arXiv subjects

Yixuan Jia

Publications and source records attributed to Yixuan Jia.

At least 19 recordsLinked to original sources

arXiv2026

Feedback-Modulated Harmonic Policies for Quadruped Locomotion

Learned quadruped locomotion policies commonly map observations directly to joint-level actions, leaving the periodic structure of locomotion implicit in the policy. We investigate an alternative representation in which each joint trajectory is expressed as a command-conditioned Fourier series and modified online using feedback from the robot state. A context network generates the Fourier coefficients and the weights of a per-step feedback network, whose outputs adjust joint offsets, harmonic gains, frequency, and phase during execution. In simulation, we examine this explicit frequency structure alongside the hidden activations of an MLP policy that directly outputs joint targets. The harmonic waveforms change frequency and shape with commanded speed. Dynamic mode decomposition of selected MLP rollouts reveals dominant activation modes near the foot-height oscillation frequency and its second harmonic, showing periodic structure without an explicit Fourier generator. On a Unitree Go2, the simulation-trained harmonic controller records a provisional onboard-estimated peak speed of 3.67 meter per second and carries added loads up to 5.883 kilogram in separate trials.

cs.RO↗

arXiv2026

Steering Generative Robot Policies with Lexicographic Preferences

Pretrained generative robot policies can produce effective behaviors across diverse environments, but deployment can lead to requirements and preferences that may not have been represented during training. Furthermore, at deployment, an operator, user, or application may assign these requirements and preferences a priority order that can vary across deployments. For example, embodiment-specific feasibility constraints may need to be satisfied first, while user-specific preferences guide behavior among the feasible options. We show that a frozen generative robot policy---based on either diffusion or flow matching---can be steered at inference time to respect such lexicographically ordered deployment objectives. To achieve this, we introduce two modifications to the sampler. First, we apply dynamic-barrier guidance to sampled trajectories, constraining lower-priority updates so that higher-priority costs do not increase (up to first order). Second, we select the executed sample using a cascade that successively filters candidate samples according to each priority level. The policy weights remain unchanged. On a navigation benchmark, we demonstrate that our method improves success, traversability, and preference compliance over the frozen policy, and achieves substantially better compliance than tuned weighted-sum baselines. The same method transfers to a flow-matching manipulation policy on LIBERO, where it improves compliance without reducing task success. A controlled manipulation study further shows that, in settings where a fixed weight can match the desired ordering, the dynamic barrier reaches comparable best performance over a substantially wider range of parameter settings.

cs.RO↗

arXiv2026

Learning-Based Measurement-Robust Control Barrier Functions for Obstacle Avoidance under State Estimation Error

Safety filters are an effective tool for enforcing constraints in safety-critical systems, but most existing methods assume perfect state information, which is rarely available in practice. Recent work has begun to close this gap by developing filtering mechanisms that are robust to state estimation error, but these methods can still exhibit safety violations or overly conservative behavior as estimation error grows. Focusing on obstacle avoidance, we develop two new control barrier function (CBF) formulations: drift-measurement-robust (DMR)-CBFs and neural measurement-robust (NMR)-CBFs. The DMR-CBF augments the standard CBF condition with an inner optimization over the worst-case uncertainty in the drift dynamics, improving robustness to estimation error. This DMR-CBF then supervises a pretraining phase for the NMR-CBF, which replaces the inner optimization with a learned term. The NMR-CBF is subsequently finetuned through differentiable trajectory rollouts, yielding a filter that achieves empirical safety comparable to the DMR-CBF while reducing both conservativeness and computational cost. We provide theoretical analysis of the DMR-CBF along with numerical results on a planar double integrator and a 12D quadrotor, where both proposed approaches prevent collisions while other robust methods either fail or are overly conservative. Finally, we deployed the NMR-CBF on a Unitree Go2, enabling successful navigation of an obstacle field under odometry errors that caused a standard CBF to collide.

