arXiv subjects

Justin Yu

Publications and source records attributed to Justin Yu.

At least 19 recordsLinked to original sources

arXiv2026

GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks

For robots to work reliably in commercial and industrial applications, can recent advances in agentic coding systems combine interpretable robot programming with the open-world adaptability of model-free policies? We focus on "Variational Automation" (VA), a class of tasks that have larger variations in object geometry and pose than fixed automation. Model-free policies often struggle to close the reliability gap for VA tasks, which must be executed persistently and reliably in commercial and industrial applications. Motivated by prior work on Task and Motion Planning (TAMP) and the Robot Operating System (ROS), we introduce Graph-as-Policy (GaP), a multi-agent coding harness that generates directed computation graphs with perception, planning, and control nodes from a Modular Open Robot Skill Library (MORSL). GaP then generates an internal simulation environment to rehearse task instances with different graphs in parallel to iteratively refine the graph structure and parameters to improve success rates and throughput. Evaluation with 8 new open VA task benchmarks, 4 in-simulation and 4 in real-world, suggests that GaP can achieve success rates that significantly outperform baselines. Details, code, and data can be found online: https://graph-robots.github.io/gap

cs.RO↗

arXiv2026

WARP-RM: A Warp-Augmented Relative Progress Reward Model for Data Curation

Scaling imitation learning requires large datasets, yet human teleoperation inevitably produces mixed-quality demonstrations containing hesitations, retries, and pauses. Prior frame-level progress reward models supervise on absolute temporal progress proxies that suffer from label noise, or require costly human annotations to define subtask boundaries. We present WARP (Warp-Augmented Relative Progress), a novel fully self-supervised algorithm for learning dense, signed relative progress magnitudes directly from successful demonstrations. WARP generates per-frame progress targets via time-warp augmentations of demonstrations (variable playback speeds and reversals) and we train WARP-RM to predict normalized signed temporal displacement from the start of each sampled window. Aggregating these predictions across overlapping windows yields a dense frame-level progress signal. We then introduce WARP-BC, which uses these scalar reward estimates to filter and reweight action chunks during behavior cloning. We evaluate our approach on a physical bimanual robot system performing a long-horizon deformable object manipulation task: folding T-shirts from a random crumpled start. To evaluate policy robustness against suboptimal data, we construct training datasets of varying quality using episode length as a proxy for teleoperation sub-optimality. Across these training tiers, WARP-BC improves successful-folding throughput by up to ~18x over vanilla BC. Furthermore, we evaluate bottle-in-bin placement in the real world and in simulation. Across 512 paired simulated scenes, WARP-BC achieves 290 bottles/hr versus 237 for vanilla BC and 271 for DemInf, with all curation methods retaining 31.5% of the data. We release open simulation data, code, checkpoints, and evaluation artifacts for end-to-end reproduction of the WARP pipeline. Project page: https://uynitsuj.github.io/warp-rm/

cs.RO↗

arXiv2026

Scalable Behavior Cloning with Open Data, Training, and Evaluation

We introduce ABC, a fully open-source stack for manipulation with behavior cloning. At its core is ABC-130K: the largest open-source teleoperation dataset to date, featuring 3,500 hours of data spanning over 130K episodes across 195 diverse tasks. Furthermore, we open-source our accessible hardware setup, training infrastructure, and simulation pipeline. We also release 400 hours of sim-teleop data and provide a co-training recipe that produces correlated simulation and real-world evaluation, offering a reliable proxy for ablating model-design and training decisions before costly real-world evaluation. We explore various training recipes and compare common architectural choices for Diffusion Transformers (DiT) and Vision-Language-Action (VLA) models, grounding our findings in real-world evaluations. The resulting policies successfully execute dexterous tasks such as box folding and extracting credit cards from wallets. By providing a reproducible toolkit, we aim to place researchers on an equal footing, establishing the necessary foundation to learn the ABCs of Behavior Cloning together as a community.

