arXiv subjects

Yuyang Gao

Publications and source records attributed to Yuyang Gao.

18 recordsLinked to original sources

arXiv2026

LabEvolver: Training-Free Experience Evolution for Safe and Grounded Wet-Lab Agents

We introduce LabEvolver, a training-free framework that equips safe and grounded wet-lab agents with episodic memory from execution experience. LabEvolver couples a state-grounded inner trial loop for adaptive perception, online planning, and safety validation with an outer evolution loop that distills completed trajectories into reusable skill, strategy, and safety experience. On robotic solution-preparation tasks, LabEvolver demonstrates real-world feasibility, reducing pH-regulation completion time and safety-gate intercepts by 48.2% and 60.0%, respectively. On ALFWorld, it further improves cumulative success rate within 20 steps from 76.2% with ReAct to 91.4% over 500 continual tasks, showing generality beyond wet-lab settings. These results support learn-by-doing experience evolution as a feasible path toward closed-loop automated scientific discovery. The project page is available at https://andygao6186.github.io/LabEvolver/.

cs.RO↗

arXiv2026

Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs

Vision-Language-Action (VLA) models show strong potential for general-purpose robotic manipulation, yet their closed-loop reliability often degrades under local deployment conditions. Existing evaluations typically treat test episodes as independent zero-shot trials. However, real robots often operate repeatedly in the same or slowly changing environments, where successful executions provide environment-verified evidence of reliable behavior patterns. We study this persistent-deployment setting, asking whether a partially competent frozen VLA can improve its reliability by reusing its successful test-time experience. We propose an online success-memory guided test-time adaptation framework for generative VLAs. During deployment, the robot stores progress-calibrated successful observation-action segments in a long-term memory. At inference, it retrieves state-relevant action chunks, filters inconsistent candidates via trajectory-level consistency, and aggregates them into an elite action prior. To incorporate this prior into action generation, we introduce confidence-adaptive prior guidance, which injects the elite prior into an intermediate state of the flow-matching action sampler and adjusts the guidance strength based on retrieval confidence. This design allows the frozen VLA to exploit environment-specific successful experience while preserving observation-conditioned generative refinement. This retrieve-then-steer mechanism enables lightweight, non-parametric test-time adaptation without requiring parameter updates. Simulation and real-world experiments show improved task success and closed-loop stability, especially in long-horizon and multi-stage tasks.

cs.RO↗

arXiv2026

Beyond World-Frame Action Heads: Motion-Centric Action Frames for Vision-Language-Action Models

Vision-Language-Action (VLA) models have advanced rapidly with stronger backbones, broader pre-training, and larger demonstration datasets, yet their action heads remain largely homogeneous: most directly predict action commands in a fixed world coordinate frame. We propose \textbf{MCF-Proto}, a lightweight action head that equips VLA policies with a Motion-Centric Action Frame (MCF) and a prototype-based action parameterization. At each step, the policy predicts a rotation $R_t \in SO(3)$, composes actions in the transformed local frame from a set of prototypes, and maps them back to the world frame for end-to-end training, using only standard demonstrations without auxiliary supervision. This simple design induces stable emergent structure. Without explicit directional labels, the learned local frames develop a stable geometric structure whose axes are strongly compatible with demonstrated end-effector motion. Meanwhile, actions in the learned representation become substantially more compact, with variation captured by fewer dominant directions and more regularly organized by shared prototypes. These structural properties translate into improved robustness, especially under geometric perturbations. Our results suggest that adding lightweight geometric and compositional structure to the action head can materially improve how VLA policies organize and generalize robotic manipulation behavior. An anonymized code repository is provided in the supplementary material.

cs.AI↗

arXiv2025

Glovity: Learning Dexterous Contact-Rich Manipulation via Spatial Wrench Feedback Teleoperation System

We present Glovity, a novel, low-cost wearable teleoperation system that integrates a spatial wrench (force-torque) feedback device with a haptic glove featuring fingertip Hall sensor calibration, enabling feedback-rich dexterous manipulation. Glovity addresses key challenges in contact-rich tasks by providing intuitive wrench and tactile feedback, while overcoming embodiment gaps through precise retargeting. User studies demonstrate significant improvements: wrench feedback boosts success rates in book-flipping tasks from 48% to 78% and reduces completion time by 25%, while fingertip calibration enhances thin-object grasping success significantly compared to commercial glove. Furthermore, incorporating wrench signals into imitation learning (via DP-R3M) achieves high success rate in novel contact-rich scenarios, such as adaptive page flipping and force-aware handovers. All hardware designs, software will be open-sourced. Project website: https://glovity.github.io/

cs.RO↗

arXiv2025

CrackSQL: A Hybrid SQL Dialect Translation System Powered by Large Language Models

