Search: “models”

Collaborative Navigation and Exploration with eta-Sparse Gaussian Processes

arXiv:2605.26304v1 Announce Type: new Abstract: Collaborative navigation of heterogeneous robots in unknown environments poses significant challenges due to sensing, communication, and computational l

local-aiarxiv-cs-ro

Comparative Study of Vision-Based Metric Measurement for Large-Scale Planar Scenes

DGX agent

arXiv:2605.26475v1 Announce Type: cross Abstract: Vision-based metric distance and area measurement remains challenging in large-scale outdoor environments due to long-range sensing, camera zoom, and

applicationsarxiv-cs-ai

27 May 2026

CompassDPO: Dynamics-Controlled Direct Preference Optimization for Robust Safety Alignment

arXiv:2603.07211v2 Announce Type: replace Abstract: Direct Preference Optimization (DPO) has become a standard framework for safety alignment, but its reliance on pairwise preference updates makes tra

safetyarxiv-cs-lg

Completely agree, @hwchase17 ! This is the meta-level breakthrough we've all been waiting for. Self-optimizing loops finally feel production…

Completely agree, @hwchase17 ! This is the meta-level breakthrough we've all been waiting for. Self-optimizing loops finally feel production-ready because LangSmith Engine turns evaluation from a manu

safetyharrison-chase--x

Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control

arXiv:2605.26754v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) increasingly underpins high-stakes applications, yet remains vulnerable to Confundo-style poisoning where adversa

Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage Ranking

arXiv:2605.26385v1 Announce Type: cross Abstract: Large-scale search, recommendation, and retrieval-augmented generation (RAG) systems typically employ a two-stage architecture: an early-stage ranker

safetyarxiv-cs-ai

Cross-Receiver Generalization for RF Fingerprint Identification via Feature Disentanglement and Adversarial Training

arXiv:2510.09405v2 Announce Type: replace Abstract: Radio frequency fingerprint identification (RFFI) is a key technique for wireless network security, leveraging intrinsic hardware imperfections to e

safetyarxiv-cs-lg

Decoupled Delay Compensation: Enhancing Pre-trained MARL Policies via Learned Dynamics Filtering

arXiv:2605.26286v1 Announce Type: cross Abstract: Real-world multi-agent reinforcement learning (MARL) systems must often operate under stale observations, stochastic communication delays, and intermi

Design First, Code Later: Aesthetically Pleasing Template-Free Slides Generation

arXiv:2605.26451v1 Announce Type: cross Abstract: Producing presentation slides automatically entails coordinating narrative structure with page-level graphic design under strict spatial constraints.

agentsarxiv-cs-cv

Dimensional Distribution Emotion State: Leveraging Valence and Arousal as a Common Embedding Space for Visual Emotion Analysis

arXiv:2605.26262v1 Announce Type: new Abstract: Museums are important sites for the dissemination of culture and art. They are institutions rooted in history and tradition; their exhibitions are often

safetyarxiv-cs-cv

Distributed Control of Network Systems in the Space of Stabilizing Graph Neural Network Policies

arXiv:2512.18540v2 Announce Type: replace-cross Abstract: We study distributed control of networked systems through reinforcement learning, where neural policies must be simultaneously scalable, expre

local-aiarxiv-cs-lg

E^3C: Video Generation with 3D Environmental Memory and Ego-Exo Human Pose Control

arXiv:2605.26316v1 Announce Type: cross Abstract: Controllable and physically grounded egocentric video generation is essential for embodied agents to reason about how their own and others' actions ma

Efficient All-Pairs Correlation Volume Sampling for Optical Flow Estimation

arXiv:2505.16942v2 Announce Type: replace Abstract: Recent optical flow estimation methods often employ local cost sampling from a dense all-pairs correlation volume. This results in quadratic computa

local-aiarxiv-cs-cv

Experiments in Agentic AI for Science

arXiv:2605.26305v1 Announce Type: new Abstract: This paper details two novel frameworks for developing autonomous, agentic AI in scientific workflows. Both systems leverage a hybrid Local Body, Remote

local-aiarxiv-cs-ai

FM-fMRI: Event Conditioned Flow Matching for Rest-to-Task fMRI Time-Series Synthesis

arXiv:2605.26423v1 Announce Type: new Abstract: Task-based fMRI provides a direct readout of task-evoked neural dynamics, but it is expensive and difficult to acquire at scale, motivating rest-to-task

safetyarxiv-cs-lg

From Contrast to Consistency: Rethinking Event-based Continuous-Time Optical Flow Estimation

arXiv:2605.25570v2 Announce Type: replace Abstract: Estimating continuous optical flow is a fundamental yet challenging problem in dynamic visual perception. Event-based cameras, with microsecond late