cs.RO↗

arXiv2026

Playful Agentic Robot Learning

Current agentic robot systems can write executable Code-as-Policy programs, observe feedback, and revise behavior across multiple attempts, but they remain largely task-driven: reusable skills are acquired only after explicit instructions. We study Playful Agentic Robot Learning, where an embodied coding agent uses self-directed play as a continual skill-learning stage before downstream tasks arrive. We introduce RATs, Robotics Agent Teams designed for play-time skill acquisition. During play, RATs proposes novel yet learnable exploratory tasks, plans and executes robot-code policies, verifies intermediate progress, diagnoses failures, retries with dense, step-level feedback, and distills successful executions into a persistent code skill library. At test time, the agent reuses relevant skills from this frozen library to help solve new tasks. Experiments in LIBERO-PRO and MolmoSpaces show that play-learned skills improve held-out downstream tasks over no-play and random-play baselines, with 20.6 and 17.0 percentage-point gains over CaP-Agent0 on LIBERO-PRO and MolmoSpaces, respectively. Moreover, the learned skills can be plugged into other inference-time Code-as-Policy agents by simply retrieving them into the context, improving RoboSuite and real-world transfer by 8.9 and 8.8 points, respectively, without finetuning the underlying model.

cs.RO↗

arXiv2026

SARM2: Multi-Task Stage Aware Reward Modeling for Self Improving Robotic Manipulation

Fine-tuning vision-language-action (VLA) policies for long-horizon manipulation still relies heavily on behavior cloning, which requires costly high-quality demonstrations and keeps policies near the demonstration distribution. Reward models can reduce this dependence by reweighting demonstrations and providing dense supervision for on-robot reinforcement learning (RL), but they must be dense, accurate, and general. Existing methods fall short: task-specific stage-aware models are accurate but require per-task annotations, while general vision-language-model (VLM) reward models are broadly applicable but too coarse for fine-grained long-horizon progress. We introduce RM, a multi-task stage-aware reward model that combines an action-primitive-based stage estimator with a multi-gate Mixture-of-Experts (MMoE) value head to produce dense per-step rewards across manipulation tasks. Building on RM, we further propose SPIRAL (Self-Policy Improvement via Reward-Aligned Learning), an on-policy reward-guided framework that improves VLA policies from cheap autonomous rollouts. On a 10-task benchmark, RM reduces value-estimation MSE by 80% over the strongest baselines; when used in SPIRAL, it improves task success from around 50% to near-perfect performance on Folding Shorts (58% to 100%) and Cleaning Whiteboard (50% to 90%), showing that high-quality dense rewards are key to a stable robot data flywheel. Project website: https://qianzhong-chen.github.io/sarm2.github.io/.

cs.RO↗

arXiv2026

CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation

"Code-as-Policy" considers how executable code can complement data-intensive Vision-Language-Action (VLA) methods, yet their effectiveness as autonomous controllers for embodied manipulation remains underexplored. We present CaP-X, an open-access framework for systematically studying Code-as-Policy agents in robot manipulation. At its core is CaP-Gym, an interactive environment in which agents control robots by synthesizing and executing programs that compose perception and control primitives. Building on this foundation, CaP-Bench evaluates frontier language and vision-language models across varying levels of abstraction, interaction, and perceptual grounding. Across 12 models, CaP-Bench reveals a consistent trend: performance improves with human-crafted abstractions but degrades as these priors are removed, exposing a dependence on designer scaffolding. At the same time, we observe that this gap can be mitigated through scaling agentic test-time computation--through multi-turn interaction, structured execution feedback, visual differencing, automatic skill synthesis, and ensembled reasoning--substantially improves robustness even when agents operate over low-level primitives. These findings allow us to derive CaP-Agent0, a training-free framework that recovers human-level reliability on several manipulation tasks in simulation and on real embodiments. We further introduce CaP-RL, showing reinforcement learning with verifiable rewards improves success rates and transfers from sim2real with minimal gap. Together, CaP-X provides a principled, open-access platform for advancing embodied coding agents.

cs.RO↗

arXiv2026

5-cycles in the complement of minimal prime graphs

Minimal prime graphs (MPGs) are a special class of prime graphs (also known as Gruenberg-Kegel graphs) associated with finite solvable groups. A graph is an MPG if it has at least two vertices, is connected, its complement is triangle-free and 3-colorable, and the addition of an edge to the complement will violate triangle-freeness or 3-colorability. In this paper, we continue the study of the complements of MPGs focusing on their cycle structure. Our main result establishes that every edge in the complement of an MPG is contained in a 5-cycle. This finding is a much stronger form of an older result stating that every minimal prime graph complement contains at least one induced 5-cycle.