Dialect translation plays a key role in enabling seamless interaction across heterogeneous database systems. However, translating SQL queries between different dialects (e.g., from PostgreSQL to MySQL) remains a challenging task due to syntactic discrepancies and subtle semantic variations. Existing approaches including manual rewriting, rule-based systems, and large language model (LLM)-based techniques often involve high maintenance effort (e.g., crafting custom translation rules) or produce unreliable results (e.g., LLM generates non-existent functions), especially when handling complex queries. In this demonstration, we present CrackSQL, the first hybrid SQL dialect translation system that combines rule and LLM-based methods to overcome these limitations. CrackSQL leverages the adaptability of LLMs to minimize manual intervention, while enhancing translation accuracy by segmenting lengthy complex SQL via functionality-based query processing. To further improve robustness, it incorporates a novel cross-dialect syntax embedding model for precise syntax alignment, as well as an adaptive local-to-global translation strategy that effectively resolves interdependent query operations. CrackSQL supports three translation modes and offers multiple deployment and access options including a web console interface, a PyPI package, and a command-line prompt, facilitating adoption across a variety of real-world use cases

cs.DB↗

arXiv2024

DUE: Dynamic Uncertainty-Aware Explanation Supervision via 3D Imputation

Explanation supervision aims to enhance deep learning models by integrating additional signals to guide the generation of model explanations, showcasing notable improvements in both the predictability and explainability of the model. However, the application of explanation supervision to higher-dimensional data, such as 3D medical images, remains an under-explored domain. Challenges associated with supervising visual explanations in the presence of an additional dimension include: 1) spatial correlation changed, 2) lack of direct 3D annotations, and 3) uncertainty varies across different parts of the explanation. To address these challenges, we propose a Dynamic Uncertainty-aware Explanation supervision (DUE) framework for 3D explanation supervision that ensures uncertainty-aware explanation guidance when dealing with sparsely annotated 3D data with diffusion-based 3D interpolation. Our proposed framework is validated through comprehensive experiments on diverse real-world medical imaging datasets. The results demonstrate the effectiveness of our framework in enhancing the predictability and explainability of deep learning models in the context of medical imaging diagnosis applications.

cs.CV↗

arXiv2024

3DPFIX: Improving Remote Novices' 3D Printing Troubleshooting through Human-AI Collaboration

The widespread consumer-grade 3D printers and learning resources online enable novices to self-train in remote settings. While troubleshooting plays an essential part of 3D printing, the process remains challenging for many remote novices even with the help of well-developed online sources, such as online troubleshooting archives and online community help. We conducted a formative study with 76 active 3D printing users to learn how remote novices leverage online resources in troubleshooting and their challenges. We found that remote novices cannot fully utilize online resources. For example, the online archives statically provide general information, making it hard to search and relate their unique cases with existing descriptions. Online communities can potentially ease their struggles by providing more targeted suggestions, but a helper who can provide custom help is rather scarce, making it hard to obtain timely assistance. We propose 3DPFIX, an interactive 3D troubleshooting system powered by the pipeline to facilitate Human-AI Collaboration, designed to improve novices' 3D printing experiences and thus help them easily accumulate their domain knowledge. We built 3DPFIX that supports automated diagnosis and solution-seeking. 3DPFIX was built upon shared dialogues about failure cases from Q&A discourses accumulated in online communities. We leverage social annotations (i.e., comments) to build an annotated failure image dataset for AI classifiers and extract a solution pool. Our summative study revealed that using 3DPFIX helped participants spend significantly less effort in diagnosing failures and finding a more accurate solution than relying on their common practice. We also found that 3DPFIX users learn about 3D printing domain-specific knowledge. We discuss the implications of leveraging community-driven data in developing future Human-AI Collaboration designs.

cs.HC↗

arXiv2023

A Comprehensive Empirical Study of Bugs in Open-Source Federated Learning Frameworks

