arXiv subjects

Yuan Zhuang

Publications and source records attributed to Yuan Zhuang.

At least 19 recordsLinked to original sources

arXiv2026

PRIMO: Prior-Informed Odometry from Human-Motion Tracking for Humanoid Robots

Simulation-trained humanoid proprioceptive odometry faces two transfer challenges: training trajectories generated by specific robot control policies intended for deployment cover only a limited range of motions, while sim-to-real mismatch can make unconstrained predictions unreliable. We address both with Prior-Informed Odometry from Human-Motion Tracking (PRIMO). On the data side, we generate odometry supervision by having the humanoid track diverse retargeted human motions in simulation, decoupling supervision from the deployment policies and broadening the training motion distribution. On the model side, a Prior-Informed estimator uses physics- and symmetry-informed priors to structure velocity and rotation prediction and a coarse raw-context pathway to preserve sensor context alongside encoded features, thereby strengthening sim-to-real generalization. Under a unified real-robot protocol, PRIMO reduces mean error by 31.6%-61.7% relative to the strongest evaluated external baseline in each domain-metric comparison. Across two locomotion-policy revisions, policy specialists exhibit symmetric crossover, whereas Tracking-Locomotion training reduces mean opposite-policy simulation error by 86.8%-94.6%. On real dynamic motion, Tracking-Locomotion training reduces mean error by 69.2%-81.7% relative to training on the union of both deployment policies. Across the tested motion compositions, the Prior-Informed estimator consistently lowers mean trajectory errors relative to its Unconstrained counterpart in both simulation and real-robot evaluation. Code is available at https://github.com/Agibot-Spatial-Intelligence/PRIMO.

cs.RO↗

arXiv2026

Artificial Foveated Perception for Mitigating Shortcut Learning in Robotic Foundation Models

Robotic foundation models still need task-specific fine-tuning before deployment, and the fine-tuned policies often break under modest changes in scene layout, lighting, or nearby distractors. We trace this brittleness to \textit{shortcut learning}: fine-tuning supervises actions but not the visual evidence the policy uses, so the policy can settle on scene-level correlations that predict the demonstrations without causing success. We propose Artificial Foveated Perception (AFP), a lightweight, policy-agnostic module that takes the same vision and language inputs as existing Vision-Language-Action and World Action Model pipelines and predicts task-conditioned masks over the relevant objects, the robot, and other action-critical regions. During fine-tuning the masks serve as an auxiliary grounding signal that aligns the policy's visual attention with task-relevant regions; the policy architecture is unchanged, and at inference the policy runs on the original observation stream with no AFP call in the control loop. In simulation with four robotic foundation models and on a real robot with $π_{0.5}$, AFP improves generalization under environmental perturbations, reduces overfitting, and shortens fine-tuning. Ablations over mask quality and grounding-loss design show that these gains come from directing policy learning toward task-relevant visual evidence. Code, data, and videos are available at https://apollo-lab-yale.github.io/26-CoRL-AFP-website/.

cs.RO↗

arXiv2026

Evaluating AlphaEarth Foundations Embeddings for Wildfire Susceptibility Mapping

Wildfire susceptibility mapping typically relies on physical variables assembled from multiple remote-sensing, climate, and geospatial products. AlphaEarth Foundations (AEF) provides analysis-ready geospatial embeddings that may reduce this dependence on heavy harmonisation and task-specific feature engineering, but their value for wildfire susceptibility mapping has not been systematically evaluated. Using Victoria, Australia (2017-2025), as a case study, we show that AEF embeddings can reconstruct commonly used variables in wildfire susceptibility analysis with high accuracy. In downstream susceptibility models trained on satellite-derived fire occurrence data, embedding-based susceptibility models achieve ROC-AUC values above 0.92 and consistently identify high wildfire susceptibility across eastern Victoria, particularly Gippsland and the north-eastern uplands, with additional localized hotspots in central and northwestern Victoria. A key feature of AEF embeddings is their strong near-region transferability within climatically similar regions. When embedding-based models trained in Victoria are applied to Canberra and Western Sydney-Blue Mountains, ROC-AUC improves by around 4% at Canberra and declines by around 2% at Western Sydney-Blue Mountains, compared with a mean decrease of approximately 25% for physical-variable models. These findings provide practical guidance for using AEF embeddings and lay a foundation for scalable wildfire susceptibility mapping workflows for downstream users such as government agencies and (re)insurers.