From Privacy to Generalization: Linear Max-Information Bounds for DP-SGD

arXiv:2605.26222v1 Announce Type: new Abstract: Understanding the relationship between generalization and privacy remains a central challenge in modern machine learning theory, particularly for deep n

Applications

G3T Up! Gravity Aligned Coordinate Frames Simplify Pointmap Processing

arXiv:2605.27372v1 Announce Type: new Abstract: Modern feed-forward 3D reconstruction methods like VGGT predict pixel-aligned pointmaps in camera-centric coordinate frames. However, this choice of coo

applicationsarxiv-cs-cv

GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training

arXiv:2605.26184v1 Announce Type: cross Abstract: Hybrid post-training usually combines supervised fine-tuning and reinforcement learning, but fixed mixing schedules cannot adapt when the relative noi

GENESIS: Harnessing AI Agents for Autonomous 6G RAN Synthesis, Research, and Testing

arXiv:2605.27360v1 Announce Type: cross Abstract: Cellular research and development (R&D) is throttled by six structural processes that each consume months of manual engineering work per iteration: (i

Genre Controlled Music Generation via Activation Steering

arXiv:2506.10225v2 Announce Type: replace-cross Abstract: Computational Music Generation is evolving towards non-conventional styles, demanding methods that enable precise and controllable blending of

Governed Evolution of Agent Runtimes through Executable Operational Cognition

arXiv:2605.27328v1 Announce Type: cross Abstract: Recent advances in agentic systems increasingly treat code as an executable operational substrate rather than as a disposable output artifact. Prior w

Graph is a Substrate Across Data Modalities

arXiv:2601.22384v2 Announce Type: replace-cross Abstract: Graphs provide a natural representation of relational structure that arises across diverse domains. Despite this ubiquity, graph structure is

GraphReview: Scientific Paper Evaluation via LLM-Based Graph Message Passing

arXiv:2605.27204v1 Announce Type: new Abstract: Scientific paper evaluation often involves not only assessing a manuscript itself, but also relating it to contemporaneous research and prior literature

researcharxiv-cs-cl

Greening AI Inference with Accuracy and Latency-aware User Incentives

arXiv:2605.27309v1 Announce Type: new Abstract: The widespread use of AI services has raised concerns for its environmental sustainability, towards which recent studies have identified carbon emission

GS-CLIP: Zero-shot 3D Anomaly Detection by Geometry-Aware Prompt and Synergistic View Representation Learning

arXiv:2602.19206v3 Announce Type: replace Abstract: Zero-shot 3D Anomaly Detection is an emerging task that aims to detect anomalies in a target dataset without any target training data, which is part

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

arXiv:2602.22190v2 Announce Type: replace-cross Abstract: Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks. This gap stems from two limitations: a

Gumbel Machine: Counterfactual Student Writing Generation via Gumbel Noise Steering

arXiv:2605.27249v1 Announce Type: new Abstract: An effective method of teaching across disciplines is to provide examples of high-quality work. However, an example may be significantly different from

Heterogeneous AAV Logistics Task Allocation: A Reinforcement Learning Enhanced Overlapping Coalition Formation Game Approach

arXiv:2605.26471v1 Announce Type: new Abstract: In dynamic urban logistics, the stochastic emergence of time-sensitive tasks poses a significant optimality challenge for heterogeneous AAVs logistics t

safetyarxiv-cs-ro

HyperSim: A Holistic Sim-To-Real Framework For Robust Robotic Manipulation

arXiv:2605.26638v1 Announce Type: new Abstract: Scaling data volume and diversity is critical for generalizing embodied intelligence. While synthetic data generation offers a scalable alternative to e

safetyarxiv-cs-ro

ICICLE: Expanding Retrieval with In-Context Documents

arXiv:2605.26902v1 Announce Type: cross Abstract: Generative retrieval (GR) maps queries directly to document identifiers (docids) using parametric knowledge, However, this design makes corpus expansi

Tutorials

Identifiability is what it means to learn the right latent space, the Gaussian is why LeJEPA works, and it's what makes planning transfer. I…

Identifiability is what it means to learn the right latent space, the Gaussian is why LeJEPA works, and it's what makes planning transfer. I think identifiability is the right definition of what it me

tutorialsyann-lecun--x

Image Feature Fusion-based Federated Client Unlearning (FCU)

arXiv:2605.26715v1 Announce Type: new Abstract: Major data protection regulations all mention the 'right to be forgotten,' and that's what pushed federated unlearning (FU) techniques forward. But one