Federated learning (FL) is a distributed machine learning (ML) paradigm, allowing multiple clients to collaboratively train shared machine learning (ML) models without exposing clients' data privacy. It has gained substantial popularity in recent years, especially since the enforcement of data protection laws and regulations in many countries. To foster the application of FL, a variety of FL frameworks have been proposed, allowing non-experts to easily train ML models. As a result, understanding bugs in FL frameworks is critical for facilitating the development of better FL frameworks and potentially encouraging the development of bug detection, localization and repair tools. Thus, we conduct the first empirical study to comprehensively collect, taxonomize, and characterize bugs in FL frameworks. Specifically, we manually collect and classify 1,119 bugs from all the 676 closed issues and 514 merged pull requests in 17 popular and representative open-source FL frameworks on GitHub. We propose a classification of those bugs into 12 bug symptoms, 12 root causes, and 18 fix patterns. We also study their correlations and distributions on 23 functionalities. We identify nine major findings from our study, discuss their implications and future research directions based on our findings.

cs.SE↗

arXiv2023

Designing a Direct Feedback Loop between Humans and Convolutional Neural Networks through Local Explanations

The local explanation provides heatmaps on images to explain how Convolutional Neural Networks (CNNs) derive their output. Due to its visual straightforwardness, the method has been one of the most popular explainable AI (XAI) methods for diagnosing CNNs. Through our formative study (S1), however, we captured ML engineers' ambivalent perspective about the local explanation as a valuable and indispensable envision in building CNNs versus the process that exhausts them due to the heuristic nature of detecting vulnerability. Moreover, steering the CNNs based on the vulnerability learned from the diagnosis seemed highly challenging. To mitigate the gap, we designed DeepFuse, the first interactive design that realizes the direct feedback loop between a user and CNNs in diagnosing and revising CNN's vulnerability using local explanations. DeepFuse helps CNN engineers to systemically search "unreasonable" local explanations and annotate the new boundaries for those identified as unreasonable in a labor-efficient manner. Next, it steers the model based on the given annotation such that the model doesn't introduce similar mistakes. We conducted a two-day study (S2) with 12 experienced CNN engineers. Using DeepFuse, participants made a more accurate and "reasonable" model than the current state-of-the-art. Also, participants found the way DeepFuse guides case-based reasoning can practically improve their current practice. We provide implications for design that explain how future HCI-driven design can move our practice forward to make XAI-driven insights more actionable.

cs.HC↗

arXiv2022

Saliency-Augmented Memory Completion for Continual Learning

Continual Learning is considered a key step toward next-generation Artificial Intelligence. Among various methods, replay-based approaches that maintain and replay a small episodic memory of previous samples are one of the most successful strategies against catastrophic forgetting. However, since forgetting is inevitable given bounded memory and unbounded tasks, how to forget is a problem continual learning must address. Therefore, beyond simply avoiding catastrophic forgetting, an under-explored issue is how to reasonably forget while ensuring the merits of human memory, including 1. storage efficiency, 2. generalizability, and 3. some interpretability. To achieve these simultaneously, our paper proposes a new saliency-augmented memory completion framework for continual learning, inspired by recent discoveries in memory completion separation in cognitive neuroscience. Specifically, we innovatively propose to store the part of the image most important to the tasks in episodic memory by saliency map extraction and memory encoding. When learning new tasks, previous data from memory are inpainted by an adaptive data generation module, which is inspired by how humans complete episodic memory. The module's parameters are shared across all tasks and it can be jointly trained with a continual learning classifier as bilevel optimization. Extensive experiments on several continual learning and image classification benchmarks demonstrate the proposed method's effectiveness and efficiency.

cs.LG↗

arXiv2022

On phase at a resonance in slow-fast Hamiltonian systems

We consider a slow-fast Hamiltonian system with one fast angular variable (a fast phase) whose frequency vanishes on some surface in the space of slow variables (a resonant surface). Systems of such form appear in the study of dynamics of charged particles in inhomogeneous magnetic field under influence of a high-frequency electrostatic waves. Trajectories of the averaged over the fast phase system cross the resonant surface. The fast phase makes $\sim \frac {1}{\varepsilon}$ turns before arrival to the resonant surface ($\varepsilon$ is a small parameter of the problem). An asymptotic formula for the value of the phase at the arrival to the resonance was derived earlier in the context of study of charged particle dynamics on the basis of heuristic considerations without any estimates of its accuracy. We provide a rigorous derivation of this formula and prove that its accuracy is $O(\sqrt \varepsilon)$ (up to a logarithmic correction). Numerics indicate that this estimate for the accuracy is optimal.