stat.AP↗

arXiv2026

Secure Long-Range Autonomous Valet Parking: A Reservation Scheme With Three-Factor Authentication and Key Agreement

Long-range autonomous valet parking (LAVP) is increasingly adopted to alleviate traffic congestion and parking difficulties. For large-scale parking demand, reservation can improve parking management. However, existing schemes mainly focus on parking request verification and parking check-in, and do not adequately protect identity legitimacy and communication security during passenger drop-off and pick-up. To address this problem, we propose SecLAVP, a provably secure three-factor authentication and key agreement protocol for LAVP reservation services. SecLAVP combines passwords, biometrics, and smart cards. With assistance from the drop-off/pick-up point (DP), the passenger and the autonomous vehicle (AV) achieve mutual authentication and establish a session key for secure communication. In the Real-Or-Random (ROR) model, we formally prove that SecLAVP provides session-key security. AVISPA simulations show that SecLAVP resists man-in-the-middle attacks, while informal analysis demonstrates that it satisfies 15 defined security goals. Finally, performance evaluation in terms of communication overhead, computational overhead, and scheduling shows that SecLAVP is feasible for practical deployment.

cs.CR↗

arXiv2026

Open-World Video Segmentation

While video segmentation has advanced rapidly on short clips and closed-set benchmarks, open-world video segmentation remains largely unexplored. The challenge is twofold: (1) existing methods are not designed to support object discovery and identity maintenance in long videos of dynamic ego-motion, and (2) existing evaluation protocols rely on a rigid 1:1 matching that unfairly penalizes semantically valid predictions with mismatched granularity. To address both gaps, we introduce Savvy, a practical and strong system for zero-shot open-world long-horizon video segmentation. Savvy combines hierarchical mask discovery, deferred admission, and track consolidation to support persistent object discovery, safe track promotion, and stable long-range identity maintenance. We further propose OGA, a granularity-aware evaluation suite for open-world video segmentation. Built on a Granularity-Agnostic (GA) matching protocol, OGA relaxes conventional 1:1 matching to an n:1 mapping, but still enforces temporal rigor by detecting support discontinuities through sever points and scoring each reference object through its dominant coherent fragment. This prevents fragmented or flickering support from being over-rewarded while enabling GA-adapted metrics and structural diagnostics: identity persistence (IP), and identity concentration (IC). On VIPSeg, we show that standard 1:1 evaluation substantially underestimates open-world methods, whereas GA evaluation recovers much of their suppressed performance. On the more realistic long-horizon benchmarks: ScanNet and HM3D, Savvy consistently outperforms strong baselines across both classical and proposed metrics, including STQ, VPQ$_\infty$, IP and IC. Together, these results establish a practical benchmark and a strong baseline for open-world long-horizon video segmentation.

cs.CV↗

arXiv2026

Examining Agents' Bias Amplification versus Suppression in Multi-Agent Systems

Multi-agent systems are increasingly deployed to support various tasks where agents interact to achieve individual and collective objectives. Although these systems can enhance task performance and decision-making, fairness preservation through bias reduction remains challenging. This study examines how agent-level biases shift and impact system-wide fairness. We use prompts to expose individual agents to group-favoring bias, then assess downstream impacts at the system level. To quantify the impact, we propose Favor Bias Strength (FBS), a zero-centered metric that decomposes bias alteration between favored-group uplift and disfavored-group suppression. Using multiple agent designs, benchmarks, and up-to-date large language models, we show that agents endowed with bias can substantially affect system-wide fairness. Interestingly, when agents are exposed to bias uniformly, the system-wide bias elevates, even exceeding the additive sum of the individual agents' biases. The empirical evidence underscores the criticality of fairness in multi-agent systems, which warrants further analyses and empirical tests.

cs.AI↗

arXiv2026

SEVO: Semantic-Enhanced Virtual Observation for Robust VLA Manipulation via Active Illumination and Data-Centric Collection