eess.SY↗

arXiv2026

Imaging-101: Benchmarking LLM Coding Agents on Scientific Computational Imaging

Computational imaging, which recovers hidden signals from indirect, noisy measurements, underpins quantitative discovery across scientific disciplines, yet building a correct reconstruction pipeline demands deep domain expertise and remains laborious even for domain scientists. We introduce Imaging-101, a benchmark of 57 expert-verified computational imaging tasks spanning six scientific domains, each grounded in a peer-reviewed paper and canonicalized into a standardized four-stage pipeline (preprocessing, forward physics modeling, inverse solver, and visualization) Three evaluation tracks (planning, function-level unit tests, and end-to-end reconstruction) probe distinct agent capabilities across the full pipeline. Evaluating seven frontier LLMs uncovers systematic challenges in applying coding agents to computational imaging that go beyond those exposed by general coding benchmarks, spanning algorithm selection, physical convention handling, and pipeline integration. These findings highlight concrete capability gaps and point toward skill-augmented, domain-specialized agents as a practical path to reliable computational imaging assistance.

cs.AI↗

arXiv2026

CILC: Cryptographically-secure Inter-agent Loop Closure Candidate Detection for Multi-Agent Collaborative SLAM

Multi-agent Simultaneous Localization and Mapping (SLAM) and collaborative SLAM (CSLAM) require robots to continuously exchange global descriptors (GDs) to detect inter-agent loop closures (ILCs). While encrypted radios protect this traffic from external eavesdroppers, they offer no protection against a compromised swarm member. We show this threat is concrete by demonstrating how a corrupted agent can reconstruct approximations of an honest agent's imagery and trajectory from its public GD broadcasts. To address this, we propose CILC (Cryptographically-secure Inter-agent Loop Closure candidate detection), a first-of-its-kind system leveraging Secure Multi-Party Computation (SMPC) to detect ILC candidates without exchanging GDs in the clear. Rather than securing the entire CSLAM pipeline, we apply SMPC only to ILC candidate detection (i.e., GD similarity comparison), a privacy-sensitive yet computationally lightweight step, yielding an advantageous privacy-to-overhead trade-off. We validate in both simulation and hardware experiments that CILC remains real-time and communication-feasible across multimodal GDs (visual and LiDAR), while mitigating information leakage to a compromised swarm agent.

cs.RO↗

arXiv2026

Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video Generation

Recent progress has shown promise in distilling multi-step video diffusion models into efficient few-step students. Among them, Distribution Matching Distillation (DMD) and its successor DMD2 achieved strong generation quality and fast convergence. However, due to the nature of the reverse Kullback--Leibler (KL) objective, these methods exhibit two persistent failure modes: a substantial drop in sample diversity, and visibly over-saturated outputs that deviate from real-video appearance. In this work, we propose Data-Forcing Distillation (DFD), a simple post-training framework that restores diversity and fidelity in DMD with only a single-line of code change. At its core is the teacher score discrepancy to guide the student toward the real-data distribution, pulling it to missing modes (mitigating mode collapse) and away from problematic modes absent in real data (avoiding over-saturation). We provide an in-depth theoretical analysis of our framework and validate our approach on text-to-video, image-to-video, and autoregressive video generation. With only 100--300 steps of finetuning, DFD effectively restores diversity and fidelity on both Wan2.1-1.3B and Cosmos-Predict2.5-2B model, resolving the over-saturation artifacts with significantly better video dynamics and appearance, and even outperforms the teacher model.

cs.CV↗

arXiv2026

Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles

Diffusion models have demonstrated remarkable generative capabilities and have also emerged as powerful self-supervised representation learners, yet the connection between these two abilities remains less explored. Drawing inspiration from self-supervised learning (SSL), we introduce a framework for jointly evaluating the representation and generation capabilities of diffusion models. Specifically, we decompose features into invariant and residual components and derive the Invariant Contamination Ratio (ICR), a Fisher-based metric that quantifies how residual variation contaminates invariant signal in feature space. We use this framework to analyze both discriminative and generative behavior of diffusion models. On the representation side, we find that invariance peaks at intermediate noise levels, which also yield the best downstream classification performance. On the generative side, we study how training transitions from genuine generalization to memorization in data-limited regimes, and show that ICR serves as a sensitive training-time indicator of early learning: increasing residual energy along Fisher directions marks the onset of memorization, detectable from training features alone without external evaluators or held-out test sets. Overall, our results show that diffusion models can be monitored from a self-supervised perspective through the geometry of their learned representations.

