arXiv:2603.08960v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models deliver high quality at low training FLOPs, but this efficiency often vanishes at inference. We identify a double penalty that structurally disadvantages MoE architectures during decoding: first, expert routing fragments microbatches and…
arXiv:2601.22444v2 Announce Type: replace Abstract: Forecasting future events is highly valuable in decision-making and is a robust measure of general intelligence. As forecasting is probabilistic, developing and evaluating AI forecasters requires generating large numbers of diverse and difficult questions, and…
arXiv:2603.08965v1 Announce Type: new Abstract: AI memory systems increasingly organize knowledge into graph structures — knowledge graphs, entity relations, community hierarchies — yet lack a principled mechanism for continuous resolution control: where do the qualitative boundaries between abstraction levels lie,…
arXiv:2603.07313v2 Announce Type: replace Abstract: Robustness under latent distribution shift remains challenging in partially observable reinforcement learning. We formalize a focused setting where an adversary selects a hidden initial latent distribution before the episode, termed an adversarial latent-initial-state POMDP. Theoretically,…
arXiv:2603.08972v1 Announce Type: new Abstract: Internet of Things (IoT) Analytics often involves applying machine learning (ML) models on data streams. In such scenarios, traditional ML paradigms face obstacles related to continuous learning while dealing with concept drifts, temporal dependence, and…
arXiv:2502.06574v4 Announce Type: replace-cross Abstract: Semivalue-based data valuation uses cooperative-game theory intuitions to assign each data point a value reflecting its contribution to a downstream task. Still, those values depend on the practitioner’s choice of utility, raising the question: How…
arXiv:2603.08987v1 Announce Type: new Abstract: Recent advances in medical large language models have explored Test-Time Reinforcement Learning (TTRL) to enhance reasoning. However, standard TTRL often relies on majority voting (MV) as a heuristic supervision signal, which can be unreliable in…
arXiv:2510.06261v2 Announce Type: replace-cross Abstract: We present AlphaApollo, an agentic reasoning system that targets two bottlenecks in foundation-model reasoning: (1) limited reasoning capacity for complex, long-horizon problem solving and (2) unreliable test-time evolution without trustworthy verification. AlphaApollo orchestrates models and…
arXiv:2603.09014v1 Announce Type: new Abstract: Flow models have rapidly become the go-to method for training and deploying large-scale generators, owing their success to inference-time flexibility via adjustable integration steps. A crucial ingredient in flow training is the choice of coupling…
arXiv:2602.16144v2 Announce Type: replace-cross Abstract: As multimodal systems increasingly process sensitive personal data, the ability to selectively revoke specific data modalities has become a critical requirement for privacy compliance and user autonomy. We present Missing-by-Design (MBD), a unified framework for…
