Transformers Can Learn Connectivity in Some Graphs but Not Others
arXiv:2509.22343v2 Announce Type: replace-cross Abstract: Reasoning capability is essential to ensure the factual correctness of the responses of transformer-based Large…
Towards Initialization-dependent and Non-vacuous Generalization Bounds for Overparameterized Shallow Neural Networks
arXiv:2604.00505v3 Announce Type: replace-cross Abstract: Overparameterized neural networks often show a benign overfitting property in the sense of achieving excellent…
FASE : A Fairness-Aware Spatiotemporal Event Graph Framework for Predictive Policing
arXiv:2604.18644v2 Announce Type: replace-cross Abstract: Predictive policing systems that allocate patrol resources based solely on predicted crime risk can unintentionally…
Location-Aware Pretraining for Medical Difference Visual Question Answering
arXiv:2603.04950v2 Announce Type: replace-cross Abstract: Differential medical VQA models compare multiple images to identify clinically meaningful changes and rely on…
GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning
arXiv:2604.20659v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Language Models…
The Tool-Overuse Illusion: Why Does LLM Prefer External Tools over Internal Knowledge?
arXiv:2604.19749v1 Announce Type: new Abstract: Equipping LLMs with external tools effectively addresses internal reasoning limitations. However, it introduces a critical…
RoLegalGEC: Legal Domain Grammatical Error Detection and Correction Dataset for Romanian
arXiv:2604.19593v2 Announce Type: replace-cross Abstract: The importance of clear and correct text in legal documents cannot be understated, and, consequently,…
MOMO: A framework for seamless physical, verbal, and graphical robot skill learning and adaptation
arXiv:2604.20468v1 Announce Type: cross Abstract: Industrial robot applications require increasingly flexible systems that non-expert users can easily adapt for varying…
VTouch++: A Multimodal Dataset with Vision-Based Tactile Enhancement for Bimanual Manipulation
arXiv:2604.20444v1 Announce Type: cross Abstract: Embodied intelligence has advanced rapidly in recent years; however, bimanual manipulation-especially in contact-rich tasks remains…
Cyber Defense Benchmark: Agentic Threat Hunting Evaluation for LLMs in SecOps
arXiv:2604.19533v2 Announce Type: replace-cross Abstract: We introduce the Cyber Defense Benchmark, a benchmark for measuring how well large language model…