Vision-Language-Action (VLA) and imitation-learning policies trained via community toolchains on low-cost hardware frequently fail when deployed outside the training environment. Existing evaluations, including the original ACT and SmolVLA benchmarks, demonstrate high success rates under controlled, fixed backgrounds, yet community practitioners report near-zero transfer to new environments. We present SEVO (Semantic-Enhanced Virtual Observation), a data-centric approach that improves cross-environment manipulation robustness without modifying the policy architecture. SEVO transforms the raw RGB camera stream through three mechanisms: (1) body-fixed cameras whose combined fields of view cover the full manipulation workspace, (2) active red-spectrum illumination that physically normalizes object appearance, and (3) real-time YOLO segmentation overlay that provides a background-invariant semantic cue. Critically, we show that a diversified data collection protocol (systematically varying lighting, backgrounds, and distractors during teleoperation) is the single most important factor for generalization. We target transparent water bottles, objects that visually blend with their surroundings, and select a simple pick-and-place task to enable hundreds of controlled real-robot trials across two mobile platforms. The full pipeline achieves 95% grasp success with ACT and 83% with SmolVLA in the training environment, transferring to novel environments at 85% and 75%. Without SEVO, the same policies achieve only 75%/70% in training and collapse to 30-35% in novel environments. Our results demonstrate that principled observation design and environmental diversity during data collection, not model scaling, enable low-cost robots to operate reliably in everyday household environments.

cs.RO↗

arXiv2026

Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning

Scaling critic capacity is a promising direction for improving off-policy reinforcement learning (RL). However, recent work shows that larger critics are prone to overfitting and instability in replay-based bootstrapped training. In this paper, we propose using Low-Rank Adaptation (LoRA) as a structural regularizer for critic learning. Our approach freezes randomly initialized base matrices and optimizes only the corresponding low-rank adapters, thereby constraining critic updates to a low-dimensional subspace. We evaluate our method across different off-policy RL algorithms, including SAC and FastTD3 based on different network architectures. Empirically, LoRA efficiently reduces critic loss during training and improves overall policy performance, achieving the best or competitive results on most tasks. Extensive experiments demonstrate that our low-rank updates provide a simple and effective form of structural regularization for critic learning in off-policy RL.

cs.LG↗

arXiv2026

Text-to-Distribution Prediction with Quantile Tokens and Neighbor Context

Many applications of LLM-based text regression require predicting a full conditional distribution rather than a single point value. We study distributional regression under empirical-quantile supervision, where each input is paired with multiple observed quantile outcomes, and the target distribution is represented by a dense grid of quantiles. We address two key limitations of current approaches: the lack of local grounding for distribution estimates, and the reliance on shared representations that create an indirect bottleneck between inputs and quantile outputs. In this paper, we introduce Quantile Token Regression, which, to our knowledge, is the first work to insert dedicated quantile tokens into the input sequence, enabling direct input-output pathways for each quantile through self-attention. We further augment these quantile tokens with retrieval, incorporating semantically similar neighbor instances and their empirical distributions to ground predictions with local evidence from similar instances. We also provide the first theoretical analysis of loss functions for quantile regression, clarifying which distributional objectives each optimizes. Experiments on the Inside Airbnb and StackSample benchmark datasets with LLMs ranging from 1.7B to 14B parameters show that quantile tokens with neighbors consistently outperform baselines (~4 points lower MAPE and 2x narrower prediction intervals), with especially large gains on smaller and more challenging datasets where quantile tokens produce substantially sharper and more accurate distributions.

cs.CL↗

arXiv2026

Rhetorical Questions in LLM Representations: A Linear Probing Study

Rhetorical questions are asked not to seek information but to persuade or signal stance. How large language models internally represent them remains unclear. We analyze rhetorical questions in LLM representations using linear probes on two social-media datasets with different discourse contexts, and find that rhetorical signals emerge early and are most stably captured by last-token representations. Rhetorical questions are linearly separable from information-seeking questions within datasets, and remain detectable under cross-dataset transfer, reaching AUROC around 0.7-0.8. However, we demonstrate that transferability does not simply imply a shared representation. Probes trained on different datasets produce different rankings when applied to the same target corpus, with overlap among the top-ranked instances often below 0.2. Qualitative analysis shows that these divergences correspond to distinct rhetorical phenomena: some probes capture discourse-level rhetorical stance embedded in extended argumentation, while others emphasize localized, syntax-driven interrogative acts. Together, these findings suggest that rhetorical questions in LLM representations are encoded by multiple linear directions emphasizing different cues, rather than a single shared direction.