math.CO↗

arXiv2025

EgoMI: Learning Active Vision and Whole-Body Manipulation from Egocentric Human Demonstrations

Imitation learning from human demonstrations offers a promising approach for robot skill acquisition, but egocentric human data introduces fundamental challenges due to the embodiment gap. During manipulation, humans actively coordinate head and hand movements, continuously reposition their viewpoint and use pre-action visual fixation search strategies to locate relevant objects. These behaviors create dynamic, task-driven head motions that static robot sensing systems cannot replicate, leading to a significant distribution shift that degrades policy performance. We present EgoMI (Egocentric Manipulation Interface), a framework that captures synchronized end-effector and active head trajectories during manipulation tasks, resulting in data that can be retargeted to compatible semi-humanoid robot embodiments. To handle rapid and wide-spanning head viewpoint changes, we introduce a memory-augmented policy that selectively incorporates historical observations. We evaluate our approach on a bimanual robot equipped with an actuated camera head and find that policies with explicit head-motion modeling consistently outperform baseline methods. Results suggest that coordinated hand-eye learning with EgoMI effectively bridges the human-robot embodiment gap for robust imitation learning on semi-humanoid embodiments. Project page: https://egocentric-manipulation-interface.github.io

cs.RO↗

arXiv2025

Inverse Behavioral Optimization of QALY-Based Incentive Systems Quantifying the System Impact of Adaptive Health Programs

This study introduces an inverse behavioral optimization framework that integrates QALY-based health outcomes, ROI-driven incentives, and adaptive behavioral learning to quantify how policy design shapes national healthcare performance. Building on the FOSSIL (Flexible Optimization via Sample-Sensitive Importance Learning) paradigm, the model embeds a regret-minimizing behavioral weighting mechanism that enables dynamic learning from heterogeneous policy environments. It recovers latent behavioral sensitivities (efficiency, fairness, and temporal responsiveness T) from observed QALY-ROI trade-offs, providing an analytical bridge between individual incentive responses and aggregate system productivity. We formalize this mapping through the proposed System Impact Index (SII), which links behavioral elasticity to measurable macro-level efficiency and equity outcomes. Using OECD-WHO panel data, the framework empirically demonstrates that modern health systems operate near an efficiency-saturated frontier, where incremental fairness adjustments yield stabilizing but diminishing returns. Simulation and sensitivity analyses further show how small changes in behavioral parameters propagate into measurable shifts in systemic resilience, equity, and ROI efficiency. The results establish a quantitative foundation for designing adaptive, data-driven health incentive programs that dynamically balance efficiency, fairness, and long-run sustainability in national healthcare systems.

q-fin.MF↗

arXiv2025

Mechanism design and equilibrium analysis of smart contract mediated resource allocation

Decentralized coordination and digital contracting are becoming critical in complex industrial ecosystems, yet existing approaches often rely on ad hoc heuristics or purely technical blockchain implementations without a rigorous economic foundation. This study develops a mechanism design framework for smart contract-based resource allocation that explicitly embeds efficiency and fairness in decentralized coordination. We establish the existence and uniqueness of contract equilibria, extending classical results in mechanism design, and introduce a decentralized price adjustment algorithm with provable convergence guarantees that can be implemented in real time. To evaluate performance, we combine extensive synthetic benchmarks with a proof-of-concept real-world dataset (MovieLens). The synthetic tests probe robustness under fee volatility, participation shocks, and dynamic demand, while the MovieLens case study illustrates how the mechanism can balance efficiency and fairness in realistic allocation environments. Results demonstrate that the proposed mechanism achieves substantial improvements in both efficiency and equity while remaining resilient to abrupt perturbations, confirming its stability beyond steady state analysis. The findings highlight broad managerial and policy relevance for supply chains, logistics, energy markets, healthcare resource allocation, and public infrastructure, where transparent and auditable coordination is increasingly critical. By combining theoretical rigor with empirical validation, the study shows how digital contracts can serve not only as technical artifacts but also as institutional instruments for transparency, accountability, and resilience in high-stakes resource allocation.

