arXiv:2505.09284v3 Announce Type: replace-cross Abstract: Modeling and reconstructing multidimensional physical dynamics from sparse and off-grid observations presents a fundamental challenge in scientific research. Recently, diffusion-based generative modeling shows promising potential for physical simulation. However, current approaches typically operate on on-grid…
Explosive growth of AI data centers is expected to increase greenhouse gas emissions. Researchers are now seeking solutions to reduce these environmental harms.
arXiv:2509.24814v1 Announce Type: cross Abstract: When solving PDEs, classical numerical solvers are often computationally expensive, while machine learning methods can suffer from spectral bias, failing to capture high-frequency components. Designing an optimal hybrid iterative solver–where, at each iteration, a solver…
arXiv:2410.15986v2 Announce Type: replace-cross Abstract: The Robbins-Siegmund theorem is one of the most important results in stochastic optimization, where it is widely used to prove the convergence of stochastic algorithms. We provide a quantitative version of the theorem, establishing a…
arXiv:2505.17127v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) perform well on tasks such as visual question answering, but it remains unclear whether their reasoning relies more on memorized world knowledge or on the visual information present in the…
arXiv:2506.04430v3 Announce Type: replace Abstract: Fine-tuning Large Language Models (LLMs) is essential for adapting pre-trained models to downstream tasks. Yet traditional first-order optimizers such as Stochastic Gradient Descent (SGD) and Adam incur prohibitive memory and computational costs that scale poorly…
arXiv:2508.18244v2 Announce Type: replace Abstract: Reliably composing Large Language Models (LLMs) for complex, multi-step workflows remains a significant challenge. The dominant paradigm — optimizing discrete prompts in a pipeline — is notoriously brittle and struggles to enforce the formal compliance…
arXiv:2509.22868v1 Announce Type: new Abstract: Neighborhood sampling is an important ingredient in the training of large-scale graph neural networks. It suppresses the exponential growth of the neighborhood size across network layers and maintains feasible memory consumption and time costs. While…
arXiv:2503.02831v2 Announce Type: replace Abstract: Exploration algorithms for reinforcement learning typically replace or augment the reward function with an additional “intrinsic” reward that trains the agent to seek previously unseen states of the environment. Here, we consider an exploration algorithm…
arXiv:2509.22851v1 Announce Type: new Abstract: Margin-based optimization is fundamental to improving generalization and robustness in classification tasks. In the context of reward model learning from preferences within Reinforcement Learning from Human Feedback (RLHF), existing methods typically rely on no margins,…
