arXiv:2604.26039v1 Announce Type: new Abstract: The optimal kernel configuration for Mixture-of-Experts (MoE) inference depends on both batch size and the expert routing distribution, yet production systems dispatch from batch size alone, leaving 10-70% of kernel throughput unrealized. We present RaMP,…
arXiv:2604.26070v1 Announce Type: new Abstract: Causal inference in continuous-time sequential decision problems is challenged by hidden confounders. We show that, in latent state-space models with time-varying interventions, observability of the latent dynamics from observed data is necessary for identifying dynamic…
arXiv:2604.25982v1 Announce Type: new Abstract: Frontier AI both amplifies existing risks and introduces qualitatively novel challenges. Not only is there a notable lack of stable scientific consensus resulting from the rapid pace of technological change, but emerging frontier AI safety…
arXiv:2604.26024v1 Announce Type: new Abstract: Class-level evaluation can conceal substantial performance disparities across subconcepts within the same class, causing models that perform well on average to fail on specific subpopulations. Prior work has shown that common evaluation measures for imbalanced…
arXiv:2604.25978v1 Announce Type: new Abstract: Prior work on node classification has shown that Graph Neural Networks (GNNs) can learn representations that transfer across graphs, when underlying graph properties are shared. For a fixed graph, one would then expect GNNs trained…
arXiv:2604.25975v1 Announce Type: new Abstract: Key-value (KV) caching is essential for large language model inference, yet its memory overhead poses a critical bottleneck for long-context generation. Existing eviction policies predominantly rely on empirical heuristics, lacking a rigorous theoretical foundation. This…
arXiv:2604.25972v1 Announce Type: new Abstract: In multi-agent reinforcement learning (MARL), the integration of a communication mechanism, allowing agents to better learn to coordinate their actions and converge on their objectives by sharing information. Based on an interaction graph, a subclass…
arXiv:2405.13729v3 Announce Type: replace Abstract: In this paper, we study an under-explored but important factor of diffusion generative models, i.e., the combinatorial complexity. Data samples are generally high-dimensional, and for various structured generation tasks, additional attributes are combined to associate…
arXiv:2604.26073v1 Announce Type: new Abstract: Industrial chemical plants often operate under strict data confidentiality constraints, making centralized data-driven process modeling difficult. Federated learning (FL) provides a promising solution by enabling collaborative model training across distributed facilities without sharing raw operational…
arXiv:2506.05878v2 Announce Type: replace Abstract: We present a feasibility-seeking approach to neural network training. This mathematical optimization framework is distinct from conventional gradient-based loss minimization and uses projection operators and iterative projection algorithms. We reformulate training as a large-scale feasibility…
