| Energy-Efficient Deep Learning for Traffic Classification on Microcontrollers | Jun 12, 2025 | Computational EfficiencyDeep Learning | —Unverified | 0 |
| Deep Learning-based Multi Project InP Wafer Simulation for Unsupervised Surface Defect Detection | Jun 12, 2025 | Defect DetectionManagement | —Unverified | 0 |
| Unsourced Adversarial CAPTCHA: A Bi-Phase Adversarial CAPTCHA Framework | Jun 12, 2025 | Adversarial AttackDiversity | —Unverified | 0 |
| VRBench: A Benchmark for Multi-Step Reasoning in Long Narrative Videos | Jun 12, 2025 | Question Answering | —Unverified | 0 |
| GenWorld: Towards Detecting AI-generated Real-world Simulation Videos | Jun 12, 2025 | Video Generation | —Unverified | 0 |
| InstaInpaint: Instant 3D-Scene Inpainting with Masked Large Reconstruction Model | Jun 12, 2025 | 3D Scene Reconstruction | —Unverified | 0 |
| Generalist Models in Medical Image Segmentation: A Survey and Performance Comparison with Task-Specific Approaches | Jun 12, 2025 | Image SegmentationMedical Image Segmentation | —Unverified | 0 |
| Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop | Jun 12, 2025 | ARC | —Unverified | 0 |
| Optimus-3: Towards Generalist Multimodal Minecraft Agents with Scalable Task Experts | Jun 12, 2025 | DiversityMinecraft | —Unverified | 0 |
| Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills | Jun 12, 2025 | Large Language ModelTask Planning | —Unverified | 0 |
| Primender Sequence: A Novel Mathematical Construct for Testing Symbolic Inference and AI Reasoning | Jun 12, 2025 | Benchmarking | —Unverified | 0 |
| Grounded Vision-Language Navigation for UAVs with Open-Vocabulary Goal Understanding | Jun 12, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Graph Neural Networks for Automatic Addition of Optimizing Components in Printed Circuit Board Schematics | Jun 12, 2025 | | CodeCode Available | 0 |
| Spurious Rewards: Rethinking Training Signals in RLVR | Jun 12, 2025 | MathMathematical Reasoning | CodeCode Available | 3 |
| StepProof: Step-by-step verification of natural language mathematical proofs | Jun 12, 2025 | Mathematical ProofsSentence | CodeCode Available | 0 |
| Monitoring Decomposition Attacks in LLMs with Lightweight Sequential Monitors | Jun 12, 2025 | Question AnsweringSafety Alignment | CodeCode Available | 0 |
| Unsupervised Deformable Image Registration with Structural Nonparametric Smoothing | Jun 12, 2025 | Image Registration | CodeCode Available | 0 |
| Foundation Models for Causal Inference via Prior-Data Fitted Networks | Jun 12, 2025 | Bayesian InferenceCausal Inference | —Unverified | 0 |
| Saturation Self-Organizing Map | Jun 12, 2025 | Continual Learning | CodeCode Available | 0 |
| Data-Driven Prediction of Dynamic Interactions Between Robot Appendage and Granular Material | Jun 12, 2025 | Dimensionality ReductionRobot Navigation | —Unverified | 0 |
| RT-VC: Real-Time Zero-Shot Voice Conversion with Speech Articulatory Coding | Jun 12, 2025 | CPUVoice Conversion | —Unverified | 0 |
| EmbodiedGen: Towards a Generative 3D World Engine for Embodied Intelligence | Jun 12, 2025 | Image to 3DLayout Generation | —Unverified | 0 |
| Viability of Future Actions: Robust Safety in Reinforcement Learning via Entropy Regularization | Jun 12, 2025 | Reinforcement Learning (RL) | CodeCode Available | 0 |
| SlotPi: Physics-informed Object-centric Reasoning Models | Jun 12, 2025 | ObjectQuestion Answering | CodeCode Available | 0 |
