arXiv:2510.11978v1 Announce Type: new Abstract: Preference-based finetuning of vision–language models (VLMs) is brittle: trivially wrong negatives inject uninformative gradients that destabilize training. We recast alignment as textbf{learning-dynamics–aware optimization} and introduce textbf{Cooling-Weighted DPO (CW-DPO)}, a two-stage recipe that explicitly models and…
arXiv:2412.00382v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have demonstrated strong performance in graph representation learning across various real-world applications. However, they often produce biased predictions caused by sensitive attributes, such as religion or gender, an issue that has…
arXiv:2510.11984v1 Announce Type: new Abstract: Despite the striking successes of deep neural networks trained with gradient-based optimization, these methods differ fundamentally from their biological counterparts. This gap raises key questions about how nature achieves robust, sample-efficient learning at minimal energy…
arXiv:2502.03698v3 Announce Type: replace Abstract: Learning from Demonstration (LfD) algorithms have shown promising results in robotic manipulation tasks, but their vulnerability to offline universal perturbation attacks remains underexplored. This paper presents a comprehensive study of adversarial attacks on both classic…
arXiv:2510.11987v1 Announce Type: new Abstract: Second-order methods are emerging as promising alternatives to standard first-order optimizers such as gradient descent and ADAM for training neural networks. Though the advantages of including curvature information in computing optimization steps have been celebrated…
arXiv:2505.10833v4 Announce Type: replace Abstract: Model merging provides a scalable alternative to multi-task training by combining specialized finetuned models through parameter arithmetic, enabling efficient deployment without the need for joint training or access to all task data. While recent methods…
arXiv:2510.12026v1 Announce Type: new Abstract: Mamba, a recently proposed linear-time sequence model, has attracted significant attention for its computational efficiency and strong empirical performance. However, a rigorous theoretical understanding of its underlying mechanisms remains limited. In this work, we provide…
In a new study, MIT researchers evaluated quantum materials’ potential for scalable commercial success — and identified promising candidates.
arXiv:2403.00841v2 Announce Type: replace-cross Abstract: Offline Reinforcement Learning (RL) enables policy improvement from fixed datasets without online interactions, making it highly suitable for real-world applications lacking efficient simulators. Despite its success in the single-agent setting, offline multi-agent RL remains a…
arXiv:2507.19349v2 Announce Type: replace Abstract: As sixth generation (6G) wireless networks evolve, accurate signal-to-interference-noise ratio (SINR) maps are becoming increasingly critical for effective resource management and optimization. However, acquiring such maps at high resolution is often cost-prohibitive, creating a severe…