cs.LG↗

arXiv2026

ForcingDAS: Unified and Robust Data Assimilation via Diffusion Forcing

Data assimilation (DA) estimates the state of an evolving dynamical system from noisy, partial observations, and is widely used in scientific simulation as well as weather and climate science. In practice, filtering methods rely on frame-to-frame transition models. However, these models are fragile when observations are non-Markovian (when they form only a partial slice of a higher-dimensional latent state as in real-world weather data): they tend to accumulate errors over long horizons. At the same time, learned DA methods typically commit to a single regime, either filtering (nowcasting, real-time forecasting) or smoothing (retrospective reanalysis), which splits what should be a shared prior across application-specific pipelines. To address both issues, we introduce ForcingDAS, a unified and robust DA framework. Built on Diffusion Forcing with an independent noise level assigned to each frame, ForcingDAS learns a joint-trajectory prior instead of frame-to-frame transitions. This allows it to capture long-horizon temporal dependencies and reduce error accumulation. In addition, the same trained model spans the full filtering to smoothing spectrum at inference time. Specifically, nowcasting, fixed-lag smoothing, and batch reanalysis are selected through the inference schedule alone, without retraining. We evaluate ForcingDAS on 2D Navier-Stokes vorticity, precipitation nowcasting, and global atmospheric state estimation. Across all settings, a single model is competitive with or outperforms both learned and classical baselines that are specialized for individual regimes, with the largest gains observed on real-world weather benchmarks.

eess.IV↗

arXiv2026

Meridian: Metric-Semantic Primitive Matching for Cross-View Geo-Localization Beyond Urban Environments

Successful robot automation requires accurate global localization to support repeatability, task planning, goal specification, and safe operation. However, reliable localization in GNSS-denied environments remains an open problem. Overhead aerial imagery offers a promising solution, but existing approaches primarily target structured urban environments and have been rarely demonstrated in unstructured natural terrain. Limitations of the state-of-the-art include a reliance on models trained for specific environments, as well as difficulty handling repetitive geometries and featureless landscapes commonly found in natural outdoor areas. To overcome these challenges, we present Meridian, a method for matching high-level metric-semantic primitives across aerial images and ground robot RGB-D camera data that achieves accurate global localization and generalizes well across diverse environments, all without any training or algorithmic fine-tuning on area-specific data. We formulate novel consistency metrics to estimate a distribution over robot submap poses and to reject outlier hypotheses in a robust pose graph optimization step for accurate robot trajectory estimation. We demonstrate that our algorithm can localize a ground robot across a wide variety of environments, including an autonomous driving dataset, a park and campus area, and a wilderness camp, with an average optimized trajectory error of 2.4 m over 19 km of ground traversal.

cs.RO↗

arXiv2026

MCLR: Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives

Diffusion models achieve strong performance in generative modeling, but their success often relies heavily on classifier-free guidance (CFG), an inference-time heuristic that modifies the sampling trajectory. In theory, diffusion models trained with standard denoising score matching (DSM) should recover the target data distribution, raising two fundamental questions: (i) why is inference-time guidance necessary in practice, and (ii) can its underlying effect be internalized into a principled training objective? In this work, we argue that a key limitation of standard DSM is insufficient inter-class separation. To address this issue, we propose MCLR, an alignment objective that explicitly maximizes inter-class likelihood-ratios during training. Fine-tuning diffusion models with MCLR induces CFG-like improvements under standard sampling, substantially improving guidance-free conditional generation and narrowing the gap to inference-time CFG. Beyond these empirical benefits, we show theoretically that the CFG-guided score is exactly the optimal solution to a sample-adaptive weighted MCLR objective. This result connects CFG to alignment-based objectives, providing a mechanistic interpretation of CFG as an implicit inference-time contrastive alignment procedure.

cs.LG↗

arXiv2026

Robust Dynamic Object Detection in Cluttered Indoor Scenes via Learned Spatiotemporal Cues

Reliable dynamic object detection in cluttered environments remains a critical challenge for autonomous navigation. Purely geometric LiDAR pipelines that rely on clustering and heuristic filtering can miss dynamic obstacles when they move in close proximity to static structure or are only partially observed. Vision-augmented approaches can provide additional semantic cues, but are often limited by closed-set detectors and camera field-of-view constraints, reducing robustness to novel obstacles and out-of-frustum events. In this work, we present a LiDAR-only framework that fuses temporal occupancy-grid-based motion segmentation with a learned bird's-eye-view (BEV) dynamic prior. A fusion module prioritizes 3D detections when available, while using the learned dynamic grid to recover detections that would otherwise be lost due to proximity-induced false negatives. Experiments with motion-capture ground truth show our method achieves 28.67% higher recall and 18.50% higher F1 score than the state-of-the-art in substantially cluttered environments while maintaining comparable precision and position error.

