All entries

EgoHTR: Egocentric 4D Demonstrations of Human Terrain Traversal

arXiv:2607.13472v1 Announce Type: cross Abstract: Deploying humanoid robots in unstructured terrain remains an open problem. While classic reinforcement learning struggles with the sheer complexity of

EgoProceVQA: A Novel Egocentric Procedural Understanding Task with Self-Skill-Exploration Agent

DGX agent

arXiv:2607.13792v1 Announce Type: new Abstract: Most daily activities are inherently procedural. However, existing evaluations for egocentric video understanding seldom address procedural understandin

model-releasesarxiv-cs-cv

16 Jul 2026

EM-GANSim: Real-time and Accurate EM Simulation Using Conditional GANs for 3D Indoor Scenes

arXiv:2405.17366v3 Announce Type: replace Abstract: We present a novel machine-learning (ML) approach (EM-GANSim) for real-time electromagnetic (EM) propagation that is used for wireless communication

Hardware

EMAGN: Efficient Multi-Attention Graph Network via Learned Clustering for Scalable Traffic Forecasting

arXiv:2607.13241v1 Announce Type: cross Abstract: Traffic forecasting is highly challenging due to complex and nonlinear spatial and temporal dependencies. Self-attention mechanisms have been widely a

hardwarearxiv-cs-ai

Evaluating Frontier AI Agents as Autonomous Clinical Security Auditors

arXiv:2607.13411v1 Announce Type: cross Abstract: Clinical AI models can expose patients to harm when adversarial vulnerabilities go undetected, yet formal security auditing requires statistical exper

Evaluating Vision Foundation Models for Pixel and Object Classification in Microscopy

arXiv:2603.19802v2 Announce Type: replace Abstract: Deep learning underlies most modern approaches and tools in computer vision, including biomedical imaging. However, for interactive semantic segment

Evaluation Ability Does Not Imply Optimization Utility: LLM-as-a-Judge Signals in Closed-Loop Table Recognition

arXiv:2607.13347v1 Announce Type: cross Abstract: LLM-as-a-judge is widely used to provide feedback and selection signals in closedloop regeneration, but this use remains insufficiently validated. We

Agents

Experience Memory Graph: One-Shot Error Correction for Agents

arXiv:2607.13884v1 Announce Type: new Abstract: Large Language Model (LLM) agents have shown remarkable capabilities in autonomous decision-making by generating sequential trajectories of states, acti

agentsarxiv-cs-ai

Explainable Artificial Intelligence for Anomaly Detection in Banking Transactions: An Internal Audit Perspective

arXiv:2607.13469v1 Announce Type: cross Abstract: The banking sector increasingly relies on automated systems to monitor electronic transactions for signs of fraud, yet conventional rule-based approac

Explaining Reinforcement Learning Agents via Inductive Logic Programming

arXiv:2607.13655v1 Announce Type: new Abstract: Explainable Reinforcement Learning (XRL) seeks to make Reinforcement Learning (RL) policies more transparent and interpretable, a key requirement in saf

Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation

arXiv:2607.13653v1 Announce Type: new Abstract: Real-world deployment of embodied agents requires active exploration, visual grounding, and interactive intent disambiguation. However, existing framewo

EXPLORE: Exploration with Guided Search for Analog Topology Generation using Language Models

arXiv:2607.13416v1 Announce Type: new Abstract: Automating analog circuit topology design is essential to reduce the extensive manual effort required to meet increasingly diverse and customized applic

ExTernD: Expanded-Rank Ternary Decomposition Ternary LLM PTQ with Accuracy Approaching Any Quantization Level

model-releasesarxiv-cs-ai

arXiv:2607.13511v1 Announce Type: cross Abstract: We introduce ExTernD (Expanded-rank Ternary Decomposition), a post-training factorization of each LLM weight matrix A in R^{m imes n} into A approx B

EZSMT Version 3, Matured

arXiv:2607.13344v1 Announce Type: new Abstract: Constraint Answer Set Programming (CASP) is a hybrid reasoning paradigm that combines Answer Set Programming (ASP) with Constraint Processing and Satisf

Factorized Spectral Representations for Reinforcement Learning

arXiv:2607.13498v1 Announce Type: new Abstract: Learning a compact model of the world from interaction data is central to sample-efficient deep reinforcement learning. Spectral representation methods

Faithful Autoformalization of Natural Language Assertions

arXiv:2607.13303v1 Announce Type: cross Abstract: Formal contracts are essential for software testing and verification, yet writing them remains labor-intensive and error-prone. LLMs offer a promising

