type: cross Abstract: Nash equilibrium (NE) arises from selfish utility maximization, yet its social welfare can be arbitrarily far from optimal. Moreover, computing an NE

agentsarxiv-cs-lg

Error Highways: Scaling Predictive Coding to Very Deep Networks

arXiv:2606.22744v1 Announce Type: new Abstract: Predictive coding networks (PCNs) offer a biologically-plausible, local-learning alternative to back-propagation of errors (backprop). Nevertheless, the

local-aiarxiv-cs-lg

Escaping the Variance Trap: Jacobian-Free Dynamics for Root-Finding Bilevel Optimization

arXiv:2606.22433v1 Announce Type: new Abstract: Many central machine learning tasks, from entropy tuning in reinforcement learning to equilibrating generative adversarial networks, are fundamentally s

Essential Subspace Merging for Multi-Task Learning

arXiv:2606.19164v2 Announce Type: replace Abstract: Model merging aims to enable multi-task learning by integrating the capabilities of multiple models fine-tuned from the same pre-trained checkpoint

Applications

Estimating Learners' Skill Acquisition Without Temporal Information

arXiv:2606.20611v1 Announce Type: cross Abstract: Recent research in educational data mining, especially knowledge tracing, has focused on predicting learners' future knowledge states to support adapt

applicationsarxiv-cs-lg

Evals are the new PRDs, @hwchase17 It might be my takeaway of the @LangChain Chicago meetup tonight.

Harrison Chase suggests that evaluations (evals) are becoming as critical to AI/LLM development as Product Requirements Documents (PRDs) traditionally were, implying a shift in how teams validate and

agentsharrison-chase--x

Evaluating and Enhancing Negation Comprehension in Remote Sensing MLLMs

arXiv:2606.20177v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in various Remote Sensing (RS) tasks. However, their ability to compre

Evaluating Document-Tuned Transformer Representations for Person-level Mental Health Assessment

arXiv:2606.21622v1 Announce Type: cross Abstract: Person-level psychological assessment requires aggregating meaning across many messages from the same individual, a task that document-level training

Evaluating Large Language Models for Hausa and Fongbe Machine Translation: Benchmarks, Failures, and Metric Reliability

arXiv:2606.22269v1 Announce Type: cross Abstract: We investigate the translation quality of current large language models (LLMs) for English-to-Hausa and English-to-Fongbe - two typologically distinct

Evaluating self-supervised echocardiographic representations across downstream extraction strategies for left-ventricular segmentation and ejection fraction estimation

arXiv:2606.22943v1 Announce Type: new Abstract: Self-supervised learning (SSL) is increasingly used in medical imaging to reduce annotation requirements, but representation quality is often judged usi

researcharxiv-cs-cv

Evaluation of Medical Vision Language Models HuluMed and MedGemma, and general purpose chatbots Gemma 3, ChatGPT Plus, and Claude Pro on real previously unseen wound images

arXiv:2606.20723v1 Announce Type: new Abstract: Chronic wound assessment remains a clinically challenging task that requires accurate interpretation of wound morphology, tissue composition, vascular c

Applications

Evidential Fusion Network for Multimodal Survival Prediction under Missing Modalities

arXiv:2606.20757v1 Announce Type: new Abstract: Recent multimodal survival prediction models have demonstrated strong predictive performance by leveraging complementary information across modalities.

applicationsarxiv-cs-lg

Evo-RAD: Navigating Rare Retinal Disease Diagnosis via Self-Evolving Agentic Retrieval

arXiv:2606.22955v1 Announce Type: new Abstract: Large-scale pretrained foundation models have revolutionized general medical screening, but often falter on rare diseases because such conditions are un

Tutorials

Evolutionary Discovery of Developmental Reward Schedules in Deep Reinforcement Learning

arXiv:2606.20858v1 Announce Type: new Abstract: The temporal structure of reward composition in reinforcement learning (RL) is typically hand-designed and held fixed throughout training, leaving the p

tutorialsarxiv-cs-lg