All entries

Correct codes for the wrong reasons? validating LLMs as measurement instruments for theoretical constructs

arXiv:2606.28574v1 Announce Type: cross Abstract: When a large language model (LLM) codes a construct in text as a human annotator would, that agreement makes the LLM a reliable coder. Yet reliability

Model Releases

CORTEX: High-Quality Cross-Domain Organization of Web-Scale Corpora through Ontological Corpus Graph

DGX agent

arXiv:2606.30175v1 Announce Type: new Abstract: The continuous evolution of large language models drives escalating demands on data scale and quality, and as different training stages impose increasin

model-releasesarxiv-cs-cl

30 Jun 2026

CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates

model-releasesarxiv-cs-cv

arXiv:2512.10342v3 Announce Type: replace Abstract: Vision Language Models (VLMs) have shown promising planning capabilities, yet their success remains confined to the text domain, leaving visual deci

CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents

arXiv:2511.02734v3 Announce Type: replace Abstract: Current evaluations of Large Language Model (LLM) agents primarily emphasize task completion, often overlooking resource efficiency and adaptability

CouCE: A Unified Causal Framework for Debiased Deep Metric Learning

arXiv:2606.30365v1 Announce Type: new Abstract: Deep Metric Learning (DML) often struggles with zero-shot generalization because standard objectives inherently capture what co-occurs rather than what

Agents

Couchbase’s AI Data Plane aims to turn fragmented data into real enterprise agent memory

Couchbase Inc. is trying to solve one of the hardest problems in enterprise artificial intelligence today: turning brittle, chat-style pilots into production-grade agents capable of remembering, reaso

agentssiliconangle

Counterfactual Residual Data Augmentation for Regression

arXiv:2606.28460v1 Announce Type: cross Abstract: Data-driven modeling in real-world regression tasks often suffers from limited training samples, high collection costs, and noisy observations. Inspir

Coverage-Driven KV Cache Eviction for Efficient and Improved Inference of LLM

arXiv:2606.29563v1 Announce Type: cross Abstract: Large language models (LLMs) excel at complex tasks like question answering and summarization, thanks to their ability to handle long-context inputs.

Covering the Unseen: Information Demand Coverage Optimization for Retrieval-Augmented Generation

arXiv:2606.29328v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) typically treats context selection as ranking chunks against a single query embedding. This assumption breaks dow

Safety

CRAFT: Counterfactual Credit Assignment from Free Sibling Rollouts for Self-Distilled Agentic Reinforcement Learning

arXiv:2606.29476v1 Announce Type: cross Abstract: Self-distilled agentic reinforcement learning augments trajectory-level reward with a token-level distillation loss, using as its teacher the same pol

safetyarxiv-cs-ai

Safety

Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies

arXiv:2606.29898v1 Announce Type: cross Abstract: Real-world evaluation is the gold standard for robot policies because it tests them against the physical conditions and deployment challenges they are

safetyarxiv-cs-ai

Cross-Modal Iteration Distillation for Robust IHD Screening: The IDNet Framework and A New Benchmark

model-releasesarxiv-cs-cv

arXiv:2606.30027v1 Announce Type: new Abstract: Color Fundus Photography (CFP) offers a low-cost and non-invasive route for ischemic heart disease (IHD) screening, but current studies are limited by s

Applications

Cross-Resolution Semantic Transfer for Robust Text-to-Image Retrieval in Low-Resolution Surveillance

arXiv:2606.30458v1 Announce Type: new Abstract: Text-to-image person re-identification (TIPR) retrieves target persons using natural language descriptions. However, existing methods largely overlook r

applicationsarxiv-cs-cv

Cross-Session 3D LiDAR and Camera Fusion for Robust Localization of Unmanned Aerial Vehicles in GPS-Denied Environments

arXiv:2606.28951v1 Announce Type: new Abstract: Accurate localization of unmanned aerial vehicles (UAVs) is essential for applications such as structural health monitoring, especially in environments

researcharxiv-cs-ro

Cross-Spectral Stereo Inertial Odometry

arXiv:2606.29757v1 Announce Type: new Abstract: Standard stereo VIO focuses exclusively on the benefit of metric scale via single-spectrum baselines, often overlooking the risks of spectral redundancy

researcharxiv-cs-ro

Cross-Temporal Sinhala OCR: Page-Level Adaptation and Diachronic Analysis

model-releasesarxiv-cs-cl

arXiv:2606.29378v1 Announce Type: new Abstract: Sinhala is a morphologically rich abugida spoken by roughly 16 million people in Sri Lanka, and to date, there are no publicly available real-world data

CrossWeaver: Cross-modal Weaving for Arbitrary-Modality Semantic Segmentation

arXiv:2604.02948v2 Announce Type: replace Abstract: Multimodal semantic segmentation has shown great potential in leveraging complementary information across diverse sensing modalities. However, exist

