All entries

Crowding Out The Noise: Algorithmic Collective Action Under Differential Privacy

arXiv:2505.05707v2 Announce Type: replace Abstract: The integration of AI into daily life has generated considerable attention and excitement, while also raising concerns about automating algorithmic

safetyarxiv-cs-lg

Crystal Fractional Graph Neural Network for Energy Prediction of High-Entropy Alloys

DGX agent

arXiv:2605.08103v1 Announce Type: cross Abstract: High-entropy alloys (HEAs) have attracted growing attention for their exceptional mechanical and thermal properties arising from complex atomic config

local-aiarxiv-cs-ai

12 May 2026

CrystalREPA: Transferring Physical Priors from Universal MLIPs to Crystal Generative Models

arXiv:2605.08960v1 Announce Type: cross Abstract: Crystal generative models mainly learn what stable crystals look like, with little explicit supervision for what makes them stable. We reveal a substa

CT-IDP: Segmentation-Derived Quantitative Phenotypes for Interpretable Abdominal CT Disease Classification

arXiv:2605.09002v1 Announce Type: cross Abstract: In this retrospective multi-institutional study, a quantitative phenotyping framework, CT-IDP (CT Image-Derived Phenotypes) was developed on the MERLI

CTQWformer: A CTQW-based Transformer for Graph Classification

arXiv:2605.09486v1 Announce Type: cross Abstract: Graph Neural Networks (GNN) and Transformer-based architectures have achieved remarkable progress in graph learning, yet they still struggle to captur

CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging

arXiv:2605.08455v1 Announce Type: new Abstract: Debugging CUDA programs has long been challenging because failures often arise from subtle interactions among hardware behavior, compiler decisions, mem

CUDAHercules: Benchmarking Hardware-Aware Expert-level CUDA Optimization for LLMs

arXiv:2605.08467v1 Announce Type: new Abstract: Large language models show promise for automated CUDA programming, however even the strongest coding models (e.g., Claude-Opus-4.6) may still fall short

cuRegOT: A GPU-Accelerated Solver for Entropic-Regularized Optimal Transport

arXiv:2605.08793v1 Announce Type: cross Abstract: Optimal transport (OT) has emerged as a fundamental tool in modern machine learning, yet its computational cost remains a significant bottleneck for l

Curriculum Learning for LLM Pretraining: An Analysis of Learning Dynamics

arXiv:2601.21698v2 Announce Type: replace-cross Abstract: Curriculum learning changes the order of pretraining data, but it remains unclear how ordering changes the learning dynamics. We pretrain mode

Local Ai

Curvature-Aware Captioning:Leveraging Geodesic Attention for 3D Scene Understanding

arXiv:2605.08808v1 Announce Type: cross Abstract: Accurate 3D scene description is fundamental to robotic navigation and augmented reality, yet current dense captioning methods face significant limita

local-aiarxiv-cs-ai

Cyclic Nullspace Coordination: Perpetual Flight of Aerial Carriers for Static Suspension

arXiv:2503.03481v2 Announce Type: replace Abstract: This work demonstrates that the non-stop flights of three or more carriers are compatible with holding a constant pose of a cable-suspended load. It

researcharxiv-cs-ro

D2ACE: Multi-Label Batch Selection Guided by Dual Dynamics and Adaptive Correlation Enhancement

arXiv:2605.09400v1 Announce Type: new Abstract: Batch selection is crucial for improving both training efficiency and predictive performance in deep multi-label classification (MLC). Existing batch se

DA-SegFormer: Damage-Aware Semantic Segmentation for Fine-Grained Disaster Assessment

arXiv:2605.09864v1 Announce Type: new Abstract: Rapid and accurate damage assessment following natural disasters is critical for effective emergency response. However, identifying fine-grained damage

researcharxiv-cs-cv

DANCE: Detect and Classify Events in EEG

arXiv:2605.10688v1 Announce Type: new Abstract: Event identification in continuous neural recordings is a critical task in neuroscience. Decoding in EEG is dominated by classifying windows aligned to

applicationsarxiv-cs-lg

DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition

arXiv:2605.09604v1 Announce Type: new Abstract: Millimeter-wave (mmWave) radar provides privacy-preserving sensing and is valuable for human action recognition (HAR). Existing mmWave point cloud datas

safetyarxiv-cs-cv

DAPE: Dynamic Non-uniform Alignment and Progressive Detail Enhancement Techniques for Improving the Performance of Efficient Visual Language Models

arXiv:2605.08902v1 Announce Type: cross Abstract: In recent years, pre-trained visual-linguistic models have demonstrated tremendous potential, becoming a crucial foundational framework for numerous d

DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation

arXiv:2605.09188v1 Announce Type: cross Abstract: Reinforcement learning improves the reasoning ability of large language models but remains costly and sample-inefficient, as many rollouts provide wea

DARE: Diffusion Language Model Activation Reuse for Efficient Inference

arXiv:2605.08134v1 Announce Type: cross Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to auto-regressive (AR) models, offering greater expressive capacity a

Data-Asymmetric Latent Imagination and Reranking for 3D Robotic Imitation Learning

arXiv:2605.10166v1 Announce Type: new Abstract: Robotic imitation learning typically assumes access to optimal demonstrations, yet real-world data collection often yields suboptimal, exploratory, or e

applicationsarxiv-cs-ro

Local Ai

Data-driven Circuit Discovery for Interpretability of Language Models

arXiv:2605.09129v1 Announce Type: new Abstract: Circuit discovery aims to explain how language models (LMs) implement a specific task by localizing and interpreting a circuit, a computational subgraph

local-aiarxiv-cs-ai

Data-driven transport modelling without overfit

arXiv:2605.08801v1 Announce Type: new Abstract: Macroscopic transport modelling aims to predict traffic flows after proposed public policy interventions, such as a new road or railway section or a tem

safetyarxiv-cs-lg

Data Mixing Can Induce Phase Transitions in Knowledge Acquisition

arXiv:2505.18091v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are typically trained on data mixtures: most data come from web scrapes, while a small portion is curated from hi

DataArc-SynData-Toolkit: A Unified Closed-Loop Framework for Multi-Path, Multimodal, and Multilingual Data Synthesis

arXiv:2605.08138v1 Announce Type: new Abstract: Synthetic data has emerged as a crucial solution to the data scarcity bottleneck in large language models (LLMs), particularly for specialized domains a

applicationsarxiv-cs-lg

DataMaster: Towards Autonomous Data Engineering for Machine Learning

arXiv:2605.10906v1 Announce Type: cross Abstract: As model families, training recipes, and compute budgets become increasingly standardized, further gains in machine learning systems depend increasing

agentsarxiv-cs-ai

datasette 1.0a29

model-releasessimon-willison

Release: datasette 1.0a29 New TokenRestrictions.abbreviated(datasette) utility method for creating '_r' dictionaries. #2695 Table headers and column options are now visible even if a table contains ze

Debiased Front-Door Learners for Heterogeneous Effects

arXiv:2509.22531v2 Announce Type: replace-cross Abstract: In observational settings where treatment and outcome share unmeasured confounders but an observed mediator remains unconfounded, the front-do

applicationsarxiv-cs-lg

Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents

arXiv:2605.08717v1 Announce Type: cross Abstract: Software engineering agents are increasingly deployed in evaluable engineering environments, yet post-failure recovery remains costly, manual, and ad

Decentralized Conformal Novelty Detection via Quantized Model Exchange

arXiv:2605.08263v1 Announce Type: cross Abstract: This work studies decentralized novelty detection with global false discovery rate (FDR) control across heterogeneous composite null distributions, wi

Decentralized Contingency MPC based on Safe Sets for Nonlinear Multi-agent Collision Avoidance

arXiv:2605.10738v1 Announce Type: cross Abstract: Decentralized collision avoidance remains challenging, particularly when agents do not communicate any information related to planned trajectories. Mo

agentsarxiv-cs-ro

DECO-MWE: building a linguistic resource of Korean multiword expressions for feature-based sentiment analysis

arXiv:2605.10295v1 Announce Type: new Abstract: This paper aims to construct a linguistic resource of Korean Multiword Expressions for Feature-Based Sentiment Analysis (FBSA): DECO-MWE. Dealing with m

researcharxiv-cs-cl

DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices

model-releasesarxiv-cs-cl

arXiv:2605.10933v1 Announce Type: cross Abstract: While Mixture-of-Experts (MoE) scales model capacity without proportionally increasing computation, its massive total parameter footprint creates sign

Decoding Islamophobic Discourse: Using LLMs to Identify Tropes and Semi-Coded Hate Speech

arXiv:2503.18273v3 Announce Type: replace Abstract: In recent years, Islamophobia has gained significant traction across Western societies, fueled by the rise of digital communication networks. This p

