| Deferred is Better: A Framework for Multi-Granularity Deferred Interaction of Heterogeneous Features | Mar 13, 2026 | | —Unverified | 0 |
| Self-Supervised Speech Models Encode Phonetic Context via Position-dependent Orthogonal Subspaces | Mar 13, 2026 | | —Unverified | 0 |
| SteerRM: Debiasing Reward Models via Sparse Autoencoders | Mar 13, 2026 | | —Unverified | 0 |
| Residual SODAP: Residual Self-Organizing Domain-Adaptive Prompting with Structural Knowledge Preservation for Continual Learning | Mar 13, 2026 | | —Unverified | 0 |
| Spectral-Geometric Neural Fields for Pose-Free LiDAR View Synthesis | Mar 13, 2026 | | —Unverified | 0 |
| MoKus: Leveraging Cross-Modal Knowledge Transfer for Knowledge-Aware Concept Customization | Mar 13, 2026 | | —Unverified | 0 |
| MalURLBench: A Benchmark Evaluating Agents' Vulnerabilities When Processing Web URLs | Mar 13, 2026 | | CodeCode Available | 0 |
| Deep Distance Measurement Method for Unsupervised Multivariate Time Series Similarity Retrieval | Mar 13, 2026 | | —Unverified | 0 |
| AutoClimDS: Climate Data Science Agentic AI -- A Knowledge Graph is All You Need | Mar 13, 2026 | | —Unverified | 0 |
| Visual Alignment of Medical Vision-Language Models for Grounded Radiology Report Generation | Mar 13, 2026 | | —Unverified | 0 |
| From Formal Language Theory to Statistical Learning: Finite Observability of Subregular Languages | Mar 13, 2026 | | CodeCode Available | 0 |
| UniPrompt-CL: Sustainable Continual Learning in Medical AI with Unified Prompt Pools | Mar 13, 2026 | | —Unverified | 0 |
| FSDAM: Few-Shot Driving Attention Modeling via Vision-Language Coupling | Mar 13, 2026 | | —Unverified | 0 |
| LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning | Mar 13, 2026 | | —Unverified | 1 |
| DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving | Mar 13, 2026 | | —Unverified | 0 |
| SDF-Net: Structure-Aware Disentangled Feature Learning for Opticall-SAR Ship Re-identification | Mar 13, 2026 | | CodeCode Available | 0 |
| Literary Narrative as Moral Probe : A Cross-System Framework for Evaluating AI Ethical Reasoning and Refusal Behavior | Mar 13, 2026 | | —Unverified | 0 |
| When Drafts Evolve: Speculative Decoding Meets Online Learning | Mar 13, 2026 | | —Unverified | 0 |
| Stake the Points: Structure-Faithful Instance Unlearning | Mar 13, 2026 | | —Unverified | 0 |
| Purify Once, Edit Freely: Breaking Image Protections under Model Mismatch | Mar 13, 2026 | | —Unverified | 0 |
| A Method for Learning Large-Scale Computational Construction Grammars from Semantically Annotated Corpora | Mar 13, 2026 | | —Unverified | 0 |
| PISE: Physics-Anchored Semantically-Enhanced Deep Computational Ghost Imaging for Robust Low-Bandwidth Machine Perception | Mar 13, 2026 | | —Unverified | 0 |
| MovieTeller: Tool-augmented Movie Synopsis with ID Consistent Progressive Abstraction | Mar 13, 2026 | | —Unverified | 0 |
| Spectral Defense Against Resource-Targeting Attack in 3D Gaussian Splatting | Mar 13, 2026 | | —Unverified | 0 |
| Long-form RewardBench: Evaluating Reward Models for Long-form Generation | Mar 13, 2026 | | —Unverified | 0 |
| EvolveCoder: Evolving Test Cases via Adversarial Verification for Code Reinforcement Learning | Mar 13, 2026 | | —Unverified | 0 |
| How to Build a Quantum Supercomputer: Scaling from Hundreds to Millions of Qubits | Mar 13, 2026 | | —Unverified | 0 |
| Multimodal Continual Learning with MLLMs from Multi-scenario Perspectives | Mar 13, 2026 | | —Unverified | 0 |
| Do You See What I Am Pointing At? Gesture-Based Egocentric Video Question Answering | Mar 13, 2026 | | —Unverified | 0 |
| Towards unified brain-to-text decoding across speech production and perception | Mar 13, 2026 | | —Unverified | 0 |
| Seeing Eye to Eye: Enabling Cognitive Alignment Through Shared First-Person Perspective in Human-AI Collaboration | Mar 13, 2026 | | —Unverified | 0 |
| VCBench: A Streaming Counting Benchmark for Spatial-Temporal State Maintenance in Long Videos | Mar 13, 2026 | | —Unverified | 0 |
| Design-Specification Tiling for ICL-based CAD Code Generation | Mar 13, 2026 | | —Unverified | 0 |
| SciDesignBench: Benchmarking and Improving Language Models for Scientific Inverse Design | Mar 13, 2026 | | —Unverified | 0 |
| Graph In-Context Operator Networks for Generalizable Spatiotemporal Prediction | Mar 13, 2026 | | —Unverified | 0 |
| On Using Machine Learning to Early Detect Catastrophic Failures in Marine Diesel Engines | Mar 13, 2026 | | —Unverified | 0 |
| SLICE: Semantic Latent Injection via Compartmentalized Embedding for Image Watermarking | Mar 13, 2026 | | —Unverified | 0 |
| SAP: Segment Any 4K Panorama | Mar 13, 2026 | | —Unverified | 0 |
| PVI: Plug-in Visual Injection for Vision-Language-Action Models | Mar 13, 2026 | | —Unverified | 0 |
| A New Kernel Regularity Condition for Distributed Mirror Descent: Broader Coverage and Simpler Analysis | Mar 13, 2026 | | —Unverified | 0 |
| SAVA-X: Ego-to-Exo Imitation Error Detection via Scene-Adaptive View Alignment and Bidirectional Cross View Fusion | Mar 13, 2026 | | CodeCode Available | 0 |
| Upper Bounds for Local Learning Coefficients of Three-Layer Neural Networks | Mar 13, 2026 | | —Unverified | 0 |
| NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval | Mar 13, 2026 | | —Unverified | 0 |
| coDrawAgents: A Multi-Agent Dialogue Framework for Compositional Image Generation | Mar 13, 2026 | | —Unverified | 0 |
| CLARIN-PT-LDB: An Open LLM Leaderboard for Portuguese to assess Language, Culture and Civility | Mar 13, 2026 | | —Unverified | 0 |
| HMS-BERT: Hybrid Multi-Task Self-Training for Multilingual and Multi-Label Cyberbullying Detection | Mar 13, 2026 | | —Unverified | 0 |
| Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization | Mar 13, 2026 | | —Unverified | 0 |
| MotionAnymesh: Physics-Grounded Articulation for Simulation-Ready Digital Twins | Mar 13, 2026 | | —Unverified | 0 |
| SGMatch: Semantic-Guided Non-Rigid Shape Matching with Flow Regularization | Mar 13, 2026 | | —Unverified | 0 |
| ARL-Tangram: Unleash the Resource Efficiency in Agentic Reinforcement Learning | Mar 13, 2026 | | —Unverified | 0 |