cs.GT↗

arXiv2025

SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulation

Large-scale robot learning has made progress on complex manipulation tasks, yet long horizon, contact rich problems, especially those involving deformable objects, remain challenging due to inconsistent demonstration quality. We propose a stage-aware, video-based reward modeling framework that jointly predicts task stage and fine-grained progress, using natural language subtask annotations to derive consistent labels across variable-length demonstrations. This avoids the brittleness of frame index based labeling and provides stable supervision even in tasks like T-shirt folding. Our reward model is robust to demonstration variability, generalizes to out-of-distribution scenarios, and improves downstream policy training. Building on it, we introduce Reward-Aligned Behavior Cloning (RA-BC), which filters and reweights demonstrations based on reward estimates. Experiments show that our method significantly outperforms baselines in both real-world rollouts and human validation. On T-shirt folding, we achieve 83% success from the flattened state and 67% from the crumpled state, compared to 8% and 0% with vanilla BC. Overall, our results highlight reward modeling as a scalable and annotation-efficient solution for long horizon robotic manipulation. Project website: https://qianzhong-chen.github.io/sarm.github.io/

cs.RO↗

arXiv2025

Real2Render2Real: Scaling Robot Data Without Dynamics Simulation or Robot Hardware

Scaling robot learning requires vast and diverse datasets. Yet the prevailing data collection paradigm-human teleoperation-remains costly and constrained by manual effort and physical robot access. We introduce Real2Render2Real (R2R2R), a novel approach for generating robot training data without relying on object dynamics simulation or teleoperation of robot hardware. The input is a smartphone-captured scan of one or more objects and a single video of a human demonstration. R2R2R renders thousands of high visual fidelity robot-agnostic demonstrations by reconstructing detailed 3D object geometry and appearance, and tracking 6-DoF object motion. R2R2R uses 3D Gaussian Splatting (3DGS) to enable flexible asset generation and trajectory synthesis for both rigid and articulated objects, converting these representations to meshes to maintain compatibility with scalable rendering engines like IsaacLab but with collision modeling off. Robot demonstration data generated by R2R2R integrates directly with models that operate on robot proprioceptive states and image observations, such as vision-language-action models (VLA) and imitation learning policies. Physical experiments suggest that models trained on R2R2R data from a single human demonstration can match the performance of models trained on 150 human teleoperation demonstrations. Project page: https://real2render2real.com

cs.RO↗

arXiv2025

Persistent Object Gaussian Splat (POGS) for Tracking Human and Robot Manipulation of Irregularly Shaped Objects

Tracking and manipulating irregularly-shaped, previously unseen objects in dynamic environments is important for robotic applications in manufacturing, assembly, and logistics. Recently introduced Gaussian Splats efficiently model object geometry, but lack persistent state estimation for task-oriented manipulation. We present Persistent Object Gaussian Splat (POGS), a system that embeds semantics, self-supervised visual features, and object grouping features into a compact representation that can be continuously updated to estimate the pose of scanned objects. POGS updates object states without requiring expensive rescanning or prior CAD models of objects. After an initial multi-view scene capture and training phase, POGS uses a single stereo camera to integrate depth estimates along with self-supervised vision encoder features for object pose estimation. POGS supports grasping, reorientation, and natural language-driven manipulation by refining object pose estimates, facilitating sequential object reset operations with human-induced object perturbations and tool servoing, where robots recover tool pose despite tool perturbations of up to 30{\deg}. POGS achieves up to 12 consecutive successful object resets and recovers from 80% of in-grasp tool perturbations.

cs.RO↗

arXiv2024

Language-Embedded Gaussian Splats (LEGS): Incrementally Building Room-Scale Representations with a Mobile Robot

Building semantic 3D maps is valuable for searching for objects of interest in offices, warehouses, stores, and homes. We present a mapping system that incrementally builds a Language-Embedded Gaussian Splat (LEGS): a detailed 3D scene representation that encodes both appearance and semantics in a unified representation. LEGS is trained online as a robot traverses its environment to enable localization of open-vocabulary object queries. We evaluate LEGS on 4 room-scale scenes where we query for objects in the scene to assess how LEGS can capture semantic meaning. We compare LEGS to LERF and find that while both systems have comparable object query success rates, LEGS trains over 3.5x faster than LERF. Results suggest that a multi-camera setup and incremental bundle adjustment can boost visual reconstruction quality in constrained robot trajectories, and suggest LEGS can localize open-vocabulary and long-tail object queries with up to 66% accuracy.

