| On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment arxiv:2605.11882v1 | arXiv | HIGH | 8/8/9 | 2026-05-12 |
| Sobolev Regularized MMD Gradient Flow arxiv:2605.11884v1 | arXiv | MEDIUM | 7/6/7 | 2026-05-12 |
| From Clever Hans to Scientific Discovery: Interpreting EEG Foundational Transformers with LRP arxiv:2605.11885v1 | arXiv | MEDIUM | 6/7/6 | 2026-05-12 |
| Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models arxiv:2605.11887v1 | arXiv | HIGH | 8/8/9 | 2026-05-12 |
| Incentivizing Truthfulness and Collaborative Fairness in Bayesian Learning arxiv:2605.11889v1 | arXiv | HIGH | 7/7/7 | 2026-05-12 |
| Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems arxiv:2605.11891v1 | arXiv | HIGH | 8/8/8 | 2026-05-12 |
| Toward Modeling Player-Specific Chess Behaviors arxiv:2605.11893v1 | arXiv | MEDIUM | 5/6/5 | 2026-05-12 |
| Few-Shot Synthetic Data Generation with Diffusion Models for Downstream Vision Tasks arxiv:2605.11898v1 | arXiv | HIGH | 7/9/8 | 2026-05-12 |
| Mobile Traffic Camera Calibration from Road Geometry for UAV-Based Traffic Surveillance arxiv:2605.11900v1 | arXiv | HIGH | 6/8/7 | 2026-05-12 |
| AccLock: Unlocking Identity with Heartbeat Using In-Ear Accelerometers arxiv:2605.11901v1 | arXiv | HIGH | 6/7/6 | 2026-05-12 |
| Beyond Point-wise Neural Collapse: A Topology-Aware Hierarchical Classifier for Class-Incremental Learning arxiv:2605.11904v1 | arXiv | HIGH | 8/7/8 | 2026-05-12 |
| Rethinking Supervision Granularity: Segment-Level Learning for LLM-Based Theorem Proving arxiv:2605.11905v1 | arXiv | MEDIUM | 7/7/7 | 2026-05-12 |
| YFPO: A Preliminary Study of Yoked Feature Preference Optimization with Neuron-Guided Rewards for Mathematical Reasoning arxiv:2605.11906v1 | arXiv | MEDIUM | 7/6/6 | 2026-05-12 |
| Procedural-skill SFT across capacity tiers: A W-Shaped pre-SFT Trajectory and Regime-Asymmetric Mechanism on 0.8B-4B Qwen3.5 Models arxiv:2605.11907v1 | arXiv | MEDIUM | 5/7/5 | 2026-05-12 |
| Delightful Gradients Accelerate Corner Escape arxiv:2605.11908v1 | arXiv | MEDIUM | 7/6/8 | 2026-05-12 |
| Rethinking Positional Encoding for Neural Vehicle Routing arxiv:2605.11910v1 | arXiv | HIGH | 7/8/7 | 2026-05-12 |
| Understanding Sample Efficiency in Predictive Coding arxiv:2605.11911v1 | arXiv | MEDIUM | 6/6/7 | 2026-05-12 |
| Vector Scaffolding: Inter-Scale Orchestration for Differentiable Image Vectorization arxiv:2605.11913v1 | arXiv | HIGH | 8/7/8 | 2026-05-12 |
| STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning arxiv:2605.11919v1 | arXiv | HIGH | 7/8/7 | 2026-05-12 |
| Domain Restriction via Multi SAE Layer Transitions arxiv:2605.11920v1 | arXiv | MEDIUM | 6/7/6 | 2026-05-12 |
| StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning arxiv:2605.11922v1 | arXiv | HIGH | 8/8/8 | 2026-05-12 |
| RealDiffusion: Physics-informed Attention for Multi-character Storybook Generation arxiv:2605.11927v1 | arXiv | MEDIUM | 7/6/6 | 2026-05-12 |
| When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents arxiv:2605.11928v1 | arXiv | HIGH | 9/9/9 | 2026-05-12 |
| Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training arxiv:2605.11931v1 | arXiv | HIGH | 7/8/7 | 2026-05-12 |
| Interactive State Space Model with Cross-Modal Local Scanning for Depth Super-Resolution arxiv:2605.11934v1 | arXiv | MEDIUM | 6/7/6 | 2026-05-12 |