cs.RO↗

arXiv2026

Off-Road Navigation via Implicit Neural Representation of Terrain Traversability

Autonomous off-road navigation requires robots to estimate terrain traversability from onboard sensors and plan motion accordingly. Conventional approaches typically rely on sampling-based planners such as MPPI to generate short-term control actions that aim to minimize traversal time and risk measures derived from the traversability estimates. These planners can react quickly but optimize only over a short look-ahead window, limiting their ability to reason about the full path geometry, which is important for navigating in challenging off-road environments. Moreover, they lack the ability to adjust speed based on the terrain-induced vibrations, which is important for smooth navigation on challenging terrains. In this paper, we introduce TRAIL (Traversability with an Implicit Learned Representation), an off-road navigation framework that leverages an implicit neural representation to model terrain properties as a continuous field that can be queried at arbitrary locations. This representation yields spatial gradients that enable integration with a novel gradient-based trajectory optimization method that adapts the path geometry and speed profile based on terrain traversability.

cs.RO↗

arXiv2025

Distribution Estimation for Global Data Association via Approximate Bayesian Inference

Global data association is an essential prerequisite for robot operation in environments seen at different times or by different robots. Repetitive or symmetric data creates significant challenges for existing methods, which typically rely on maximum likelihood estimation or maximum consensus to produce a single set of associations. However, in ambiguous scenarios, the distribution of solutions to global data association problems is often highly multimodal, and such single-solution approaches frequently fail. In this work, we introduce a data association framework that leverages approximate Bayesian inference to capture multiple solution modes to the data association problem, thereby avoiding premature commitment to a single solution under ambiguity. Our approach represents hypothetical solutions as particles that evolve according to a deterministic or randomized update rule to cover the modes of the underlying solution distribution. Furthermore, we show that our method can incorporate optimization constraints imposed by the data association formulation and directly benefit from GPU-parallelized optimization. Extensive simulated and real-world experiments with highly ambiguous data show that our method correctly estimates the distribution over transformations when registering point clouds or object maps.

cs.RO↗

arXiv2025

Terrain-aware Low Altitude Path Planning

In this paper, we study the problem of generating low-altitude path plans for nap-of-the-earth (NOE) flight in real time with only RGB images from onboard cameras and the vehicle pose. We propose a novel training method that combines behavior cloning and self-supervised learning, where the self-supervision component allows the learned policy to refine the paths generated by the expert planner. Simulation studies show 24.7% reduction in average path elevation compared to the standard behavior cloning approach.

cs.RO↗

arXiv2025

FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation

Data assimilation (DA) integrates observations with a dynamical model to estimate states of PDE-governed systems. Model-driven methods (e.g., Kalman, particle) presuppose full knowledge of the true dynamics, which is not always satisfied in practice, while purely data-driven solvers learn a deterministic mapping between observations and states and therefore miss the intrinsic stochasticity of real processes. Recently, score-based diffusion models learn a global diffusion prior and provide a good modeling of the stochastic dynamics, showing new potential for DA. However, their all-at-once generation rather than step-by-step transition limits their performance when dealing with highly complex stochastic processes and lacks physical interpretability. To tackle these drawbacks, we introduce FlowDAS, a generative DA framework that uses stochastic interpolants to directly learn state transition dynamics and achieve step-by-step transition to better model the real dynamics. We also improve the framework by combining the observation, better suiting the DA settings. Directly learning the underlying dynamics from collected data removes restrictive dynamical assumptions, and conditioning on observations at each interpolation step yields stable, measurement-consistent forecasts. Experiments on Lorenz-63, Navier-Stokes super-resolution/sparse-observation scenarios, and large-scale weather forecasting -- where dynamics are partly or wholly unknown -- show that FlowDAS surpasses model-driven methods, neural operators, and score-based baselines in accuracy and physical plausibility.

eess.SP↗

arXiv2025

ROMAN: Open-Set Object Map Alignment for Robust View-Invariant Global Localization

