| Acoustic Classification of Maritime Vessels using Learnable Filterbanks | May 29, 2025 | ClassificationRobust classification | CodeCode Available | 0 |
| Can Emotion Fool Anti-spoofing? | May 29, 2025 | Emotion RecognitionSpeech Emotion Recognition | —Unverified | 0 |
| A New Deep-learning-Based Approach For mRNA Optimization: High Fidelity, Computation Efficiency, and Multiple Optimization Factors | May 29, 2025 | Computational EfficiencyTranslation | CodeCode Available | 0 |
| DSR-Bench: Evaluating the Structural Reasoning Abilities of LLMs via Data Structures | May 29, 2025 | Attribute | CodeCode Available | 0 |
| Hidden Persuasion: Detecting Manipulative Narratives on Social Media During the 2022 Russian Invasion of Ukraine | May 29, 2025 | Binary ClassificationClassification | —Unverified | 0 |
| Diversity of Transformer Layers: One Aspect of Parameter Scaling Laws | May 29, 2025 | Diversity | —Unverified | 0 |
| Using Reasoning Models to Generate Search Heuristics that Solve Open Instances of Combinatorial Design Problems | May 29, 2025 | Code Generation | CodeCode Available | 0 |
| Mamba Integrated with Physics Principles Masters Long-term Chaotic System Forecasting | May 29, 2025 | EpidemiologyMamba | CodeCode Available | 0 |
| OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generation | May 29, 2025 | | CodeCode Available | 2 |
| Grounded Reinforcement Learning for Visual Reasoning | May 29, 2025 | reinforcement-learningReinforcement Learning | —Unverified | 0 |
| Table-R1: Inference-Time Scaling for Table Reasoning | May 29, 2025 | Fact Verification | CodeCode Available | 1 |
| DenoiseRotator: Enhance Pruning Robustness for LLMs via Importance Concentration | May 29, 2025 | | CodeCode Available | 1 |
| Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles | May 29, 2025 | Reinforcement Learning (RL) | CodeCode Available | 1 |
| ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind | May 29, 2025 | | CodeCode Available | 1 |
| Uni-MuMER: Unified Multi-Task Fine-Tuning of Vision-Language Model for Handwritten Mathematical Expression Recognition | May 29, 2025 | Handwritten Mathmatical Expression RecognitionLanguage Modeling | CodeCode Available | 1 |
| CDR-Agent: Intelligent Selection and Execution of Clinical Decision Rules Using Large Language Model Agents | May 29, 2025 | Decision MakingLanguage Modeling | CodeCode Available | 0 |
| TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning | May 29, 2025 | In-Context LearningState Space Models | CodeCode Available | 3 |
| K^2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting | May 29, 2025 | Decision MakingProbabilistic Time Series Forecasting | CodeCode Available | 1 |
| ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering | May 29, 2025 | Large Language ModelPrompt Engineering | CodeCode Available | 2 |
| QLIP: A Dynamic Quadtree Vision Prior Enhances MLLM Performance Without Retraining | May 29, 2025 | Question AnsweringRepresentation Learning | CodeCode Available | 0 |
| DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers | May 29, 2025 | Metric Learningparameter-efficient fine-tuning | CodeCode Available | 1 |
| Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds | May 29, 2025 | Bayesian Optimization | —Unverified | 0 |
| Sentinel: Attention Probing of Proxy Models for LLM Context Compression with an Understanding Perspective | May 29, 2025 | DecoderRAG | CodeCode Available | 1 |
| Threading the Needle: Reweaving Chain-of-Thought Reasoning to Explain Human Label Variation | May 29, 2025 | | CodeCode Available | 0 |
| Measuring Participant Contributions in Decentralized Federated Learning | May 29, 2025 | Federated Learning | —Unverified | 0 |
| AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views | May 29, 2025 | Neural RenderingNovel View Synthesis | —Unverified | 0 |
| Query Routing for Retrieval-Augmented Language Models | May 29, 2025 | Contrastive LearningRAG | —Unverified | 0 |
| Matryoshka Model Learning for Improved Elastic Student Models | May 29, 2025 | LAMBADAMath | —Unverified | 0 |
| Graph Positional Autoencoders as Self-supervised Learners | May 29, 2025 | Graph Property PredictionMissing Elements | —Unverified | 0 |
| Let's Reason Formally: Natural-Formal Hybrid Reasoning Enhances LLM's Math Capability | May 29, 2025 | MathMathematical Reasoning | —Unverified | 0 |
| VITON-DRR: Details Retention Virtual Try-on via Non-rigid Registration | May 29, 2025 | Image GenerationSemantic Segmentation | CodeCode Available | 0 |
| DiCoFlex: Model-agnostic diverse counterfactuals with flexible control | May 29, 2025 | counterfactualDecision Making | —Unverified | 0 |
| LoLA: Low-Rank Linear Attention With Sparse Caching | May 29, 2025 | 4k8k | —Unverified | 0 |
| Qwen Look Again: Guiding Vision-Language Reasoning Models to Re-attention Visual Information | May 29, 2025 | Hallucination | CodeCode Available | 0 |
| Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models | May 29, 2025 | 2k4k | CodeCode Available | 1 |
| Meta-Learning Approaches for Speaker-Dependent Voice Fatigue Models | May 29, 2025 | Meta-Learning | —Unverified | 0 |
| X2Graph for Cancer Subtyping Prediction on Biological Tabular Data | May 29, 2025 | Deep Learning | —Unverified | 0 |
| Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models | May 29, 2025 | Autonomous DrivingDiagnostic | CodeCode Available | 3 |
| A Practical Approach for Building Production-Grade Conversational Agents with Workflow Graphs | May 29, 2025 | Chatbot | —Unverified | 0 |
| Conceptual Framework Toward Embodied Collective Adaptive Intelligence | May 29, 2025 | Navigate | —Unverified | 0 |
| EmoBench-UA: A Benchmark Dataset for Emotion Detection in Ukrainian | May 29, 2025 | Emotion Classification | —Unverified | 0 |
| Dynamic Spectral Backpropagation for Efficient Neural Network Training | May 29, 2025 | Efficient Neural NetworkMeta-Learning | —Unverified | 0 |
| Radiant Triangle Soup with Soft Connectivity Forces for 3D Reconstruction and Novel View Synthesis | May 29, 2025 | 3D ReconstructionNovel View Synthesis | —Unverified | 0 |
| Gradient Boosting Decision Tree with LSTM for Investment Prediction | May 29, 2025 | Stock Price Prediction | —Unverified | 0 |
| Adaptive Spatial Augmentation for Semi-supervised Semantic Segmentation | May 29, 2025 | Data AugmentationDiversity | —Unverified | 0 |
| CryoCCD: Conditional Cycle-consistent Diffusion with Biophysical Modeling for Cryo-EM Synthesis | May 29, 2025 | Contrastive LearningDiversity | —Unverified | 0 |
| LAFR: Efficient Diffusion-based Blind Face Restoration via Latent Codebook Alignment Adapter | May 29, 2025 | Blind Face RestorationDenoising | —Unverified | 0 |
| R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation | May 29, 2025 | BenchmarkingImage Generation | —Unverified | 0 |
| OmniEarth-Bench: Towards Holistic Evaluation of Earth's Six Spheres and Cross-Spheres Interactions with Multimodal Observational Earth Data | May 29, 2025 | scientific discovery | —Unverified | 0 |
| CLIP-AE: CLIP-assisted Cross-view Audio-Visual Enhancement for Unsupervised Temporal Action Localization | May 29, 2025 | Action LocalizationInformation Retrieval | —Unverified | 0 |