CUEBES

LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans

arXiv:2507.02861v2 Announce Type: replace Abstract: We propose LiteReality, a novel pipeline that converts RGB-D scans of indoor environments into compact, realistic, and interactive 3D virtual...

Robotics Software

arXiv CS Mar 2

Concept-based Adversarial Attack: a Probabilistic Perspective

arXiv:2507.02965v2 Announce Type: replace Abstract: We propose a concept-based adversarial attack framework that extends beyond single-image perturbations by adopting a probabilistic perspective. Rather than modifying...

Mathematics Policy

arXiv CS Mar 2

Knowledge-Guided Machine Learning: Illustrating the use of Explainable Boosting Machines to Identify Overshooting Tops in Satellite Imagery

arXiv:2507.03183v2 Announce Type: replace Abstract: Machine learning (ML) algorithms have emerged in many meteorological applications. However, these algorithms struggle to extrapolate beyond the data they...

Software Artificial Intelligence

arXiv CS Mar 2

pFedMMA: Personalized Federated Fine-Tuning with Multi-Modal Adapter for Vision-Language Models

arXiv:2507.05394v3 Announce Type: replace Abstract: Vision-Language Models (VLMs) like CLIP have demonstrated remarkable generalization in zero- and few-shot settings, but adapting them efficiently to decentralized,...

Software World News

arXiv CS Mar 2

Quantum Control and General Recursion beyond the Unitary Case

arXiv:2507.10466v3 Announce Type: replace Abstract: Coherent control, aka quantum control, is a central concept in quantum computing that is attracting increasing attention from both the...

Software Quantum Computing

arXiv CS Mar 2

Approximate SMT Counting Beyond Discrete Domains

arXiv:2507.18612v2 Announce Type: replace Abstract: Satisfiability Modulo Theory (SMT) solvers have advanced automated reasoning, solving complex formulas across discrete and continuous domains. Recent progress in...

Software Policy

arXiv CS Mar 2

Integrating LLM in Agent-Based Social Simulation: Opportunities and Challenges

arXiv:2507.19364v2 Announce Type: replace Abstract: This position paper examines the use of Large Language Models (LLMs) in social simulation, analyzing their potential and limitations from...

Software Psychology

arXiv CS Mar 2

DA-Occ: Direction-Aware 2D Convolution for Efficient and Geometry-Preserving 3D Occupancy Prediction in Autonomous Driving

arXiv:2507.23599v5 Announce Type: replace Abstract: Efficient and high-accuracy 3D occupancy prediction is vital for the performance of autonomous driving systems. However, existing methods struggle to...

Software Robotics

arXiv CS Mar 2

AutoDebias: Automated Framework for Debiasing Text-to-Image Models

arXiv:2508.00445v2 Announce Type: replace Abstract: Text-to-Image (T2I) models generate high-quality images but are vulnerable to malicious backdoor attacks that inject harmful biases (e.g., trigger-activated gender...

Policy Biology

arXiv CS Mar 2

From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model

arXiv:2508.00955v2 Announce Type: replace Abstract: Adapting generative Multimodal Large Language Models (MLLMs) into universal embedding models typically demands resource-intensive contrastive pre-training, while traditional hard negative...

Software Energy

arXiv CS Mar 2

DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging

arXiv:2508.01148v2 Announce Type: replace Abstract: Model merging has emerged as an efficient and flexible paradigm for multi-task learning, with numerous methods being proposed in recent...

Technology Policy

arXiv CS Mar 2

MLP Memory: A Retriever-Pretrained Memory for Large Language Models

arXiv:2508.01832v4 Announce Type: replace Abstract: Modern approaches to enhancing Large Language Models' factual accuracy and knowledge utilization face a fundamental trade-off: non-parametric retrieval-augmented generation (RAG)...

Psychology Software

arXiv CS Mar 2

FeynTune: Large Language Models for High-Energy Theory

arXiv:2508.03716v2 Announce Type: replace Abstract: We present specialized Large Language Models for theoretical High-Energy Physics, obtained as 20 fine-tuned variants of the 8-billion parameter Llama-3.1...

Artificial Intelligence Policy

arXiv CS Mar 2

Physics-Informed Time-Integrated DeepONet: Temporal Tangent Space Operator Learning for High-Accuracy Inference

arXiv:2508.05190v3 Announce Type: replace Abstract: Accurately modeling and inferring solutions to time-dependent partial differential equations (PDEs) over extended horizons remains a core challenge in scientific...

Biology Software

arXiv CS Mar 2

Mixed-Initiative Dialog for Human-Robot Collaborative Manipulation

arXiv:2508.05535v2 Announce Type: replace Abstract: Effective robotic systems for long-horizon human-robot collaboration must adapt to a wide range of human partners, whose physical behavior, willingness...

Software Robotics

arXiv CS Mar 2

On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

arXiv:2508.05629v3 Announce Type: replace Abstract: In this work, we present a simple yet theoretically motivated improvement to Supervised Fine-Tuning (SFT) for the Large Language Model...

Mathematics Biology

arXiv CS Mar 2

AnimateScene: Camera-controllable Animation in Any Scene

arXiv:2508.05982v2 Announce Type: replace Abstract: Recent advances in 3D scene reconstruction and 4D human animation have broadened adoption, but integrating the two remains difficult. Key...

Software Business

arXiv CS Mar 2

OM2P: Offline Multi-Agent Mean-Flow Policy

arXiv:2508.06269v2 Announce Type: replace Abstract: Generative models, especially diffusion and flow-based models, have been promising in offline multi-agent reinforcement learning. However, integrating powerful generative models...

Energy Policy

arXiv CS Mar 2

The Beauty of Anisotropic Mesh Refinement: Omnitrees for Efficient Dyadic Discretizations

arXiv:2508.06316v2 Announce Type: replace Abstract: Structured adaptive mesh refinement (AMR), commonly implemented via quadtrees and octrees, underpins a wide range of applications including databases, computer...

Software Policy

arXiv CS Mar 2

Beyond Na\"ive Prompting: Strategies for Improved Context-aided Forecasting with LLMs

arXiv:2508.09904v2 Announce Type: replace Abstract: Real-world forecasting requires models to integrate not only historical data but also relevant contextual information provided in textual form. While...

Artificial Intelligence Psychology

arXiv CS Mar 2

Actor-Critic for Continuous Action Chunks: A Reinforcement Learning Framework for Long-Horizon Robotic Manipulation with Sparse Reward

arXiv:2508.11143v2 Announce Type: replace Abstract: Existing reinforcement learning (RL) methods struggle with long-horizon robotic manipulation tasks, particularly those involving sparse rewards. While action chunking is...

Policy Robotics

arXiv CS Mar 2

LumiMAS: A Comprehensive Framework for Real-Time Monitoring and Enhanced Observability in Multi-Agent Systems

arXiv:2508.12412v2 Announce Type: replace Abstract: The incorporation of LLMs in multi-agent systems (MASs) has the potential to significantly improve our ability to autonomously solve complex...

Software Robotics

arXiv CS Mar 2

Federated Nonlinear System Identification

arXiv:2508.15025v3 Announce Type: replace Abstract: We consider federated learning of linearly-parameterized nonlinear systems. We establish theoretical guarantees on the effectiveness of federated nonlinear system identification...

Psychology Software

arXiv CS Mar 2

A Reduction of Input/Output Logics to SAT

arXiv:2508.16242v2 Announce Type: replace Abstract: Deontic logics are formalisms for reasoning over norms, obligations, permissions and prohibitions. Input/Output (I/O) Logics are a particular family of...

Robotics Software