FastCentNN: Accelerating Centroid Neural Network with Entropy Proxy

arXiv:2607.13613v1 Announce Type: cross Abstract: Centroid neural network (CentNN) is an unsupervised competitive learning algorithm in which centroid splitting is triggered only after strict local st

Local Ai

Federated Explainable Artificial Intelligence: Roles, Architectures, Evaluation, and Open Challenges

arXiv:2607.13045v1 Announce Type: cross Abstract: Federated Learning (FL) has emerged as a key paradigm for privacy-preserving collaborative model training across distributed and heterogeneous data so

local-aiarxiv-cs-ai

Final Authority in AI Governance: Frontier-Provider Sovereignty and Action-Centered Deployer Governance

arXiv:2607.13040v1 Announce Type: cross Abstract: This paper examines where final authority should sit once capable AI systems are embedded in organizational workflows. It compares two governance mode

Fine-grained CLIP fine-tuning with self-annotated region alignment

arXiv:2607.13661v1 Announce Type: new Abstract: Contrastive Language-Image Pre-training (CLIP) has been shown to have limitations in its fine-grained dense feature representation, due to its pre-train

Fine-Grained Vision-Language Pretraining with Organ-Conditioned Pattern Tokens for CT Understanding

arXiv:2607.13892v1 Announce Type: new Abstract: Computed tomography (CT) vision-language pretraining from paired volumes and radiology reports is a scalable yet challenging task. Existing methods comm

safetyarxiv-cs-cv

Fire as a Service: Augmenting Robot Simulators with Thermally and Visually Accurate Fire Dynamics

model-releasesarxiv-cs-ro

arXiv:2603.19063v2 Announce Type: replace Abstract: Most existing robot simulators prioritize rigid-body dynamics and photorealistic rendering, but largely neglect the thermally and optically complex

FixItFlow: Automated Troubleshooting Guide Generation from Cloud Incidents

arXiv:2607.13035v1 Announce Type: cross Abstract: Cloud services experience frequent incidents that require rapid diagnosis and resolution. Troubleshooting guides help engineers respond consistently,

tutorialsarxiv-cs-ai

Agents

Flow-aware Optimal Navigation in Unsteady Flows through Reinforcement Learning

arXiv:2607.13553v1 Announce Type: cross Abstract: Autonomous robotic navigation in nonstationary time-varying fluid flows remains a fundamental challenge due to partial observability and the unpredict

agentsarxiv-cs-lg

FM^2: Unified Federated Foundation Models for Heterogeneous Multimodal Medical Imaging

arXiv:2607.13386v1 Announce Type: new Abstract: Building foundation models for medical imaging requires pooling data across institutions, yet privacy regulations prohibit centralized aggregation. Exis

FOLIO: Focused Semantic Memory for Streaming Video Understanding

arXiv:2607.13298v1 Announce Type: new Abstract: In online streaming video understanding, a video stream continues to arrive and queries may be issued at any time. Because streaming frames grow without

tutorialsarxiv-cs-cv

FreeLit: Paired-Free Indoor Relighting via Physics-Guided Diffusion

arXiv:2607.13656v1 Announce Type: new Abstract: Image-based indoor scene relighting remains challenging due to the complex interplay between cluttered geometry and local illumination, requiring precis

safetyarxiv-cs-cv

From Language to Navigation Goals: A Vision-Language Approach for Semantic Navigation of Mobile Robots Using RGB-D Perception

model-releasesarxiv-cs-ai

arXiv:2607.13624v1 Announce Type: cross Abstract: Natural language interaction provides an intuitive way for non-expert users to communicate with robotic platforms. However, transforming user requests

From Novice to Expert: Cost-Aware Bandits for Evolving Worker Performance in Crowdsensing

arXiv:2607.13546v1 Announce Type: new Abstract: Mobile crowdsensing (MC) recruits mobile users to perform sensing tasks using their smartphones, enabling large-scale applications such as traffic monit

tutorialsarxiv-cs-lg

From Pixels to States: Rethinking Interactive World Models as Game Engines

arXiv:2607.14076v1 Announce Type: new Abstract: Building interactive worlds that respond coherently to player actions has long been a shared goal of computer graphics, games, and artificial intelligen

researcharxiv-cs-cv

From Prediction to Collaboration: Interactive Symbolic Music Analysis

model-releasesarxiv-cs-ai

arXiv:2607.13587v1 Announce Type: cross Abstract: Automatic symbolic music analysis has made substantial progress, yet existing systems are typically designed for a single mode of use, such as full-sc

From Surface Forecasting to Observability Forecasting: A Latent World Model for Cloud-Aware EO Monitoring

arXiv:2607.13651v1 Announce Type: new Abstract: The bottleneck of Earth Observation processing chains is not the arrival of new imagery but whether the surface is actually visible when the image arriv

