arXiv:2603.18256v1 Announce Type: new Abstract: Recent advances in reasoning-based large language models (LLMs) have demonstrated substantial improvements in complex problem-solving tasks. Motivated by these advances, several works have explored the application of reasoning LLMs to drug discovery and molecular design.…
arXiv:2603.19209v1 Announce Type: cross Abstract: Large vision–language models (VLMs) often use a frozen vision backbone, whose image features are mapped into a large language model through a lightweight connector. While transformer-based encoders are the standard visual backbone, we ask whether…
arXiv:2603.18257v1 Announce Type: new Abstract: Selecting relevant state dimensions in the presence of confounded distractors is a causal identification problem: observational statistics alone cannot reliably distinguish dimensions that correlate with actions from those that actions cause. We formalize this as…
arXiv:2602.11534v2 Announce Type: replace Abstract: Self-attention in Transformers relies on globally normalized softmax weights, causing all tokens to compete for influence at every layer. When composed across depth, this interaction pattern induces strong synchronization dynamics that favor convergence toward a…
arXiv:2502.16116v3 Announce Type: replace Abstract: Short-term precipitation nowcasting is essential for flood management, transportation, energy system operations, and emergency response. However, many existing models fail to fully exploit the extensive atmospheric information available, relying primarily on precipitation data alone. This…
arXiv:2510.01643v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks. However, the quadratic complexity of softmax attention remains a central bottleneck that limits their scalability. Alman and Song (NeurIPS 2023a; NeurIPS…
arXiv:2603.19025v1 Announce Type: cross Abstract: When large AI models are deployed as cloud-based services, clients have no guarantee that responses are correct or were produced by the intended model. Rerunning inference locally is infeasible for large models, and existing cryptographic…
arXiv:2603.19222v1 Announce Type: cross Abstract: Denoising diffusion models are widely used for high-quality image and video generation. Their performance depends on noise schedules, which define the distribution of noise levels applied during training and the sequence of noise levels traversed…
arXiv:2510.19731v2 Announce Type: replace-cross Abstract: HAPS are emerging as key enablers in the evolution of 6G wireless networks, bridging terrestrial and non-terrestrial infrastructures. Operating in the stratosphere, HAPS can provide wide-area coverage, low-latency, energy-efficient broadband communications with flexible deployment options…
arXiv:2603.18846v1 Announce Type: cross Abstract: Foundation models are used to extract transferable representations from large amounts of unlabeled data, typically via self-supervised learning (SSL). However, many of these models rely on architectures that offer limited interpretability, which is a critical…