| Learning Chaotic Dynamics with Neuromorphic Network Dynamics | Jun 12, 2025 | | CodeCode Available | 0 |
| TexTailor: Customized Text-aligned Texturing via Effective Resampling | Jun 12, 2025 | Texture Synthesis | CodeCode Available | 0 |
| Augmenting Large Language Models with Static Code Analysis for Automated Code Quality Improvements | Jun 12, 2025 | Prompt EngineeringRAG | —Unverified | 0 |
| AniMaker: Automated Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation | Jun 12, 2025 | Video Generation | CodeCode Available | 3 |
| SoK: Evaluating Jailbreak Guardrails for Large Language Models | Jun 12, 2025 | | CodeCode Available | 1 |
| Low-Barrier Dataset Collection with Real Human Body for Interactive Per-Garment Virtual Try-On | Jun 12, 2025 | Virtual Try-on | CodeCode Available | 1 |
| CreatiPoster: Towards Editable and Controllable Multi-Layer Graphic Design Generation | Jun 12, 2025 | | CodeCode Available | 2 |
| A Benchmark for Generalizing Across Diverse Team Strategies in Competitive Pokémon | Jun 12, 2025 | Large Language ModelStarcraft | CodeCode Available | 1 |
| Understanding In-Context Learning on Structured Manifolds: Bridging Attention to Kernel Methods | Jun 12, 2025 | In-Context Learningregression | —Unverified | 0 |
| Execution Guided Line-by-Line Code Generation | Jun 12, 2025 | Code Generation | CodeCode Available | 2 |
| QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction | Jun 12, 2025 | 3D Semantic Occupancy PredictionAutonomous Driving | CodeCode Available | 2 |
| Hessian Geometry of Latent Space in Generative Models | Jun 12, 2025 | | CodeCode Available | 1 |
| TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree | Jun 12, 2025 | Continual Learning | CodeCode Available | 3 |
| Semantic-decoupled Spatial Partition Guided Point-supervised Oriented Object Detection | Jun 12, 2025 | object-detectionObject Detection | CodeCode Available | 1 |
| SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks | Jun 12, 2025 | | CodeCode Available | 1 |
| GeoCAD: Local Geometry-Controllable CAD Generation | Jun 12, 2025 | | CodeCode Available | 0 |
| Harmonizing Geometry and Uncertainty: Diffusion with Hyperspheres | Jun 12, 2025 | | CodeCode Available | 0 |
| ConStyX: Content Style Augmentation for Generalizable Medical Image Segmentation | Jun 12, 2025 | Domain GeneralizationImage Segmentation | CodeCode Available | 0 |
| EQA-RM: A Generative Embodied Reward Model with Test-time Scaling | Jun 12, 2025 | Embodied Question AnsweringQuestion Answering | CodeCode Available | 0 |
| HalLoc: Token-level Localization of Hallucinations for Vision Language Models | Jun 12, 2025 | HallucinationImage Captioning | CodeCode Available | 0 |
| Accelerating Diffusion Large Language Models with SlowFast: The Three Golden Principles | Jun 12, 2025 | | CodeCode Available | 1 |
| VideoDeepResearch: Long Video Understanding With Agentic Tool Using | Jun 12, 2025 | MMEVideo MME | CodeCode Available | 2 |
| The Diffusion Duality | Jun 12, 2025 | Text Generation | CodeCode Available | 3 |
| Conversational Search: From Fundamentals to Frontiers in the LLM Era | Jun 12, 2025 | Conversational SearchInstruction Following | —Unverified | 0 |
| BioClinical ModernBERT: A State-of-the-Art Long-Context Encoder for Biomedical and Clinical NLP | Jun 12, 2025 | DecoderDomain Adaptation | CodeCode Available | 1 |
| Unsupervised Protoform Reconstruction through Parsimonious Rule-guided Heuristics and Evolutionary Search | Jun 12, 2025 | | CodeCode Available | 0 |