研究
Silence Boosts Collective Taste Judgment
Introduces Silence Routing framework for collective intelligence in taste domains using music preferences. Specifies when contributors should speak, report, or stay silent.
ArXiv AI · 217 天前
February 12, 2026
圖像
SigLIP Boosts Multi-Label ECG Classification
Adapts SigLIP contrastive learning with a Jaccard-based sigmoid loss for multi-label ECG classification using real-world data. Incorporates medical knowledge and techniques like higher embedding dimensions and random cropping.
ArXiv AI · 217 天前
應用
Semantic Labels Enhance TPRA Retrieval
Explores semantic labeling for TPRA questionnaires using LLMs and hybrid SSSL. Compares direct labeling vs.
ArXiv AI · 217 天前
圖像
Self-Supervised SR Quality Assessor
Proposes no-reference IQA for real-world super-resolved images using content-free SSL. Pretrains multi-SR model representations via contrastive learning.
ArXiv AI · 217 天前
應用
ScratchWorld Tests GUI Agents
Introduces ScratchWorld benchmark with 83 tasks for multimodal GUI agents in Scratch. Uses primitive/composite modes and execution-based evaluation.
ArXiv AI · 217 天前
模型
Safety Alignment for Omni-Modal LLMs
OmniSteer addresses cross-modality vulnerabilities in OLLMs using AdvBench-Omni dataset and modality-semantics decoupling. Uncovers mid-layer dissolution and extracts golden refusal vector via SVD.
ArXiv AI · 217 天前
應用
SAF Improves Parkinson's ECoG Prediction
Introduces first reproducible ECoG dataset from rat models for Parkinson's disease prediction. Swap-Adversarial Framework (SAF) uses channel swapping and domain-adversarial training to tackle inter-subject variability and HDLSS issues.
ArXiv AI · 217 天前
圖像
RSHallu: Hallucination Eval for RS MLLMs
RSHallu studies hallucinations in remote-sensing MLLMs with a new taxonomy, benchmark, and dual-mode checker. Provides datasets for mitigation via training and plug-and-play strategies.
ArXiv AI · 217 天前
應用
Robust Policy Optimization for Recommendations
DRPO tackles model collapse in off-policy generative recommendation via optimistic distributionally robust optimization. Proves hard filtering recovers high-quality data from noisy logs.
ArXiv AI · 217 天前
模型
RLCER Evolves CoT Rubrics
RLCER reinforces chain-of-thought via self-evolving rubrics without human labels. Outperforms outcome-centric RLVR on reasoning tasks.
ArXiv AI · 217 天前
研究
Rewiring Sparsifies Efficient GNNs
Explores adaptive rewiring and sparsification for scalable GNNs using Erdős-Rényi models. Tested on power grid N-1 analysis with GCN/GIN.
ArXiv AI · 217 天前
圖像
RealHD Dataset Detects AI Fake Images
RealHD offers 730k high-quality real and AI-generated images from advanced methods like text-to-image and inpainting. Addresses prior dataset flaws with diverse prompts, metadata, and masks.
ArXiv AI · 217 天前
研究
Quantum ICO Merges Sensing and Computation
Proposes quantum scheme using indefinite causal order (ICO) for integrated sensing and computation on one state. Agent superposes observation-then-compute and compute-then-observation orders.
ArXiv AI · 217 天前
應用
Quadrupeds Cooperate for Super Jumps
Co-jump enables two quadrupeds to synchronize jumps up to 1.5m via MAPPO and curriculum, without communication. Achieves 144% height gain over solo robots using proprioception.
ArXiv AI · 217 天前
基建
μpscaling Optimizes Model Warm Starts
Proposes principled upscaling for model widths inspired by μP, with theory guaranteeing equivalence to widened versions. Extends μTransfer for hyperparameter scaling, avoiding costly retuning at larger sizes.
ArXiv AI · 217 天前
研究
ProtoGLAD Enables Interpretable Graph Anomalies
ProtoGLAD detects graph-level anomalies by contrasting with nearest normal prototype graphs discovered via point-set kernels. It iteratively clusters normal graphs for unsupervised detection.
ArXiv AI · 217 天前
研究
Privacy Shield for Mobile GUI Agents
Framework anonymizes sensitive UI data with type-preserving placeholders for cloud-based GUI agents. Detects PII across screenshots, XML, and instructions via layered architecture.
ArXiv AI · 217 天前
應用
Privacy-Aware XR Collaboration Framework
PRISM-XR integrates multimodal LLMs for XR collaboration while filtering sensitive data from XR headset frames on edge servers. It features lightweight registration and customizable content-sharing for efficient synchronization.
ArXiv AI · 217 天前
應用
Policy-Car Swerving Absorbs Traffic Jams
Proposes SVDD-JAD strategy mimicking police swerving to suppress stop-and-go waves via slow-in/fast-out maneuvers. Analyzes five key parameters measurable with roadside detectors.
ArXiv AI · 217 天前
模型
PiT-PO Boosts Equation Discovery with RL
PiT-PO uses reinforcement learning to evolve LLMs for symbolic regression, enforcing physical validity and parsimony. It treats LLMs as adaptive generators updated by search feedback.
ArXiv AI · 217 天前
應用
Physics-Augmented Vehicle Health Monitoring
Dual-stream unsupervised model fuses anomaly detection with physics proxies for embedded vehicle monitoring. Distinguishes transient shocks from sustained high-load states like hill climbing.
ArXiv AI · 217 天前
研究
PEST Masters 3D Turbulence Simulation
Presents Physics-Enhanced Swin Transformer (PEST) for 3D turbulence. Uses windowed attention, frequency loss, and physics constraints.
ArXiv AI · 217 天前
編程
PELLI Framework Boosts LLM Code Quality
PELLI is an iterative framework for integrating LLMs into software generation, evaluating code on maintainability, performance, and reliability. It tests five popular LLMs across three domains using Python standards.
ArXiv AI · 217 天前
開源
Open-Source TTS E-book Narrator
Calliope creates synchronized narrated EPUB3 e-books from text using open-source TTS like XTTS-v2. Ensures exact audio-text sync via direct timestamps, preserves original layout offline.
ArXiv AI · 217 天前
研究
OmniVL-Guard Fights Multimodal Forgeries
OmniVL-Guard unifies vision-language forgery detection and grounding with balanced RL. Self-Evolving CoT and ARSPO tackle difficulty bias.
ArXiv AI · 217 天前
研究
OmniSapiens: HARPO for Social Behaviors
OmniSapiens-7B 2.0 uses HARPO RL to train a unified model across heterogeneous social tasks. HARPO balances learning via modulated advantages.
ArXiv AI · 217 天前
研究
NSAM: Neuro-Symbolic Action Masking in DRL
NSAM learns symbolic models and action masks automatically during DRL to avoid infeasible actions. It integrates symbolic reasoning with deep policy optimization mutually.
ArXiv AI · 217 天前
研究
Neurosymbolic AI Conquers Schauder Theory
White paper integrates nonuniform ellipticity breakthrough with topos-theoretic LRMs. Formalizes sharp Schauder estimates using ghost equations.
ArXiv AI · 217 天前
研究
NAEs Balance Interpretability and Accuracy
Neural Additive Experts use mixture-of-experts per feature with context-gated integration for flexible additivity. Targeted regularization ensures smooth transitions from additive to interactive models.
ArXiv AI · 217 天前
應用
Multi-Layer AI Malware Detector
SecureScan uses logistic regression, heuristics, and VirusTotal for URL/file/binary triage. Achieves 93.1% accuracy with balanced precision/recall.
ArXiv AI · 217 天前