math.DS↗

arXiv2022

Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning

As the societal impact of Deep Neural Networks (DNNs) grows, the goals for advancing DNNs become more complex and diverse, ranging from improving a conventional model accuracy metric to infusing advanced human virtues such as fairness, accountability, transparency (FaccT), and unbiasedness. Recently, techniques in Explainable Artificial Intelligence (XAI) are attracting considerable attention, and have tremendously helped Machine Learning (ML) engineers in understanding AI models. However, at the same time, we started to witness the emerging need beyond XAI among AI communities; based on the insights learned from XAI, how can we better empower ML engineers in steering their DNNs so that the model's reasonableness and performance can be improved as intended? This article provides a timely and extensive literature overview of the field Explanation-Guided Learning (EGL), a domain of techniques that steer the DNNs' reasoning process by adding regularization, supervision, or intervention on model explanations. In doing so, we first provide a formal definition of EGL and its general learning paradigm. Secondly, an overview of the key factors for EGL evaluation, as well as summarization and categorization of existing evaluation procedures and metrics for EGL are provided. Finally, the current and potential future application areas and directions of EGL are discussed, and an extensive experimental study is presented aiming at providing comprehensive comparative studies among existing EGL models in various popular application domains, such as Computer Vision (CV) and Natural Language Processing (NLP) domains.

cs.AI↗

arXiv2022

RES: A Robust Framework for Guiding Visual Explanation

Despite the fast progress of explanation techniques in modern Deep Neural Networks (DNNs) where the main focus is handling "how to generate the explanations", advanced research questions that examine the quality of the explanation itself (e.g., "whether the explanations are accurate") and improve the explanation quality (e.g., "how to adjust the model to generate more accurate explanations when explanations are inaccurate") are still relatively under-explored. To guide the model toward better explanations, techniques in explanation supervision - which add supervision signals on the model explanation - have started to show promising effects on improving both the generalizability as and intrinsic interpretability of Deep Neural Networks. However, the research on supervising explanations, especially in vision-based applications represented through saliency maps, is in its early stage due to several inherent challenges: 1) inaccuracy of the human explanation annotation boundary, 2) incompleteness of the human explanation annotation region, and 3) inconsistency of the data distribution between human annotation and model explanation maps. To address the challenges, we propose a generic RES framework for guiding visual explanation by developing a novel objective that handles inaccurate boundary, incomplete region, and inconsistent distribution of human annotations, with a theoretical justification on model generalizability. Extensive experiments on two real-world image datasets demonstrate the effectiveness of the proposed framework on enhancing both the reasonability of the explanation and the performance of the backbone DNNs model.

cs.CV↗

arXiv2022

Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignment

While Deep Neural Networks (DNNs) are deriving the major innovations in nearly every field through their powerful automation, we are also witnessing the peril behind automation as a form of bias, such as automated racism, gender bias, and adversarial bias. As the societal impact of DNNs grows, finding an effective way to steer DNNs to align their behavior with the human mental model has become indispensable in realizing fair and accountable models. We propose a novel framework of Interactive Attention Alignment (IAA) that aims at realizing human-steerable Deep Neural Networks (DNNs). IAA leverages DNN model explanation method as an interactive medium that humans can use to unveil the cases of biased model attention and directly adjust the attention. In improving the DNN using human-generated adjusted attention, we introduce GRADIA, a novel computational pipeline that jointly maximizes attention quality and prediction accuracy. We evaluated IAA framework in Study 1 and GRADIA in Study 2 in a gender classification problem. Study 1 found applying IAA can significantly improve the perceived quality of model attention from human eyes. In Study 2, we found using GRADIA can (1) significantly improve the perceived quality of model attention and (2) significantly improve model performance in scenarios where the training samples are limited. We present implications for future interactive user interfaces design towards human-alignable AI.

cs.AI↗

arXiv2021

BEAN: Interpretable Representation Learning with Biologically-Enhanced Artificial Neuronal Assembly Regularization