cs.CL↗

arXiv2026

LD-MoLE: Learnable Dynamic Routing for Mixture of LoRA Experts

Recent studies have shown that combining parameter-efficient fine-tuning (PEFT) with mixture-of-experts (MoE) is an effective strategy for adapting large language models (LLMs) to the downstream tasks. However, most existing approaches rely on conventional TopK routing, which requires careful hyperparameter tuning and assigns a fixed number of experts to each token. In this work, we propose LD-MoLE, a Learnable Dynamic routing mechanism for Mixture of LoRA Experts that enables adaptive, token-dependent, and layer-wise expert allocation. Our method replaces the non-differentiable TopK selection with a differentiable routing function and a closed-form solution. Moreover, our design allows the model to adaptively determine the number of experts to activate for each token at different layers. In addition, we introduce an analytical sparsity control objective to regularize the number of activated experts. Extensive experiments on the Qwen3-1.7B and Llama-3.2-3B models show that LD-MoLE achieves the highest average scores compared to state-of-the-art baselines, across a diverse set of benchmarks. Our method not only achieves superior performance, but also demonstrates the ability to learn token-dependent and layer-wise expert allocation.

cs.CL↗

arXiv2025

YOLO-MARL: You Only LLM Once for Multi-Agent Reinforcement Learning

Advancements in deep multi-agent reinforcement learning (MARL) have positioned it as a promising approach for decision-making in cooperative games. However, it still remains challenging for MARL agents to learn cooperative strategies for some game environments. Recently, large language models (LLMs) have demonstrated emergent reasoning capabilities, making them promising candidates for enhancing coordination among the agents. However, due to the model size of LLMs, it can be expensive to frequently infer LLMs for actions that agents can take. In this work, we propose You Only LLM Once for MARL (YOLO-MARL), a novel framework that leverages the high-level task planning capabilities of LLMs to improve the policy learning process of multi-agents in cooperative games. Notably, for each game environment, YOLO-MARL only requires one time interaction with LLMs in the proposed strategy generation, state interpretation and planning function generation modules, before the MARL policy training process. This avoids the ongoing costs and computational time associated with frequent LLMs API calls during training. Moreover, trained decentralized policies based on normal-sized neural networks operate independently of the LLM. We evaluate our method across two different environments and demonstrate that YOLO-MARL outperforms traditional MARL algorithms.

cs.MA↗

arXiv2025

Human and Machine as Seen at the Co-Creation Age: A Co-Word Analysis in Human Machine Co-creation (2014-2024)

This paper explores the evolving landscape of human-machine co-creation, focusing on its development in the context of the ACM Conference on Human Factors in Computing Systems (CHI) from 2014 to 2024. We employ co-word analysis to identify emerging trends, central themes, and the intellectual trajectory of this field. The study highlights the shift from viewing machines as mere tools to recognizing them as collaborative partners in creative processes. By understanding these dynamics, we aim to provide insights into the implications of this paradigm shift for creativity, innovation, and societal impact, ultimately fostering a more inclusive and effective approach to human-machine interaction in various domains.

cs.HC↗

arXiv2025

SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents

Coding agents powered by large language models have shown impressive capabilities in software engineering tasks, but evaluating their performance across diverse programming languages and real-world scenarios remains challenging. We introduce SWE-PolyBench, a new multi-language benchmark for repository-level, execution-based evaluation of coding agents. SWE-PolyBench contains 2110 instances from 21 repositories and includes tasks in Java (165), JavaScript (1017), TypeScript (729) and Python (199), covering bug fixes, feature additions, and code refactoring. We provide a task and repository-stratified subsample (SWE-PolyBench500) and release an evaluation harness allowing for fully automated evaluation. To enable a more comprehensive comparison of coding agents, this work also presents a novel set of metrics rooted in syntax tree analysis. We evaluate leading open source coding agents on SWE-PolyBench, revealing their strengths and limitations across languages, task types, and complexity classes. Our experiments show that current agents exhibit uneven performances across languages and struggle with complex problems while showing higher performance on simpler tasks. SWE-PolyBench aims to drive progress in developing more versatile and robust AI coding assistants for real-world software engineering. Our datasets and code are available at: https://github.com/amazon-science/SWE-PolyBench

