arXiv subjects

Charles Yang

Publications and source records attributed to Charles Yang.

11 recordsLinked to original sources

arXiv2026

WALL-WM: Carving World Action Modeling at the Event Joints

WALL-WM is a World Action Model that shifts video-action learning from chunk-centric optimization to event-grounded Vision-Language-Action pretraining, using semantically coherent action events as the atomic unit of learning. Existing WAMs commonly initialize from multimodal or video foundation models and then optimize fixed-length action chunks conditioned directly on the current observation and instruction. Although convenient, this chunk-centric formulation creates a fundamental granularity mismatch. Language describes semantic goals and events, vision evolves through continuous scene dynamics, and actions operate at control-level timescales; forcing all three into the same fixed-length prediction window turns VLA training into short-horizon correlation fitting. WALL-WM addresses this mismatch by organizing both supervision and data around semantic events. Specifically, it pairs event-grounded VLA pretraining with a data ecosystem built from event-level captions and cluster-balanced sampling, enabling scalable learning over diverse behaviors, scenes, and task structures. From the same event-pretrained backbone, WALL-WM supports two complementary inference modes. The event mode consumes next-event descriptions and enables variable-length execution chunks, while the unified mode uses a VLM with Staircase Decoding to condition conventional fixed-length chunk inference while preserving a gradient-continuous VLA path. Together with Muon-optimizer-based large-scale pretraining infrastructure, WALL-WM provides a practical scale-up recipe for general-purpose WAMs. Experiments show that WALL-WM generalizes broadly across language, scenes, and tasks, achieving state-of-the-art performance in large-scale real-world generalization evaluation.

cs.RO↗

arXiv2026

Measuring Form and Function in Language Models

We introduce quantitative metrics for child language acquisition to evaluate language models. Our focus is on the formal syntactic and functional discourse properties of determiners in English, which young children acquire early and accurately. We propose Contextual Alternative Choice (CAC), a new prompting method which provides targeted tests for both syntactic and discourse knowledge of language. The method enables direct comparison of language models against children, and more importantly, against statistical benchmarks independently established in empirical research. No current model trained on a comparable amount of data simultaneously meet both formal and functional benchmarks like human children, but some very large models do. We present our results as methodological and technical contributions, with specific emphasis on cognitive status of language models.

cs.CL↗

arXiv2026

ManipArena: Comprehensive Real-world Evaluation of Reasoning-Oriented Generalist Robot Manipulation

Vision-Language-Action (VLA) models and world-action models have emerged as central paradigms for general-purpose robotic intelligence, yet their empirical progress remains constrained by the absence of evaluation protocols that are both physically realistic and diagnostically controlled. Simulator-centric benchmarks provide scale and reproducibility, but cannot fully capture the reality gap induced by perception noise, contact dynamics, latency, calibration error, and hardware constraints. Conversely, real-robot evaluations are often fragmented across platforms, scenes, objects, and scoring rules, making fair comparison and failure attribution difficult. We introduce ManipArena, a standardized real-robot evaluation framework for studying manipulation generalization under matched physical conditions. ManipArena comprises 20 tasks, 10,812 expert trajectories, 13.5M frames, and approximately 188 robot hours across tabletop and mobile manipulation. The framework combines schema-defined task variation, stratified in-domain, visualshift, and semantic-OOD trials, subtask-level partial-credit scoring, three-level language annotations, low-level motor signals, and paired real-to-sim environments reconstructed from physical scenes. Using ManipArena, we evaluate seven tabletop configurations spanning VLA and world-action-model policies. The results show that real-robot conclusions depend not only on architecture, but also on model provenance, fine-tuning regime, data sampling, and annotation granularity. ManipArena thus provides a reproducible and interpretable foundation for diagnosing capability boundaries and failure modes in embodied generalization.

cs.RO↗

arXiv2025

The First Compute Arms Race: the Early History of Numerical Weather Prediction

This paper traces the global race to apply early electronic computers to numerical weather prediction in the decades following World War Two. A brief overview of the early history of numerical weather prediction in the United States, United Kingdom, Sweden, Canada, and Japan is provided. Three critical factors that shaped the development of a national numerical weather prediction are identified: compute capabilities, institution building and state capacity, and talent. Several generalizable lessons are identified with a lens towards modern-day development of national strategies to leverage AI to accelerate scientific competitiveness.

cs.CY↗

arXiv2023

Evaluating Neural Language Models as Cognitive Models of Language Acquisition

The success of neural language models (LMs) on many technological tasks has brought about their potential relevance as scientific theories of language despite some clear differences between LM training and child language acquisition. In this paper we argue that some of the most prominent benchmarks for evaluating the syntactic capacities of LMs may not be sufficiently rigorous. In particular, we show that the template-based benchmarks lack the structural diversity commonly found in the theoretical and psychological studies of language. When trained on small-scale data modeling child language acquisition, the LMs can be readily matched by simple baseline models. We advocate for the use of the readily available, carefully curated datasets that have been evaluated for gradient acceptability by large pools of native speakers and are designed to probe the structural basis of grammar specifically. On one such dataset, the LI-Adger dataset, LMs evaluate sentences in a way inconsistent with human language users. We conclude with suggestions for better connecting LMs with the empirical study of child language acquisition.

