8718 papers
This paper systematically evaluates four training objectives—Cross-Entropy, Prototype, Triplet, and Average Precision Losses—for out-of-distribution detection in image classification, revealing that while they achieve comparable in-distribution accuracy, Cross-Entropy Loss delivers the most consistent performance across both near- and far-OOD scenarios under standardized protocols.
This paper presents a semi-supervised deep generative anomaly detection framework, utilizing a residual autoencoder with a dense bottleneck, that achieves high-accuracy, real-time defect detection and localization on high-speed pharmaceutical Blow-Fill-Seal production lines while operating within strict 500 ms timing constraints.
The paper proposes Difficulty-Scaled Segment-Wise GRPO (DSS-GRPO), a reinforcement learning method that decomposes training signals into separate "think" and "answer" segments with difficulty-aware scaling to compress reasoning traces without compromising answer quality.
The paper proposes Staged Multi-Agent Training (SMAT), a four-stage curriculum that progressively trains a human-exoskeleton system to achieve stable co-adaptation, resulting in a control policy that significantly reduces hip muscle activation and delivers consistent, positive mechanical power across diverse users without requiring subject-specific retraining.
This paper proposes a high-fidelity synthetic data generation pipeline using NVIDIA Omniverse to address data scarcity and privacy constraints in airport logistics, demonstrating that mixed training with synthetic data and only 40% of real annotations achieves performance comparable to full real-data baselines while reducing annotation effort by 25–35%.
The paper proposes AtomicVLA, a unified planning-and-execution framework that utilizes a Skill-Guided Mixture-of-Experts architecture to dynamically compose atomic skill abstractions, thereby significantly improving scalability and performance in long-horizon robotic manipulation and continual learning tasks compared to existing monolithic VLA models.
Ref-DGS is an efficient, rasterization-based framework that achieves state-of-the-art novel view synthesis on reflective scenes by decoupling surface geometry from specular reflections using a dual Gaussian representation and a lightweight adaptive mixing shader, thereby avoiding the high computational cost of explicit ray tracing.
This paper presents an AI-driven workflow combining a Gaussian mixture variational autoencoder with Pearson correlation coefficients to analyze sparsely sampled X-ray hyperspectral data, enabling the generation of nanometer-resolution multiphase maps that reveal complex phase heterogeneity and transition zones in individual Na-ion cathode particles during electrochemical cycling.
This survey provides a comprehensive overview of memory mechanisms in autonomous LLM agents from 2022 to early 2026, formalizing a write–manage–read framework, introducing a three-dimensional taxonomy, analyzing key mechanisms and evaluation benchmarks, and outlining critical applications and future challenges.
This paper proposes CDA-VSR, a compressed-domain-aware online video super-resolution network that leverages motion vectors, residual maps, and frame types to achieve real-time, high-quality reconstruction with significantly reduced computational cost compared to state-of-the-art methods.
TDM-R1 introduces a novel reinforcement learning paradigm that enables few-step diffusion models to effectively incorporate non-differentiable rewards by decoupling surrogate reward learning from generator training, achieving state-of-the-art performance across various metrics and scaling to powerful models like Z-Image with only 4 inference steps.
VoiceSHIELD-Small is a lightweight, real-time model built on Whisper-small that simultaneously transcribes speech and detects malicious content with 99.16% accuracy, offering a faster and more secure alternative to traditional text-based filtering for voice AI systems.
This paper presents YAQIN, a co-designed AI application that integrates Islamic frameworks and user-centered design to provide culturally sensitive mental health support for Muslim women in the UK, addressing gaps in trust and engagement through a faith-aware chatbot and guided journaling tool.
This paper demonstrates that large language models exhibit robust decision biases in two-arm bandit tasks, characterized by stubborn exploitation and low learning rates that persist across decoding parameters, thereby posing significant challenges for optimal human-AI collaboration.
This paper proposes a novel multi-agent architecture that automates structural modeling and analysis using OpenSeesPy by decomposing complex tasks into specialized agents to effectively reduce hallucinations and error accumulation, achieving high accuracy and scalability across benchmark frame problems.
This paper evaluates the capabilities of various large language models, including Llama-3 and ChatGPT, in solving diverse discrete optimization problems using natural language datasets, revealing that while stronger models generally perform better, Chain-of-Thought reasoning is not universally effective and data augmentation can improve performance on simpler tasks despite introducing instability.
The paper proposes FedShift, a novel two-stage "Hide and Find" distributed adversarial attack for Federated Graph Learning that injects hidden shifters to stealthily guide poisoned data toward a target boundary and efficiently generates perturbations, achieving superior effectiveness, robustness against defenses, and a 90% reduction in convergence time compared to existing methods.
The paper proposes DECADE, an unsupervised diffusion model that achieves temporally consistent denoising of Rb-82 dynamic cardiac PET images without paired training data, effectively reducing noise while preserving quantitative accuracy for myocardial blood flow and flow reserve metrics.
The QuadAI system for SemEval-2026 Task 3 achieves superior performance in dimensional aspect-based sentiment regression by employing an ensemble learning framework that combines a hybrid RoBERTa encoder with large language models, leveraging the complementary strengths of both architectures to significantly reduce RMSE and improve correlation scores.
ProgAgent is a JAX-native continual reinforcement learning agent that mitigates catastrophic forgetting and reward specification costs by unifying progress-aware reward learning from unlabeled videos with adversarial refinement and a stability-plasticity balanced architecture, achieving superior performance on robotic manipulation benchmarks.