CRPS-LAM: Probabilistic Regional Weather Forecasting with Continuous Ranked Probability Score

arXiv:2510.09484v3 Announce Type: replace Abstract: Limited-Area Models (LAMs) enable weather forecasting over regional domains at higher resolutions than what is computationally feasible for global m

Hardware

CSAR: Containerized System Architecture for Robotics

arXiv:2606.30293v1 Announce Type: new Abstract: Robotic applications increasingly rely on distributed computational infrastructures that combine embedded devices, edge servers, and cloud resources. Th

hardwarearxiv-cs-ro

CubifyGS: Object-Centric 3D Gaussian Splatting for Lifelong Dynamic Scene Maintenance

model-releasesarxiv-cs-ro

arXiv:2606.28720v1 Announce Type: new Abstract: Lifelong scene mapping under rigid object rearrangement remains a fundamental challenge in robotics. While 3D Gaussian Splatting (3DGS) enables high-fid

Curvature-Guided Sheaf Diffusion for Unsupervised Community Detection on Heterophilic Graphs

arXiv:2606.30249v1 Announce Type: cross Abstract: Detecting communities in heterophilic graphs -- where connected nodes often belong to different classes -- is hard for unsupervised methods: classical

Curvature-Weighted Gradient Diversity: A Noise Measure for Geometry-Adaptive SGD Schedules

model-releasesarxiv-cs-lg

arXiv:2606.30455v1 Announce Type: new Abstract: The standard convergence analysis of mini-batch stochastic gradient descent (SGD) models gradient noise using a single variance term that treats all par

Customized Generative AI Agent for Transportation Engineering Practice: A Development and Continued Pre-training Guideline

arXiv:2606.29014v1 Announce Type: new Abstract: Recent advancements in generative artificial intelligence (AI) and large language models (LLMs) have shown significant promise in automating complex rea

Tools

Cute illustrations made by @bclavie giving a talk at @aiDotEngineer @mixedbreadai “Code is knowledge but knowledge is not code”

This post references a talk given by @bclavie at an AI engineer event hosted by Mixed Bread AI, featuring cute illustrations and exploring the distinction between code as a form of knowledge represent

toolsswyx--x

Applications

CW-B: Class Weighted Boosting Framework for Imbalance Resilient Multi Class Cardiac Phenotyping

arXiv:2606.29907v1 Announce Type: cross Abstract: Cardiac discharge phenotyping informs post-discharge treatment and follow-up, but real-world records are often incomplete and class-imbalanced, increa

applicationsarxiv-cs-ai

Industry

Cyber unicorn Aikido acquires Israeli startup Root for 70-100 million (Meir Orbach/CTech)

Meir Orbach / CTech: Cyber unicorn Aikido acquires Israeli startup Root for 70-100 million — The Belgian company expands its AI security push and will open a new development center in Israel following

industrytechmeme

Industry

Cybercab with no steering wheel or pedals driving around Austin

Tesla's Cybercab, an autonomous vehicle concept without a steering wheel or pedals, was demonstrated operating in Austin, Texas, showcasing fully self-driving capabilities. The vehicle represents Tesl

industryelon-musk--x

Industry

Cybersecurity company Aikido Security acquires Root, which has raised about $37.6M and develops an AI platform for securing open-source components (Duncan Riley/SiliconANGLE)

Duncan Riley / SiliconANGLE: Cybersecurity company Aikido Security acquires Root, which has raised about $37.6M and develops an AI platform for securing open-source components — Belgian cybersecurity

industrytechmeme

Cybersecurity is the True Frontier for Generative AI Success or Failure

arXiv:2606.28929v1 Announce Type: cross Abstract: Cybersecurity is a real-life test-bed for many machine learning problems at once, especially when considering modern strides in using Large Language M

CylindTrack: Depth-Aware Cylindrical Motion Modeling for Panoramic Multi-Object Tracking

model-releasesarxiv-cs-cv

arXiv:2606.30097v1 Announce Type: new Abstract: Multi-Object Tracking (MOT) is a core capability for embodied perception, and panoramic cameras are attractive for embodied systems because their 360{eg