Deep neural networks (DNNs) are known for extracting useful information from large amounts of data. However, the representations learned in DNNs are typically hard to interpret, especially in dense layers. One crucial issue of the classical DNN model such as multilayer perceptron (MLP) is that neurons in the same layer of DNNs are conditionally independent of each other, which makes co-training and emergence of higher modularity difficult. In contrast to DNNs, biological neurons in mammalian brains display substantial dependency patterns. Specifically, biological neural networks encode representations by so-called neuronal assemblies: groups of neurons interconnected by strong synaptic interactions and sharing joint semantic content. The resulting population coding is essential for human cognitive and mnemonic processes. Here, we propose a novel Biologically Enhanced Artificial Neuronal assembly (BEAN) regularization to model neuronal correlations and dependencies, inspired by cell assembly theory from neuroscience. Experimental results show that BEAN enables the formation of interpretable neuronal functional clusters and consequently promotes a sparse, memory/computation-efficient network without loss of model performance. Moreover, our few-shot learning experiments demonstrate that BEAN could also enhance the generalizability of the model when training samples are extremely limited.

cs.NE↗

arXiv2021

Schematic Memory Persistence and Transience for Efficient and Robust Continual Learning

Continual learning is considered a promising step towards next-generation Artificial Intelligence (AI), where deep neural networks (DNNs) make decisions by continuously learning a sequence of different tasks akin to human learning processes. It is still quite primitive, with existing works focusing primarily on avoiding (catastrophic) forgetting. However, since forgetting is inevitable given bounded memory and unbounded task loads, 'how to reasonably forget' is a problem continual learning must address in order to reduce the performance gap between AIs and humans, in terms of 1) memory efficiency, 2) generalizability, and 3) robustness when dealing with noisy data. To address this, we propose a novel ScheMAtic memory peRsistence and Transience (SMART) framework for continual learning with external memory that builds on recent advances in neuroscience. The efficiency and generalizability are enhanced by a novel long-term forgetting mechanism and schematic memory, using sparsity and 'backward positive transfer' constraints with theoretical guarantees on the error bound. Robust enhancement is achieved using a novel short-term forgetting mechanism inspired by background information-gated learning. Finally, an extensive experimental analysis on both benchmark and real-world datasets demonstrates the effectiveness and efficiency of our model.

cs.LG↗

arXiv2020

Long-distance transmission of quantum key distribution coexisting with classical optical communication over weakly-coupled few-mode fiber

Quantum key distribution (QKD) is one of the most practical applications in quantum information processing, which can generate information-theoretical secure keys between remote parties. With the help of the wavelength-division multiplexing technique, QKD has been integrated with the classical optical communication networks. The wavelength-division multiplexing can be further improved by the mode-wavelength dual multiplexing technique with few-mode fiber (FMF), which has additional modal isolation and large effective core area of mode, and particularly is practical in fabrication and splicing technology compared with the multi-core fiber. Here, we present for the first time a QKD implementation coexisting with classical optical communication over weakly-coupled FMF using all-fiber mode-selective couplers. The co-propagation of QKD with one 100 Gbps classical data channel at -2.60 dBm launched power is achieved over 86 km FMF with 1.3 kbps real-time secure key generation. Compared with single-mode fiber, the average Raman noise in FMF is reduced by 86% at the same fiber-input power. Our work implements an important approach to the integration between QKD and classical optical communication and previews the compatibility of quantum communications with the next-generation mode division multiplexing networks

quant-ph↗

arXiv2019

DynGraph2Seq: Dynamic-Graph-to-Sequence Interpretable Learning for Health Stage Prediction in Online Health Forums

Online health communities such as the online breast cancer forum enable patients (i.e., users) to interact and help each other within various subforums, which are subsections of the main forum devoted to specific health topics. The changing nature of the users' activities in different subforums can be strong indicators of their health status changes. This additional information could allow health-care organizations to respond promptly and provide additional help for the patient. However, modeling complex transitions of an individual user's activities among different subforums over time and learning how these correspond to his/her health stage are extremely challenging. In this paper, we first formulate the transition of user activities as a dynamic graph with multi-attributed nodes, then formalize the health stage inference task as a dynamic graph-to-sequence learning problem, and hence propose a novel dynamic graph-to-sequence neural networks architecture (DynGraph2Seq) to address all the challenges. Our proposed DynGraph2Seq model consists of a novel dynamic graph encoder and an interpretable sequence decoder that learn the mapping between a sequence of time-evolving user activity graphs and a sequence of target health stages. We go on to propose dynamic graph hierarchical attention mechanisms to facilitate the necessary multi-level interpretability. A comprehensive experimental analysis of its use for a health stage prediction task demonstrates both the effectiveness and the interpretability of the proposed models.

cs.LG↗