| Accelerating Video Generation Inference with Sequential-Parallel 3D Positional Encoding Using a Global Time Index | Mar 2, 2026 | | —Unverified | 0 |
| SJD-PV: Speculative Jacobi Decoding with Phrase Verification for Autoregressive Image Generation | Mar 2, 2026 | | —Unverified | 0 |
| Leveraging Model Soups to Classify Intangible Cultural Heritage Images from the Mekong Delta | Mar 2, 2026 | | —Unverified | 0 |
| EnsAug: Augmentation-Driven Ensembles for Human Motion Sequence Analysis | Mar 2, 2026 | | —Unverified | 0 |
| Graph-of-Mark: Promote Spatial Reasoning in Multimodal Language Models with Graph-Based Visual Prompting | Mar 2, 2026 | | —Unverified | 0 |
| Better Eyes, Better Thoughts: Why Vision Chain-of-Thought Fails in Medicine | Mar 2, 2026 | | CodeCode Available | 0 |
| Diagnosing Retrieval vs. Utilization Bottlenecks in LLM Agent Memory | Mar 2, 2026 | | CodeCode Available | 0 |
| Large Language Models as Bidding Agents in Repeated HetNet Auction | Mar 2, 2026 | | —Unverified | 0 |
| On the Reliability of AI Methods in Drug Discovery: Evaluation of Boltz-2 for Structure and Binding Affinity Prediction | Mar 2, 2026 | | —Unverified | 0 |
| A Neural Network-Based Real-time Casing Collar Recognition System for Downhole Instruments | Mar 2, 2026 | | —Unverified | 0 |
| What Helps---and What Hurts: Bidirectional Explanations for Vision Transformers | Mar 2, 2026 | | —Unverified | 0 |
| Extracting Training Dialogue Data from Large Language Model based Task Bots | Mar 2, 2026 | | —Unverified | 0 |
| Bridging the Reproducibility Divide: Open Source Software's Role in Standardizing Healthcare AI | Mar 2, 2026 | | —Unverified | 0 |
| Sleeper Cell: Injecting Latent Malice Temporal Backdoors into Tool-Using LLMs | Mar 2, 2026 | | —Unverified | 0 |
| The Theory behind UMAP? | Mar 2, 2026 | | —Unverified | 0 |
| Selecting Optimal Variable Order in Autoregressive Ising Models | Mar 2, 2026 | | —Unverified | 0 |
| Manifold Aware Denoising Score Matching (MAD) | Mar 2, 2026 | | —Unverified | 0 |
| Contextual Drag: How Errors in the Context Affect LLM Reasoning | Mar 2, 2026 | | —Unverified | 0 |
| Language steering in latent space to mitigate unintended code-switching | Mar 2, 2026 | | —Unverified | 0 |
| Federated Nonlinear System Identification | Mar 2, 2026 | | —Unverified | 0 |
| WhisperNet: A Scalable Solution for Bandwidth-Efficient Collaboration | Mar 2, 2026 | | —Unverified | 0 |
| Quantifying Conversational Reliability of Large Language Models under Multi-Turn Interaction | Mar 2, 2026 | | —Unverified | 0 |
| Practical Deep Heteroskedastic Regression | Mar 2, 2026 | | —Unverified | 0 |
| MobileMold: A Smartphone-Based Microscopy Dataset for Food Mold Detection | Mar 2, 2026 | | —Unverified | 0 |
| The Hidden Width of Deep ResNets: Tight Error Bounds and Phase Diagram | Mar 2, 2026 | | —Unverified | 0 |
| Proceedings for the Inaugural Meeting of the International Society for Tractography -- IST 2025 Bordeaux | Mar 2, 2026 | | —Unverified | 0 |
| Temporal Imbalance of Positive and Negative Supervision in Class-Incremental Learning | Mar 2, 2026 | | —Unverified | 0 |
| DRAGON: LLM-Driven Decomposition and Reconstruction Agents for Large-Scale Combinatorial Optimization | Mar 2, 2026 | | —Unverified | 0 |
| Post-training Large Language Models for Diverse High-Quality Responses | Mar 2, 2026 | | —Unverified | 0 |
| Ignore All Previous Instructions: Jailbreaking as a de-escalatory peace building practise to resist LLM social media bots | Mar 2, 2026 | | —Unverified | 0 |
| VMDNet: Temporal Leakage-Free Variational Mode Decomposition for Electricity Demand Forecasting | Mar 2, 2026 | | —Unverified | 0 |
| From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents | Mar 2, 2026 | | CodeCode Available | 0 |
| FireRed-OCR Technical Report | Mar 2, 2026 | | —Unverified | 3 |
| Hard-constraint physics-residual networks enable robust extrapolation for hydrogen crossover prediction in PEM water electrolyzers | Mar 2, 2026 | | —Unverified | 0 |
| AIRMap: AI-Generated Radio Maps for Wireless Digital Twins | Mar 2, 2026 | | —Unverified | 0 |
| Transform-Invariant Generative Ray Path Sampling for Efficient Radio Propagation Modeling | Mar 2, 2026 | | CodeCode Available | 0 |
| RA-Det: Towards Universal Detection of AI-Generated Images via Robustness Asymmetry | Mar 2, 2026 | | —Unverified | 0 |
| Uniform-in-time concentration in two-layer neural networks via transportation inequalities | Mar 2, 2026 | | —Unverified | 0 |
| TiledAttention: a CUDA Tile SDPA Kernel for PyTorch | Mar 2, 2026 | | —Unverified | 0 |
| Accelerating Single-Pass SGD for Generalized Linear Prediction | Mar 2, 2026 | | —Unverified | 0 |
| GLoRIA: Gated Low-Rank Interpretable Adaptation for Dialectal ASR | Mar 2, 2026 | | —Unverified | 0 |
| Recursive Models for Long-Horizon Reasoning | Mar 2, 2026 | | —Unverified | 0 |
| REMS: a unified solution representation, problem modeling and metaheuristic algorithm design for general combinatorial optimization problems | Mar 2, 2026 | | —Unverified | 0 |
| Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic Framework | Mar 2, 2026 | | —Unverified | 0 |
| Transmit Weights, Not Features: Orthogonal-Basis Aided Wireless Point-Cloud Transmission | Mar 2, 2026 | | —Unverified | 0 |
| Gender Bias in Emotion Recognition by Large Language Models | Mar 2, 2026 | | —Unverified | 0 |
| NAB: Neural Adaptive Binning for Sparse-View CT reconstruction | Mar 2, 2026 | | CodeCode Available | 0 |
| WAXAL: A Large-Scale Multilingual African Language Speech Corpus | Mar 2, 2026 | | —Unverified | 0 |
| nchellwig at SemEval-2026 Task 3: Self-Consistent Structured Generation (SCSG) for Dimensional Aspect-Based Sentiment Analysis using Large Language Models | Mar 2, 2026 | | —Unverified | 0 |
| CoVAE: correlated multimodal generative modeling | Mar 2, 2026 | | —Unverified | 0 |