cs.SE↗

arXiv2025

SNAIL Radar: A large-scale diverse benchmark for evaluating 4D-radar-based SLAM

4D radars are increasingly favored for odometry and mapping of autonomous systems due to their robustness in harsh weather and dynamic environments. Existing datasets, however, often cover limited areas and are typically captured using a single platform. To address this gap, we present a diverse large-scale dataset specifically designed for 4D radar-based localization and mapping. This dataset was gathered using three different platforms: a handheld device, an e-bike, and an SUV, under a variety of environmental conditions, including clear days, nighttime, and heavy rain. The data collection occurred from September 2023 to February 2024, encompassing diverse settings such as roads in a vegetated campus and tunnels on highways. Each route was traversed multiple times to facilitate place recognition evaluations. The sensor suite included a 3D lidar, 4D radars, stereo cameras, consumer-grade IMUs, and a GNSS/INS system. Sensor data packets were synchronized to GNSS time using a two-step process including a convex-hull-based smoothing and a correlation-based correction. The reference motion for the platforms was generated by registering lidar scans to a terrestrial laser scanner (TLS) point cloud map by a lidar inertial sequential localizer which supports forward and backward processing. The backward pass enables detailed quantitative and qualitative assessments of reference motion accuracy. To demonstrate the dataset's utility, we evaluated several state-of-the-art radar-based odometry and place recognition methods, indicating existing challenges in radar-based SLAM.

cs.RO↗

arXiv2025

MTVHunter: Smart Contracts Vulnerability Detection Based on Multi-Teacher Knowledge Translation

Smart contracts, closely intertwined with cryptocurrency transactions, have sparked widespread concerns about considerable financial losses of security issues. To counteract this, a variety of tools have been developed to identify vulnerability in smart contract. However, they fail to overcome two challenges at the same time when faced with smart contract bytecode: (i) strong interference caused by enormous non-relevant instructions; (ii) missing semantics of bytecode due to incomplete data and control flow dependencies. In this paper, we propose a multi-teacher based bytecode vulnerability detection method, namely Multi-Teacher Vulnerability Hunter (MTVHunter), which delivers effective denoising and missing semantic to bytecode under multi-teacher guidance. Specifically, we first propose an instruction denoising teacher to eliminate noise interference by abstract vulnerability pattern and further reflect in contract embeddings. Secondly, we design a novel semantic complementary teacher with neuron distillation, which effectively extracts necessary semantic from source code to replenish the bytecode. Particularly, the proposed neuron distillation accelerate this semantic filling by turning the knowledge transition into a regression task. We conduct experiments on 229,178 real-world smart contracts that concerns four types of common vulnerabilities. Extensive experiments show MTVHunter achieves significantly performance gains over state-of-the-art approaches.

cs.CR↗

arXiv2025

A Robust and Efficient Visual-Inertial Initialization with Probabilistic Normal Epipolar Constraint

Accurate and robust initialization is essential for Visual-Inertial Odometry (VIO), as poor initialization can severely degrade pose accuracy. During initialization, it is crucial to estimate parameters such as accelerometer bias, gyroscope bias, initial velocity, gravity, etc. Most existing VIO initialization methods adopt Structure from Motion (SfM) to solve for gyroscope bias. However, SfM is not stable and efficient enough in fast-motion or degenerate scenes. To overcome these limitations, we extended the rotation-translation-decoupled framework by adding new uncertainty parameters and optimization modules. First, we adopt a gyroscope bias estimator that incorporates probabilistic normal epipolar constraints. Second, we fuse IMU and visual measurements to solve for velocity, gravity, and scale efficiently. Finally, we design an additional refinement module that effectively reduces gravity and scale errors. Extensive EuRoC dataset tests show that our method reduces gyroscope bias and rotation errors by 16\% and 4\% on average, and gravity error by 29\% on average. On the TUM dataset, our method reduces the gravity error and scale error by 14.2\% and 5.7\% on average respectively. The source code is available at https://github.com/MUCS714/DRT-PNEC.git

cs.RO↗

arXiv2024

Tightly-Coupled VLP/INS Integrated Navigation by Inclination Estimation and Blockage Handling

Visible Light Positioning (VLP) has emerged as a promising technology capable of delivering indoor localization with high accuracy. In VLP systems that use Photodiodes (PDs) as light receivers, the Received Signal Strength (RSS) is affected by the incidence angle of light, making the inclination of PDs a critical parameter in the positioning model. Currently, most studies assume the inclination to be constant, limiting the applications and positioning accuracy. Additionally, light blockages may severely interfere with the RSS measurements but the literature has not explored blockage detection in real-world experiments. To address these problems, we propose a tightly coupled VLP/INS (Inertial Navigation System) integrated navigation system that uses graph optimization to account for varying PD inclinations and VLP blockages. We also discussed the possibility of simultaneously estimating the robot's pose and the locations of some unknown LEDs. Simulations and two groups of real-world experiments demonstrate the efficiency of our approach, achieving an average positioning accuracy of 10 cm during movement and inclination accuracy within 1 degree despite inclination changes and blockages.

cs.RO↗