cs.CL↗

arXiv2023

Multi-moir\'{e} trilayer graphene: lattice relaxation, electronic structure, and magic angles

We systematically explore the structural and electronic properties of twisted trilayer graphene systems. In general, these systems are characterized by two twist angles, which lead to two incommensurate moir\'{e} periods. We show that lattice relaxation results in the formation of domains of periodic single-moir\'{e} structures only for twist angles close to the simplest fractions. For the majority of other twist angles, the incommensurate moir\'{e} periods lead to a quasicrystalline structure. We identify experimentally relevant magic angles at which the electronic density of states is sharply peaked and strongly correlated physics is most likely to be realized.

cond-mat.str-el↗

arXiv2021

The Greedy and Recursive Search for Morphological Productivity

As children acquire the knowledge of their language's morphology, they invariably discover the productive processes that can generalize to new words. Morphological learning is made challenging by the fact that even fully productive rules have exceptions, as in the well-known case of English past tense verbs, which features the -ed rule against the irregular verbs. The Tolerance Principle is a recent proposal that provides a precise threshold of exceptions that a productive rule can withstand. Its empirical application so far, however, requires the researcher to fully specify rules defined over a set of words. We propose a greedy search model that automatically hypothesizes rules and evaluates their productivity over a vocabulary. When the search for broader productivity fails, the model recursively subdivides the vocabulary and continues the search for productivity over narrower rules. Trained on psychologically realistic data from child-directed input, our model displays developmental patterns observed in child morphology acquisition, including the notoriously complex case of German noun pluralization. It also produces responses to nonce words that, despite receiving only a fraction of the training data, are more similar to those of human subjects than current neural network models' responses are.

cs.CL↗

arXiv2021

A Grounded Approach to Modeling Generic Knowledge Acquisition

We introduce and implement a cognitively plausible model for learning from generic language, statements that express generalizations about members of a category and are an important aspect of concept development in language acquisition (Carlson & Pelletier, 1995; Gelman, 2009). We extend a computational framework designed to model grounded language acquisition by introducing the concept network. This new layer of abstraction enables the system to encode knowledge learned from generic statements and represent the associations between concepts learned by the system. Through three tasks that utilize the concept network, we demonstrate that our extensions to ADAM can acquire generic information and provide an example of how ADAM can be used to model language acquisition.

cs.CL↗

arXiv2021

ADAM: A Sandbox for Implementing Language Learning

We present ADAM, a software system for designing and running child language learning experiments in Python. The system uses a virtual world to simulate a grounded language acquisition process in which the language learner utilizes cognitively plausible learning algorithms to form perceptual and linguistic representations of the observed world. The modular nature of ADAM makes it easy to design and test different language learning curricula as well as learning algorithms. In this report, we describe the architecture of the ADAM system in detail, and illustrate its components with examples. We provide our code.

cs.CL↗

arXiv2020

Interpretable inverse design of particle spectral emissivity using machine learning

We examine the optical properties of a system of nano and micro particles of varying size, shape, and material (including metals and dielectrics, and sub-wavelength and super-wavelength regimes). Training data is generated by numerically solving Maxwel Equations. We then use a combination of decision tree and random forest models to solve both the forward problem (particle design in, optical properties out) and inverse problem (desired optical properties in, range of particle designs out). We show that on even comparatively sparse datasets these machine learning models solve both the forward and inverse problems with excellent accuracy and 4 to 8 orders of magnitude faster than traditional methods. A single trained model is capable of handling the full diversity of our dataset, producing a variety of different candidate particle designs to solve an inverse problem. The interpretability of our models confirms that dielectric particles emit and absorb electromagnetic radiation volumetrically, while metallic particles interaction with light is dominated by surface modes. This work demonstrates the possibility for approachable and interpretable machine learning models to be used for rapid forward and inverse design of devices that span a broad and diverse parameter space.

physics.optics↗

arXiv2017

Sequential Optimal Placement of Distributed Photovoltaics using Downstream Power Index

The optimization of the size and location of Photovoltaic (PV) Distributed Generation (DG) is a method for reducing distribution networks loss, cutting costs for utilities, and integrating renewable energy into the power grid. However, this optimization problem is a difficult mixed continuous discrete problem that is difficult to solve efficiently. Herein, we propose a novel Sequential PVDG Placement algorithm which utilizes a Downstream Power Index (DPI) for PV allocation. We compare Sequential PVDG Placement results with those of Shuffled Frog Leaping Algorithm (SFLA), a memetic heuristic algorithm. Our algorithm demonstrates similar accuracy and drastically less computation time compared to SFLA. Given its high accuracy and low computation time, sequential PVDG allocation algorithm may be useful for rapid online power dispatch, long-term planning, and microgrid operations under high penetration of renewable sources.

physics.app-ph↗