Applications

Implementation of Big Data Analytics for Diabetes Management: Needs Assessment in the Rwanda Healthcare System

arXiv:2605.26786v1 Announce Type: cross Abstract: Diabetes is a chronic metabolic disease that can lead to serious health problems if not diagnosed and managed early. Big Data Analytics (BDA) and mach

applicationsarxiv-cs-ai

Incremental Gauss-Newton Descent for Machine Learning

arXiv:2408.05560v2 Announce Type: replace Abstract: Stochastic gradient updates are widely used for their efficiency and scalability, but their effective step sizes can depend strongly on feature scal

local-aiarxiv-cs-lg

Tutorials

Introducing DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation http://pub.sakana.ai/diffusionblocks What if we…

tutorialsclem-delangue--x

Introducing DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation http://pub.sakana.ai/diffusionblocks What if we didn’t have to hold an entire neural network in memory to t

Intuitions of Machine Learning Researchers about Transfer Learning for Medical Image Classification

arXiv:2510.00902v2 Announce Type: replace Abstract: Transfer learning is crucial for medical imaging, yet the selection of source datasets often relies on researchers' intuition rather than systematic

safetyarxiv-cs-cv

Is Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memory

arXiv:2605.26252v1 Announce Type: new Abstract: Long-running AI agents need persistent memory. Memory supports learning across sessions, reduces repeated context injection, and enables auditing of pas

local-aiarxiv-cs-ai

Joint Instance Segmentation and Geometric Attribute Regression for Roof Structures in Aerial Imagery

arXiv:2605.26370v1 Announce Type: new Abstract: We present a method for jointly predicting instance-level roof segment masks together with three continuous geometric attributes -- building height, roo

Kan Extension Transformers: A Categorical Unification of Attention, Diffusion, and Predict-Detach Self-Conditioning

arXiv:2605.27259v1 Announce Type: new Abstract: We propose Kan Extension Transformers (KETs) as a unifying categorical framework for a diverse group of Transformer implementations. The core claim is t

Learning to Balance Motor Thermal Safety and Quadrupedal Locomotion Performance with Residual Policy

arXiv:2605.27046v1 Announce Type: new Abstract: Motor thermal management is often overlooked in the context of electrically-actuated robots, particularly legged robots, but motor overheating is a key

safetyarxiv-cs-ro

LiM-YOLO: Less is More with Pyramid Level Shift for Ship Detection in Optical Remote Sensing

arXiv:2512.09700v3 Announce Type: replace Abstract: General-purpose object detectors face fundamental structural limitations when applied to ship detection in satellite imagery, where the ship scale d

Linear and Neural Dueling Bandits with Delayed Feedback

arXiv:2605.26554v1 Announce Type: cross Abstract: Contextual dueling bandits form a cornerstone of preference-based decision-making, with critical applications in recommender systems and large languag

safetyarxiv-cs-ai

Applications

LuxRemix: Lighting Decomposition and Remixing for Indoor Scenes

arXiv:2601.15283v2 Announce Type: replace Abstract: We present a novel approach for interactive light editing in indoor scenes from a single multi-view scene capture. Our method leverages a generative

applicationsarxiv-cs-cv

Managing Uncertainty in LLM-Generated Procedural Knowledge for Virtual Laboratory Planning

arXiv:2605.26333v1 Announce Type: new Abstract: Educational virtual laboratories can make experimental training more scala-ble, adaptive, and accessible, especially when students have limited access t

Manipulating Tangible Virtual Object Dynamics to Promote Learning of Precision Force Generation

arXiv:2605.26782v1 Announce Type: new Abstract: Robotic haptic devices combined with virtual reality offer novel opportunities to train fine force generation, an essential yet overlooked component of

researcharxiv-cs-ro

Memory-Distilled Selection for Noise-Robust Anomaly Detection

arXiv:2605.26676v1 Announce Type: new Abstract: Anomaly detection (AD) under data contamination is critical for deploying unsupervised defect detection in industrial environments, where curating perfe

MiRD: Reliable Set-Valued Prediction for Open-Ended Question Answering via Miscoverage Risk Decomposition

arXiv:2605.27091v1 Announce Type: cross Abstract: Reliable set-valued prediction provides a principled way to mitigate hallucinations in open-ended question answering (QA), yet existing conformal appr