cs.RO↗

arXiv2023

Mitigating Outlier Activations in Low-Precision Fine-Tuning of Language Models

Low-precision fine-tuning of language models has gained prominence as a cost-effective and energy-efficient approach to deploying large-scale models in various applications. However, this approach is susceptible to the existence of outlier values in activation. The outlier values in the activation can negatively affect the performance of fine-tuning language models in the low-precision regime since they affect the scaling factor and thus make representing smaller values harder. This paper investigates techniques for mitigating outlier activation in low-precision integer fine-tuning of the language models. Our proposed novel approach enables us to represent the outlier activation values in 8-bit integers instead of floating-point (FP16) values. The benefit of using integers for outlier values is that it enables us to use operator tiling to avoid performing 16-bit integer matrix multiplication to address this problem effectively. We provide theoretical analysis and supporting experiments to demonstrate the effectiveness of our approach in improving the robustness and performance of low-precision fine-tuned language models.

cs.CL↗

arXiv2023

Effectively Rearranging Heterogeneous Objects on Cluttered Tabletops

Effectively rearranging heterogeneous objects constitutes a high-utility skill that an intelligent robot should master. Whereas significant work has been devoted to the grasp synthesis of heterogeneous objects, little attention has been given to the planning for sequentially manipulating such objects. In this work, we examine the long-horizon sequential rearrangement of heterogeneous objects in a tabletop setting, addressing not just generating feasible plans but near-optimal ones. Toward that end, and building on previous methods, including combinatorial algorithms and Monte Carlo tree search-based solutions, we develop state-of-the-art solvers for optimizing two practical objective functions considering key object properties such as size and weight. Thorough simulation studies show that our methods provide significant advantages in handling challenging heterogeneous object rearrangement problems, especially in cluttered settings. Real robot experiments further demonstrate and confirm these advantages. Source code and evaluation data associated with this research will be available at https://github.com/arc-l/TRLB upon the publication of this manuscript.

cs.RO↗

arXiv2021

MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning

Exploration in reinforcement learning is a challenging problem: in the worst case, the agent must search for high-reward states that could be hidden anywhere in the state space. Can we define a more tractable class of RL problems, where the agent is provided with examples of successful outcomes? In this problem setting, the reward function can be obtained automatically by training a classifier to categorize states as successful or not. If trained properly, such a classifier can provide a well-shaped objective landscape that both promotes progress toward good states and provides a calibrated exploration bonus. In this work, we show that an uncertainty aware classifier can solve challenging reinforcement learning problems by both encouraging exploration and provided directed guidance towards positive outcomes. We propose a novel mechanism for obtaining these calibrated, uncertainty-aware classifiers based on an amortized technique for computing the normalized maximum likelihood (NML) distribution. To make this tractable, we propose a novel method for computing the NML distribution by using meta-learning. We show that the resulting algorithm has a number of intriguing connections to both count-based exploration methods and prior algorithms for learning reward functions, while also providing more effective guidance towards the goal. We demonstrate that our algorithm solves a number of challenging navigation and robotic manipulation tasks which prove difficult or impossible for prior methods.

cs.LG↗

arXiv2021

Legged Robot State Estimation using Invariant Kalman Filtering and Learned Contact Events

This work develops a learning-based contact estimator for legged robots that bypasses the need for physical sensors and takes multi-modal proprioceptive sensory data as input. Unlike vision-based state estimators, proprioceptive state estimators are agnostic to perceptually degraded situations such as dark or foggy scenes. While some robots are equipped with dedicated physical sensors to detect necessary contact data for state estimation, some robots do not have dedicated contact sensors, and the addition of such sensors is non-trivial without redesigning the hardware. The trained network can estimate contact events on different terrains. The experiments show that a contact-aided invariant extended Kalman filter can generate accurate odometry trajectories compared to a state-of-the-art visual SLAM system, enabling robust proprioceptive odometry.

cs.RO↗