Related papers: HEAS: Hierarchical Evolutionary Agent-Based Simula…
Hardware-aware Neural Architecture Search (HW-NAS) is a technique used to automatically design the architecture of a neural network for a specific task and target hardware. However, evaluating the performance of candidate architectures is a…
Self-play constitutes a fundamental paradigm for autonomous skill acquisition, whereby agents iteratively enhance their capabilities through self-directed environmental exploration. Conventional self-play frameworks exploit agent symmetry…
In the envisioned future dense urban airspace, multiple companies will operate heterogeneous fleets of small unmanned aerial systems (sUASs), where each fleet includes several homogeneous aircraft with identical policies and configurations,…
Ensemble clustering integrates a set of base clustering results to generate a stronger one. Existing methods usually rely on a co-association (CA) matrix that measures how many times two samples are grouped into the same cluster according…
Classical game-theoretic models typically assume rational agents, complete information, and common knowledge of payoffs - assumptions that are often violated in real-world MAS characterized by uncertainty, misaligned perceptions, and nested…
Problems which require both long-horizon planning and continuous control capabilities pose significant challenges to existing reinforcement learning agents. In this paper we introduce a novel hierarchical reinforcement learning agent which…
We address the multi-agent motion planning problem where interactions, collisions, and congestion co-exist. Conventional game-theoretic planners capture interactions among agents but often converge to conservative, congested equilibria.…
Standard cross-entropy is the default classification loss across virtually all of machine learning, yet it treats all misclassifications equally, ignoring the semantic distances that a class hierarchy encodes. We propose Hierarchy-Aware…
Building accurate and flexible galaxy-halo connection models is crucial in modeling galaxy clustering on non-linear scales. Recent studies have found that halo concentration by itself cannot capture the full galaxy assembly bias effect and…
The operational efficacy of large language models relies heavily on their inference-time context. This has established Context Engineering (CE) as a formal discipline for optimizing these inputs. Current CE methods rely on manually crafted…
Real Time Strategy (RTS) games require macro strategies as well as micro strategies to obtain satisfactory performance since it has large state space, action space, and hidden information. This paper presents a novel hierarchical…
Motivated by the hypothesis that neural network representations encode abstract, interpretable features as linearly accessible, approximately orthogonal directions, sparse autoencoders (SAEs) have become a popular tool in interpretability.…
Search has been proposed as an effective method for self-improving language models and agentic systems, both for post-training sample generation and for inference. However, widely used methods such as best-of-N sampling and tree search face…
Federated learning (FL) was recently proposed to securely train models with data held over multiple locations (``clients'') under the coordination of a central server. Prolonged training times caused by slow clients may hinder the…
We consider several estimation and learning problems that networked agents face when making decisions given their uncertainty about an unknown variable. Our methods are designed to efficiently deal with heterogeneity in both size and…
Scientific theory shift in AI agents requires more than fitting equations to data. An artificial scientific agent must detect whether an existing representational framework remains transportable into a new regime, or whether its language…
The quadratic computational complexity of MultiHead SelfAttention (MHSA) remains a fundamental bottleneck in scaling Large Language Models (LLMs) for longcontext tasks. While sparse and linearized attention mechanisms attempt to mitigate…
Deepgenerative models havebecomeapromisingapproach for human motion prediction due to their ability to capture multimodal distributions and represent diverse human be haviors. However, generating predictions that are both di verse and…
Automated feature engineering (AFE) enables AI systems to autonomously construct high-utility representations from raw tabular data. However, existing AFE methods rely on statistical heuristics, yielding brittle features that fail under…
A new model for evolving Evolutionary Algorithms (EAs) is proposed in this paper. The model is based on the Multi Expression Programming (MEP) technique. Each MEP chromosome encodes an evolutionary pattern that is repeatedly used for…