| From Noise to Diversity: Random Embedding Injection in LLM Reasoning arxiv:2605.11936v1 | arXiv | HIGH | 9/6/8 | 2026-05-12 |
| Cluster-Aware Neural Collapse Prompt Tuning for Long-Tailed Generalization of Vision-Language Models arxiv:2605.11939v1 | arXiv | HIGH | 7/7/7 | 2026-05-12 |
| Counterfactual Trace Auditing of LLM Agent Skills arxiv:2605.11946v1 | arXiv | HIGH | 8/7/8 | 2026-05-12 |
| From Reaction to Anticipation: Proactive Failure Recovery through Agentic Task Graph for Robotic Manipulation arxiv:2605.11951v1 | arXiv | HIGH | 8/9/8 | 2026-05-12 |
| Assessing and Mitigating Miscalibration in LLM-Based Social Science Measurement arxiv:2605.11954v1 | arXiv | HIGH | 7/8/7 | 2026-05-12 |
| Multimodal Abstractive Summarization of Instructional Videos with Vision-Language Models arxiv:2605.11959v1 | arXiv | MEDIUM | 7/8/7 | 2026-05-12 |
| Chronicles-OCR: A Cross-Temporal Perception Benchmark for the Evolutionary Trajectory of Chinese Characters arxiv:2605.11960v1 | arXiv | HIGH | 8/6/7 | 2026-05-12 |
| What Does It Mean for a Medical AI System to Be Right? arxiv:2605.11963v1 | arXiv | HIGH | 9/8/9 | 2026-05-12 |
| Enhancing Target-Guided Proactive Dialogue Systems via Conversational Scenario Modeling and Intent-Keyword Bridging arxiv:2605.11964v1 | arXiv | MEDIUM | 6/7/6 | 2026-05-12 |
| Assessment of cloud and associated radiation fields from a GAN stochastic cloud subcolumn generator arxiv:2605.11968v1 | arXiv | MEDIUM | 6/7/6 | 2026-05-12 |
| H2G: Hierarchy-Aware Hyperbolic Grouping for 3D Scenes arxiv:2605.11967v1 | arXiv | MEDIUM | 7/7/7 | 2026-05-12 |
| NOFE -- Neural Operator Function Embedding arxiv:2605.11970v1 | arXiv | HIGH | 8/6/8 | 2026-05-12 |
| Cooperative Robotics Reinforced by Collective Perception for Traffic Moderation arxiv:2605.11972v1 | arXiv | HIGH | 7/8/7 | 2026-05-12 |
| Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization arxiv:2605.11974v1 | arXiv | MEDIUM | 6/7/6 | 2026-05-12 |
| Stochastic Minimum-Cost Reach-Avoid Reinforcement Learning arxiv:2605.11975v1 | arXiv | MEDIUM | 7/6/6 | 2026-05-12 |
| Optimizing 4D Wires for Sparse 3D Abstraction arxiv:2605.11977v1 | arXiv | MEDIUM | 8/6/7 | 2026-05-12 |
| On Predicting the Post-training Potential of Pre-trained LLMs arxiv:2605.11978v1 | arXiv | HIGH | 8/7/8 | 2026-05-12 |
| High-lift Wing Separation Control via Bayesian Optimization and Deep Reinforcement Learning arxiv:2605.11981v1 | arXiv | MEDIUM | 7/8/7 | 2026-05-12 |
| QDSB: Quantized Diffusion Schrödinger Bridges arxiv:2605.11983v1 | arXiv | HIGH | 9/6/8 | 2026-05-12 |
| On the Limitations of Large Language Models for Conceptual Database Modeling arxiv:2605.11986v1 | arXiv | MEDIUM | 5/8/6 | 2026-05-12 |
| Random-Set Graph Neural Networks arxiv:2605.11987v1 | arXiv | MEDIUM | 7/6/7 | 2026-05-12 |
| A Transfer Learning Evaluation of Deep Neural Networks for Image Classification arxiv:2605.11989v1 | arXiv | MEDIUM | 4/7/5 | 2026-05-12 |
| Towards Visually-Guided Movie Subtitle Translation for Indic Languages arxiv:2605.11993v1 | arXiv | MEDIUM | 6/8/6 | 2026-05-12 |
| BadSKP: Backdoor Attacks on Knowledge Graph-Enhanced LLMs with Soft Prompts arxiv:2605.11996v1 | arXiv | MEDIUM | 7/7/6 | 2026-05-12 |
| The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures arxiv:2605.11999v1 | arXiv | HIGH | 8/9/8 | 2026-05-12 |