CUEBES

Mamba-based Spatio-Frequency Motion Perception for Video Camouflaged Object Detection

arXiv:2507.23601v2 Announce Type: replace Abstract: Existing video camouflaged object detection (VCOD) methods primarily rely on spatial appearances for motion perception. However, the high foreground-background similarity...

Software Energy

arXiv CS Feb 10

A Parallel Alternative for Energy-Efficient Neural Network Training and Inferencing

arXiv:2508.00960v2 Announce Type: replace Abstract: Energy efficiency of training and inferencing with large neural network models is a critical challenge facing the future of sustainable...

Artificial Intelligence Neuroscience

arXiv CS Feb 10

AffectGPT-R1: Leveraging Reinforcement Learning for Open-Vocabulary Multimodal Emotion Recognition

arXiv:2508.01318v3 Announce Type: replace Abstract: Open-Vocabulary Multimodal Emotion Recognition (OV-MER) aims to predict emotions without being constrained by label spaces, enabling fine-grained emotion understanding. Unlike...

Psychology Software

arXiv CS Feb 10

MAMBO-G: Magnitude-Aware Mitigation for Boosted Guidance

arXiv:2508.03442v4 Announce Type: replace Abstract: High-fidelity text-to-image and text-to-video generation typically relies on Classifier-Free Guidance (CFG), but achieving optimal results often demands computationally expensive sampling...

Chemistry Software

arXiv CS Feb 10

Information-Theoretic Graph Fusion with Vision-Language-Action Model for Policy Reasoning and Dual Robotic Control

arXiv:2508.05342v2 Announce Type: replace Abstract: Teaching robots dexterous skills from human videos remains challenging due to the reliance on low-level trajectory imitation, which fails to...

Psychology Policy

arXiv CS Feb 10

Learning Geometric-Aware Quadrature Rules for Functional Minimization

arXiv:2508.05445v2 Announce Type: replace Abstract: Accurate numerical integration over non-uniform point clouds is a challenge for modern mesh-free machine learning solvers for partial differential equations...

Artificial Intelligence Genetics

arXiv CS Feb 10

WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction

arXiv:2508.05599v3 Announce Type: replace Abstract: Visual tokenizer is a critical component for vision generation. However, the existing tokenizers often face unsatisfactory trade-off between compression ratios...

Books & Literature Technology

arXiv CS Feb 10

Robust Image Stitching with Optimal Plane

arXiv:2508.05903v2 Announce Type: replace Abstract: We present \textit{RopStitch}, an unsupervised deep image stitching framework with both robustness and naturalness. To ensure the robustness of \textit{RopStitch},...

Biology Engineering

arXiv CS Feb 10

Hyperspectral Imaging

arXiv:2508.08107v2 Announce Type: replace Abstract: Hyperspectral imaging (HSI) is an advanced sensing modality that simultaneously captures spatial and spectral information, enabling non-invasive, label-free analysis of...

Hardware Technology

arXiv CS Feb 10

Benchmarking Large Language Models for Geolocating Colonial Virginia Land Grants

arXiv:2508.08266v2 Announce Type: replace Abstract: Virginia's seventeenth- and eighteenth-century land patents survive primarily as narrative metes-and-bounds descriptions, limiting spatial analysis. This study systematically evaluates current-generation...

Artificial Intelligence Biology

arXiv CS Feb 10

Prospect Theory Fails for LLMs: Revealing Instability of Decision-Making under Epistemic Uncertainty

arXiv:2508.08992v2 Announce Type: replace Abstract: Prospect Theory (PT) models human decision-making under uncertainty, while epistemic markers (e.g., maybe) serve to express uncertainty in language. However,...

Software Mathematics

arXiv CS Feb 10

Legal$\Delta$: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain

arXiv:2508.12281v3 Announce Type: replace Abstract: Legal Artificial Intelligence (LegalAI) has achieved notable advances in automating judicial decision-making with the support of Large Language Models (LLMs)....