Global localization is a fundamental capability required for long-term and drift-free robot navigation. However, current methods fail to relocalize when faced with significantly different viewpoints. We present ROMAN (Robust Object Map Alignment Anywhere), a global localization method capable of localizing in challenging and diverse environments by creating and aligning maps of open-set and view-invariant objects. ROMAN formulates and solves a registration problem between object submaps using a unified graph-theoretic global data association approach with a novel incorporation of a gravity direction prior and object shape and semantic similarity. This work's open-set object mapping and information-rich object association algorithm enables global localization, even in instances when maps are created from robots traveling in opposite directions. Through a set of challenging global localization experiments in indoor, urban, and unstructured/forested environments, we demonstrate that ROMAN achieves higher relative pose estimation accuracy than other image-based pose estimation methods or segment-based registration methods. Additionally, we evaluate ROMAN as a loop closure module in large-scale multi-robot SLAM and show a 35% improvement in trajectory estimation error compared to standard SLAM systems using visual features for loop closures. Code and videos can be found at https://acl.mit.edu/roman.

cs.RO↗

arXiv2025

Strategic Decision-Making in Multi-Agent Domains: A Weighted Constrained Potential Dynamic Game Approach

In interactive multi-agent settings, decision-making and planning are challenging mainly due to the agents' interconnected objectives. Dynamic game theory offers a formal framework for analyzing such intricacies. Yet, solving constrained dynamic games and determining the interaction outcome in the form of generalized Nash Equilibria (GNE) pose computational challenges due to the need for solving constrained coupled optimal control problems. In this paper, we address this challenge by proposing to leverage the special structure of many real-world multi-agent interactions. More specifically, our key idea is to leverage constrained dynamic potential games, which are games for which GNE can be found by solving a single constrained optimal control problem associated with minimizing the potential function. We argue that constrained dynamic potential games can effectively facilitate interactive decision-making in many multi-agent interactions. We will identify structures in realistic multi-agent interactive scenarios that can be transformed into weighted constrained potential dynamic games (WCPDGs). We will show that the GNE of the resulting WCPDG can be obtained by solving a single constrained optimal control problem. We will demonstrate the effectiveness of the proposed method through various simulation studies and show that we achieve significant improvements in solve time compared to state-of-the-art game solvers. We further provide experimental validation of our proposed method in a navigation setup involving two quadrotors carrying a rigid object while avoiding collisions with two humans.

cs.RO↗

arXiv2024

Shorter SPECT Scans Using Self-supervised Coordinate Learning to Synthesize Skipped Projection Views

Purpose: This study addresses the challenge of extended SPECT imaging duration under low-count conditions, as encountered in Lu-177 SPECT imaging, by developing a self-supervised learning approach to synthesize skipped SPECT projection views, thus shortening scan times in clinical settings. Methods: We employed a self-supervised coordinate-based learning technique, adapting the neural radiance field (NeRF) concept in computer vision to synthesize under-sampled SPECT projection views. For each single scan, we used self-supervised coordinate learning to estimate skipped SPECT projection views. The method was tested with various down-sampling factors (DFs=2, 4, 8) on both Lu-177 phantom SPECT/CT measurements and clinical SPECT/CT datasets, from 11 patients undergoing Lu-177 DOTATATE and 6 patients undergoing Lu-177 PSMA-617 radiopharmaceutical therapy. Results: For SPECT reconstructions, our method outperformed the use of linearly interpolated projections and partial projection views in relative contrast-to-noise-ratios (RCNR) averaged across different downsampling factors: 1) DOTATATE: 83% vs. 65% vs. 67% for lesions and 86% vs. 70% vs. 67% for kidney, 2) PSMA: 76% vs. 69% vs. 68% for lesions and 75% vs. 55% vs. 66% for organs, including kidneys, lacrimal glands, parotid glands, and submandibular glands. Conclusion: The proposed method enables reduction in acquisition time (by factors of 2, 4, or 8) while maintaining quantitative accuracy in clinical SPECT protocols by allowing for the collection of fewer projections. Importantly, the self-supervised nature of this NeRF-based approach eliminates the need for extensive training data, instead learning from each patient's projection data alone. The reduction in acquisition time is particularly relevant for imaging under low-count conditions and for protocols that require multiple-bed positions such as whole-body imaging.

eess.IV↗