Tutorials

CytoCLIP: Learning Cytoarchitectural Characteristics in Developing Human Brain Using Contrastive Language Image Pre-Training

arXiv:2601.12282v2 Announce Type: replace-cross Abstract: The functions of different regions of the human brain are closely linked to their distinct cytoarchitecture, which is defined by the spatial a

tutorialsarxiv-cs-ai

Applications

D^{2}R^{2}OSR: Degradation-Disentangled Representation for Real-World Omnidirectional Image Super-Resolution

arXiv:2606.29314v1 Announce Type: new Abstract: With the growing demand for immersive visual experiences, high-quality omnidirectional images (ODIs) have become increasingly important. However, limita

applicationsarxiv-cs-cv

Agents

DAIN: Dynamic Agent-Based Interaction Network for Efficient and Collaborative Multimodal Reasoning

arXiv:2606.30189v1 Announce Type: new Abstract: Current multimodal fusion approaches, particularly those based on static Mixture-of-Experts (MoE) architectures, often struggle to provide the adaptive

agentsarxiv-cs-cl

Tutorials

DAPS++: Rethinking Diffusion Inverse Problems with Decoupled Posterior Annealing

arXiv:2511.17038v4 Announce Type: replace Abstract: From a Bayesian perspective, score-based diffusion solves inverse problems through joint inference, embedding the likelihood with the prior to guide

tutorialsarxiv-cs-ai

Data and Evaluation Closed-Loop for Model Capability Enhancement

arXiv:2606.28471v1 Announce Type: new Abstract: Model capability is the central variable in LLM pre-training, yet is never observed directly: data shapes it prospectively, while evaluation reveals it

Data-Driven Energy-Based Learning via Gibbs Measures on Hierarchical Structures

model-releasesarxiv-cs-lg

arXiv:2606.30064v1 Announce Type: new Abstract: We introduce a data-driven probabilistic framework for learning systems based on Gibbs measures on hierarchical structures. Unlike standard empirical ri

Local Ai

Data-Driven Modeling and Control for Tethered Space Systems with Koopman-Informed Graphs

arXiv:2606.29825v1 Announce Type: new Abstract: Modeling tethered space systems is critical for advanced orbital operations. Flexible components such as tethers and space nets are integral to these sy

local-aiarxiv-cs-ro

Safety

Data-Efficient Multimodal Alignment for Histopathology-based Molecular Prediction

arXiv:2606.29949v1 Announce Type: cross Abstract: H&E-stained whole-slide images offer cohort-scale availability and rich spatial context but lack molecular specificity, whereas bulk RNA-seq provides

safetyarxiv-cs-ai

Data Provenance for Image Auto-Regressive Generation

arXiv:2606.28386v1 Announce Type: cross Abstract: Image autoregressive models (IARs) have recently demonstrated remarkable capabilities in visual content generation, achieving photorealistic quality a

Database Context Compression for Text-to-SQL on Real-World Large Databases

arXiv:2606.28601v1 Announce Type: cross Abstract: Recent progress in Text-to-SQL has been driven by stronger language models and prompting strategies, yet performance on real enterprise benchmarks suc

DataComp-VLM: Improved Open Datasets for Vision-Language Models

model-releasesarxiv-cs-cl

arXiv:2606.28551v1 Announce Type: cross Abstract: Building performant Vision-Language Models (VLMs) requires carefully curating large-scale training datasets, yet the community lacks systematic benchm

DBpedia-Enriched Company Representation for B2B Lead Recommendation

arXiv:2606.28355v1 Announce Type: cross Abstract: Selecting which companies to approach is a central challenge in business-to-business (B2B) sales, where decisions are often based on manual research a

DCGrasp: Distance-aware Controllable Grasp Generation

arXiv:2606.29924v1 Announce Type: new Abstract: Generating 3D hand-object interactions is essential for applications in robotics, XR, and synthetic data generation, where flexible controllability and

DCSNet: Multiscale Feature Aggregation for Small Medical Object Segmentation with Detection-guided Hierarchical Cropping

arXiv:2606.28402v1 Announce Type: new Abstract: Small object segmentation in medical imaging is primarily hindered by class imbalance and inherent boundary complexity. Consequently, conventional globa

Dead-Direction Conditioners: Gauge-Equivariant Preconditioning for Deep Networks

arXiv:2606.29176v1 Announce Type: new Abstract: A deep network's loss is invariant to continuous symmetries of its parameters: the logit shift, the ReLU rescaling, the LayerNorm scale, the per-head at

Deciphering Region-Level Signatures from Latency Measurements in LEO Satellite Internet

arXiv:2606.29324v1 Announce Type: new Abstract: Low-Earth orbit (LEO) satellite Internet has become an indispensable infrastructure that provide growing coverage for global users. Despite extensive me

Tutorials

Decision-Value Attribution in Predict-then-Optimize Systems

arXiv:2606.29878v1 Announce Type: new Abstract: Predictive models are increasingly embedded in operational decision-making, yet standard explanation methods typically explain forecasts rather than the

tutorialsarxiv-cs-lg

Decomposing Memorization Reduction in Privacy-Preserving Fine-Tuning of SLMs for CSIRTs

arXiv:2606.28479v1 Announce Type: cross Abstract: CSIRTs increasingly fine tune language models on vulnerability scan records, but these records expose internal network topology and create privacy ris