Hardware

Full-Pipeline Inference Optimization for MiMo-V2.5 Series: Pushing Hybrid SWA Efficiency to the Limit

arXiv:2607.13095v1 Announce Type: cross Abstract: We present a full-pipeline inference optimization for the MiMo-V2.5 model family, which combines Hybrid Sliding Window Attention (Hybrid SWA), sparse

hardwarearxiv-cs-ai

Gauge-Invariant, Parameter-Insensitive Regularization for Potential Recovery from Flow on Directed Graphs

arXiv:2607.13609v1 Announce Type: new Abstract: Recovering a latent potential from observed flow on a directed graph (a discrete Poisson problem with Dirichlet boundaries) is ill-posed, and the standa

Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment

arXiv:2607.13429v1 Announce Type: cross Abstract: Finetuning a pretrained vision-language model (VLM) on robot demonstrations via behavior cloning (BC) has become the standard recipe for vision-langua

safetyarxiv-cs-cv

Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code

arXiv:2607.13921v1 Announce Type: cross Abstract: Languages with rich static semantics, such as Rust, provide stronger guarantees for AI-generated code, but their strictness makes generation more diff

tutorialsarxiv-cs-ai

Local Ai

GeoAnchor: Collaborative Reasoning via Latent Decomposition for 3D Spatial Understanding

arXiv:2607.13454v1 Announce Type: cross Abstract: Although multimodal large language models (MLLMs) have achieved remarkable progress, understanding 3D spatial relationships from 2D images remains a c

local-aiarxiv-cs-ai

GFlowRL: Scaling Distribution-Matching RL to Large Language Models

arXiv:2607.13394v1 Announce Type: cross Abstract: Generative Flow Networks (GFlowNets) offer a promising alternative to reward-maximizing reinforcement learning (RL) for large reasoning models, encour

Applications

GHR-VLM: Making Zero-Shot Transit Video Analytics Realizable with Grounded Hybrid Reasoning

arXiv:2607.13569v1 Announce Type: cross Abstract: Transit video understanding can provide valuable fine-grained data that conventional passenger counters and fare systems cannot capture. However, supe

applicationsarxiv-cs-ai

Local Ai

GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch

arXiv:2607.13960v1 Announce Type: new Abstract: World Action Models (WAMs) improve robot policy learning by jointly modeling actions and future visual observations, using future scene evolution as den

local-aiarxiv-cs-ro

GNN-DIP: Neural Corridor Selection for Decomposition-Based Motion Planning

arXiv:2603.12361v2 Announce Type: replace Abstract: Motion planning through narrow passages remains a core challenge: sampling-based planners rarely place samples inside these narrow but critical regi

safetyarxiv-cs-ro

GPOcc++: Unified Sparse Gaussian Occupancy Prediction with Visual Geometry Priors

arXiv:2607.13481v1 Announce Type: new Abstract: Accurate 3D scene understanding is fundamental to embodied intelligence and autonomous driving, where 3D occupancy provides a unified representation of

GPUSimBench: Towards Scalable and Reliable GPU-Accelerated Simulators in Embodied AI

model-releasesarxiv-cs-ro

arXiv:2607.13059v1 Announce Type: new Abstract: Data-driven embodied AI is rapidly transitioning into a paradigm that scales training through massively parallel simulation, where GPU-accelerated simul

Graded Entity-Familiarity Readouts in Language Models: Polish Adaptation, Cross-Language Robustness, and Refusal Steering

arXiv:2607.13568v1 Announce Type: cross Abstract: Can a language model estimate its familiarity with an entity before generating an answer? We study activations at the final prompt token in twelve ins

Graph Partitioning with Demands: Generalized Conductance and its Applications

arXiv:2607.13218v1 Announce Type: cross Abstract: In this work, we study various graph partitioning problems under a general demand model. In each such task, we are given a graph G=(V,E,c,w) with a ca

Greedy Volume Maximization of Gradient Embeddings for Long-Tailed Frame-Level Bioacoustic Active Learning

arXiv:2607.13555v1 Announce Type: cross Abstract: Bioacoustic call-type classification relies on costly expert annotation. Active learning can reduce this burden by selecting a small batch of segments

Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs

arXiv:2607.13712v1 Announce Type: cross Abstract: Despite the rapid progress of Multimodal Large Language Models (MLLMs), they still suffer from untruthfulness issues, such as visual hallucinations, c

Agents

Grounded world models in biological organisms and future embodied AI

arXiv:2607.13560v1 Announce Type: cross Abstract: Recent advances in generative and embodied AI have been driven by large-scale predictive learning over multimodal data. However, the resulting systems

agentsarxiv-cs-ai