Decomposing and Steering Functional Metacognition in Large Language Models

model-releasesarxiv-cs-cl

arXiv:2605.08942v1 Announce Type: new Abstract: Large language models (LLMs) increasingly exhibit behaviors suggesting awareness of their evaluation context, often adapting their reasoning strategies

Decoupling Endpoint and Semantic Transition Learning for Zero-Shot Composed Image Retrieval

arXiv:2605.08389v1 Announce Type: cross Abstract: Zero-shot composed image retrieval (ZS-CIR) retrieves a target image from a reference image and a text modification without human-annotated CIR triple

Deep Agents ship with durable execution out of the box: every agent step is checkpointed, so you get observability, fault tolerance, and hum…

Deep Agents ship with durable execution out of the box: every agent step is checkpointed, so you get observability, fault tolerance, and human-in-the-loop for free. But as agents run longer and contex

agentsharrison-chase--x

Tutorials

Deep Arguing

arXiv:2605.10569v1 Announce Type: new Abstract: Deep learning has become the dominant approach for creating high capacity, scalable models across diverse data modalities. However, because these models

tutorialsarxiv-cs-ai

Deep Dreams Are Made of This: Visualizing Monosemantic Features in Diffusion Models

arXiv:2605.08218v1 Announce Type: cross Abstract: This paper proposes latent visualization by optimization (LVO), a mechanistic interpretability technique that extends feature visualization by optimiz

researcharxiv-cs-cv

Deep-ICE: the first globally optimal algorithm for minimizing 0-1 loss in two-layer ReLU and maxout networks

arXiv:2505.05740v3 Announce Type: replace Abstract: This paper introduces the first globally optimal algorithm for the empirical risk minimization problem of two-layer maxout and ReLU networks, i.e.,

Deep learning hit a wall. Neurosymbolic AI rescued it.

model-releasesgary-marcus--x

Deep learning hit a wall. Neurosymbolic AI rescued it. 🤩🤯🤩 Claude Code (still not AGI but biggest advance since GPT-4) is the most neurosymbolic thing I have ever seen in my life. 53 symbolic tools, 5

Deep Learning under Fractional-Order Differential Privacy

arXiv:2605.09890v1 Announce Type: cross Abstract: Differentially private stochastic gradient descent (DP-SGD) is a standard approach to privacy-preserving learning based on per-example clipping, subsa

Deep set based operator learning with uncertainty quantification

arXiv:2509.25646v2 Announce Type: replace Abstract: Learning operators from data is central to scientific machine learning. While DeepONets are widely used for their ability to handle complex domains,

Deepfake Detection that Generalizes Across Benchmarks

model-releasesarxiv-cs-cv

arXiv:2508.06248v4 Announce Type: replace Abstract: The generalization of deepfake detectors to unseen manipulation techniques remains a challenge for practical deployment. Although many approaches ad

DeepLevy: Learning Heavy-Tailed Uncertainty in Highly Volatile Time Series

arXiv:2605.10364v1 Announce Type: new Abstract: Modeling uncertainty in heavy-tailed time series remains a critical challenge for deep probabilistic forecasting models, which often struggle to capture

DeepLog: A Software Framework for Modular Neurosymbolic AI

arXiv:2605.10279v1 Announce Type: new Abstract: DeepLog is an operational neurosymbolic framework that unifies logic and deep learning within standard PyTorch workflows. While existing neurosymbolic s

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning

arXiv:2605.10488v1 Announce Type: cross Abstract: Agent-compiled knowledge bases provide persistent external knowledge for large language model (LLM) agents in open-ended, knowledge-intensive downstre

agentsarxiv-cs-ai

DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving

model-releasesarxiv-cs-cv

arXiv:2605.10564v1 Announce Type: new Abstract: End-to-end autonomous driving systems are increasingly integrating Vision-Language Model (VLM) architectures, incorporating text reasoning or visual rea

DeepTumorVQA: A Hierarchical 3D CT Benchmark for Stage-Wise Evaluation of Medical VLMs and Tool-Augmented Agents

arXiv:2605.09679v1 Announce Type: cross Abstract: Medical vision-language models (VLMs) and AI agents have made significant progress in learning to analyze and reason about clinical images. However, e

Defense effectiveness across architectural layers: a mechanistic evaluation of persistent memory attacks on stateful LLM agents

arXiv:2605.08442v1 Announce Type: cross Abstract: Persistent memory attacks against LLM agents achieve high attack success rates against open-source models. In these attacks, malicious instructions in