arXiv:2509.26536v2 Announce Type: replace-cross Abstract: We introduce OceanGym, the first comprehensive benchmark for ocean underwater embodied agents, designed to advance AI in one of the most demanding real-world environments. Unlike terrestrial or aerial domains, underwater settings present extreme perceptual and…
arXiv:2511.19509v1 Announce Type: new Abstract: Traditional vision-based material perception methods often experience substantial performance degradation under visually impaired conditions, thereby motivating the shift toward non-visual multimodal material perception. Despite this, existing approaches frequently perform naive fusion of multimodal inputs, overlooking…
arXiv:2511.19879v1 Announce Type: cross Abstract: We show that Restricted Boltzmann Machines (RBMs) provide a flexible generative framework for modeling spin configurations in disordered yet strongly correlated phases of frustrated magnets. As a benchmark, we first demonstrate that an RBM can…
arXiv:2511.19513v1 Announce Type: new Abstract: Decentralized learning often involves a weighted global loss with heterogeneous node weights $lambda$. We revisit two natural strategies for incorporating these weights: (i) embedding them into the local losses to retain a uniform weight (and…
Large language models can learn to mistakenly link certain sentence patterns with specific topics — and may then repeat these patterns instead of reasoning.
arXiv:2506.20024v2 Announce Type: replace Abstract: Diffusion models are a powerful tool for probabilistic forecasting, yet most applications in high-dimensional complex systems predict future states individually. This approach struggles to model complex temporal dependencies and fails to explicitly account for the…
arXiv:2511.20641v1 Announce Type: cross Abstract: Long-tailed multi-label visual recognition poses a significant challenge, as images typically contain multiple labels with highly imbalanced class distributions, leading to biased models that favor head classes while underperforming on tail classes. Recent efforts have…
arXiv:2412.03068v2 Announce Type: replace Abstract: Conventional deep models have achieved unprecedented success in time series forecasting. However, facing the challenge of cross-domain generalization, existing studies utilize statistical prior as prompt engineering fails under the huge distribution shift among various domains.…
arXiv:2511.20038v1 Announce Type: cross Abstract: Hard attention Chain-of-Thought (CoT) transformers are known to be Turing-complete. However, it is an open problem whether softmax attention Chain-of-Thought (CoT) transformers are Turing-complete. In this paper, we prove a stronger result that length-generalizable softmax…
arXiv:2511.20462v1 Announce Type: cross Abstract: Normalizing flows (NFs) are end-to-end likelihood-based generative models for continuous data, and have recently regained attention with encouraging progress on image generation. Yet in the video generation domain, where spatiotemporal complexity and computational cost are…