Psychology Software

arXiv CS Feb 10

From Fomo3D to Lottery DAPP: Analysis of Ethereum-Based Gambling Applications

arXiv:2508.12303v2 Announce Type: replace Abstract: As blockchain technology advances, Ethereum based gambling decentralized applications (DApps) represent a new paradigm in online gambling. This paper examines...

Software Technology

arXiv CS Feb 10

SNAP-UQ: Self-supervised Next-Activation Prediction for Single-Pass Uncertainty in TinyML

arXiv:2508.12907v3 Announce Type: replace Abstract: Reliable uncertainty estimation is a key missing piece for on-device monitoring in TinyML: microcontrollers must detect failures, distribution shift, or...

Hardware Technology

arXiv CS Feb 10

HiFo-Prompt: Prompting with Hindsight and Foresight for LLM-based Automatic Heuristic Design

arXiv:2508.13333v2 Announce Type: replace Abstract: LLM-based Automatic Heuristic Design (AHD) within Evolutionary Computation (EC) frameworks has shown promising results. However, its effectiveness is hindered by...

Biology Psychology

arXiv CS Feb 10

DyMixOp: A Neural Operator Designed from a Complex Dynamics Perspective with Local-Global Mixing for Solving PDEs

arXiv:2508.13490v3 Announce Type: replace Abstract: A primary challenge in using neural networks to approximate nonlinear dynamical systems governed by partial differential equations (PDEs) lies in...

Biology Technology

arXiv CS Feb 10

CaPGNN: Optimizing Parallel Graph Neural Network Training with Joint Caching and Resource-Aware Graph Partitioning

arXiv:2508.13716v2 Announce Type: replace Abstract: Graph-structured data is ubiquitous in the real world, and Graph Neural Networks (GNNs) have become increasingly popular in various fields...

Artificial Intelligence Technology

arXiv CS Feb 10

DegDiT: Controllable Audio Generation with Dynamic Event Graph Guided Diffusion Transformer

arXiv:2508.13786v2 Announce Type: replace Abstract: Controllable text-to-audio generation aims to synthesize audio from textual descriptions while satisfying user-specified constraints, including event types, temporal sequences, and...

Software Energy

arXiv CS Feb 10

Beyond the Mean: Fisher-Orthogonal Projection for Natural Gradient Descent in Large Batch Training

arXiv:2508.13898v3 Announce Type: replace Abstract: Modern GPUs are equipped with large amounts of high-bandwidth memory, enabling them to support mini-batch sizes of up to tens...

Technology Software

arXiv CS Feb 10

Sim-to-Real Dynamic Object Manipulation on Conveyor Systems via Optimization Path Shaping

arXiv:2508.14042v2 Announce Type: replace Abstract: Realizing generalizable dynamic object manipulation on conveyor systems is important for enhancing manufacturing efficiency, as it eliminates specialized engineering for...

Engineering Policy

arXiv CS Feb 10

Your Reward Function for RL is Your Best PRM for Search: Unifying RL and Search-Based TTS

arXiv:2508.14313v3 Announce Type: replace Abstract: Test-time scaling (TTS) for large language models (LLMs) has thus far fallen into two largely separate paradigms: (1) reinforcement learning...

Artificial Intelligence Software

arXiv CS Feb 10

Virtual Community: An Open World for Humans, Robots, and Society

arXiv:2508.14893v3 Announce Type: replace Abstract: The rapid progress in AI and Robotics may lead to a profound societal transformation, as humans and robots begin to...

Robotics Software

arXiv CS Feb 10

You Only Pose Once: A Minimalist's Detection Transformer for Monocular RGB Category-level 9D Multi-Object Pose Estimation

arXiv:2508.14965v2 Announce Type: replace Abstract: Accurately recovering the full 9-DoF pose of unseen instances within specific categories from a single RGB image remains a core...

Robotics Software

arXiv CS Feb 10

Coarse-to-Fine Grounded Memory for LLM Agent Planning

arXiv:2508.15305v2 Announce Type: replace Abstract: Recent advancements in Large Language Models (LLMs) have driven growing interest in LLM-based agents for complex planning tasks. To avoid...

Environment Psychology