相关论文: Probing the Impact of Scale on Data-Efficient, Gen…

Much human and computational effort has aimed to improve how deep reinforcement learning algorithms perform on benchmarks such as the Atari Learning Environment. Comparatively less effort has focused on understanding what has been learned…

The current paradigm of test-time scaling relies on generating long reasoning traces ("thinking" more) before producing a response. In agent problems that require interaction, this can be done by generating thinking traces before acting in…

Classical scaling laws model AI performance as monotonically improving with model size. We challenge this assumption by deriving the Institutional Scaling Law, showing that institutional fitness -- jointly measuring capability, trust,…

We evaluate the use of original game curricula supported by the Atari 2600 console as a heterogeneous transfer benchmark for deep reinforcement learning agents. Game designers created curricula using combinations of several discrete…

We investigate the performance of linear consensus algorithms subject to a scaling of the underlying network size. Specifically, we model networked systems with $n^{\text{th}}$ order integrator dynamics over families of undirected, weighted…

Many networking applications require timely access to recent network measurements, which can be captured using a sliding window model. Maintaining such measurements is a challenging task due to the fast line speed and scarcity of fast…

Energy and pollution are urging problems of the 21th century. By gradually changing the actual power grid system, smart grid may evolve into different systems by means of size, elements and strategies, but its fundamental requirements and…

Despite substantial investment in safety alignment, the vulnerability of large language models to sophisticated multi-turn adversarial attacks remains poorly characterized, and whether model scale or inference mode affects robustness is…

Assessing the capabilities and risks of frontier AI systems is a critical area of research, and recent work has shown that repeated sampling from models can dramatically increase both. For instance, repeated sampling has been shown to…

Transformers have proven highly effective across various applications, especially in handling sequential data such as natural languages and time series. However, transformer models often lack clear interpretability, and the success of…

Recent work in deep reinforcement learning has allowed algorithms to learn complex tasks such as Atari 2600 games just from the reward provided by the game, but these algorithms presently require millions of training steps in order to…

Designing autonomous drone swarms is hampered by a vast design space spanning platform, algorithmic, and numerical-strength choices. We perform large-scale agent-based simulations in three canonical scenarios: swarm-on-swarm battle,…

Real-world artificial intelligence (AI) systems are increasingly required to operate autonomously in dynamic, uncertain, and continuously changing environments. However, most existing AI models rely on predefined objectives, static training…

We consider parallel simulations for asynchronous systems employing L processing elements that are arranged on a ring. Processors communicate only among the nearest neighbors and advance their local simulated time only if it is guaranteed…

Foundation models have rapidly advanced AI, raising the question of whether their decisions will ultimately surpass human strategies in real-world domains. The exponential, and possibly super-exponential, pace of AI development makes such…

The performance of embodied agents has been shown to improve by increasing model parameters, dataset size, and compute. This has been demonstrated in domains from robotics to video games, when generative learning objectives on offline…

The Transformer architecture aggregates input information through the self-attention mechanism, but there is no clear understanding of how this information is mixed across the entire model. Additionally, recent works have demonstrated that…

Scaling laws have made language-model performance predictable from model size, data, and compute, but they typically treat the optimizer as a fixed training detail. We show that this assumption misses a fundamental axis of representation…

Large Language Model (LLM) agents show great promise for complex, multi-turn tool-use tasks, but their development is often hampered by the extreme scarcity of high-quality training data. Supervised fine-tuning (SFT) on synthetic data leads…

This study proposes an anomaly detection method based on the Transformer architecture with integrated multiscale feature perception, aiming to address the limitations of temporal modeling and scale-aware feature representation in cloud…