arXiv subjects

Yibo Yuan

Publications and source records attributed to Yibo Yuan.

7 recordsLinked to original sources

arXiv2026

4D-WAM: 4D Consistent World Modeling for Autonomous Driving

Emerging World-Action Models (WAMs) have demonstrated promising performance in autonomous driving by jointly modeling future driving scene evolution and trajectory planning. However, existing WAMs are typically trained with video data, which is only 2D projections of the underlying 4D driving scene. Consequently, WAMs fail to understand and capture the structure of 4D scenes and thus generate visually plausible yet 4D inconsistent future predictions that mislead downstream planning. To alleviate this issue, we present 4D-WAM, a model that leverages geometric foundation models for training-time supervision to enable 4D consistent world modeling. Specifically, we feed WAM-predicted future frames into a geometric foundation model, and use 4D-aware responses to define a 4D consistency loss. This loss encourages the model to understand, represent, and predict physically consistent 4D scenes during training, without additional inference cost. Moreover, we identify an early-decision phenomenon in WAMs and propose a decision-oriented timestep sampling strategy that emphasizes supervision at early, high-noise stages, where driving decisions are primarily formed. By propagating 4D supervision to this critical decision-formation phase, the proposed strategy further improves trajectory planning. Extensive experiments demonstrate that 4D-WAM effectively models 4D consistent scene evolution and achieves state-of-the-art performance on challenging NAVSIM-v1 and NAVSIM-v2 benchmarks.

cs.CV↗

arXiv2026

SUV: Future Scene Understanding as Video Generation for End-to-End Driving

End-to-end driving requires a coherent understanding of future scenes, yet existing methods model these scenes using task-specific heads and output formats, with limited scalability. Can video generation instead provide a shared predictor? We introduce SUV, a unified end-to-end driving framework that casts future Scene Understanding as Video generation using a pretrained video foundation model. SUV models future appearance, semantics, relative depth, and instance-level dynamics as video streams with a shared video expert, without stream-specific visual prediction heads. Through joint video-action attention, the action expert attends to the latent representations of all future streams and generates the ego trajectory. Experiments show that SUV directly predicts all four future streams, while controlled ablations show that structured future supervision and direct future-stream access yield higher trajectory planning scores. With only a single front camera and no candidate-trajectory selection, SUV outperforms a broad set of recent state-of-the-art methods on both NAVSIM-v2 splits, achieving 91.0 EPDMS on navtest and 36.9 on navhard. On the long-tail WOD-E2E benchmark, SUV achieves a competitive RFS of 7.94.

cs.CV↗

arXiv2026

$χ_{0}$: Resource-Aware Robust Manipulation via Taming Distributional Inconsistencies

High-reliability long-horizon robotic manipulation has traditionally relied on large-scale data and compute to understand complex real-world dynamics. However, we identify that the primary bottleneck to real-world robustness is not resource scale alone, but the distributional shift among the human demonstration distribution, the inductive bias learned by the policy, and the test-time execution distribution -- a systematic inconsistency that causes compounding errors in multi-stage tasks. To mitigate these inconsistencies, we propose $χ_{0}$, a resource-efficient framework with effective modules designated to achieve production-level robustness in robotic manipulation. Our approach builds off three technical pillars: (i) Model Arithmetic, a weight-space merging strategy that efficiently soaks up diverse distributions of different demonstrations, varying from object appearance to state variations; (ii) Stage Advantage, a stage-aware advantage estimator that provides stable, dense progress signals, overcoming the numerical instability of prior non-stage approaches; and (iii) Train-Deploy Alignment, which bridges the distribution gap via spatio-temporal augmentation, heuristic DAgger corrections, and temporal chunk-wise smoothing. $χ_{0}$ enables two sets of dual-arm robots to collaboratively orchestrate long-horizon garment manipulation, spanning tasks from flattening, folding, to hanging different clothes. Our method exhibits high-reliability autonomy; we are able to run the system from arbitrary initial state for consecutive 24 hours non-stop. Experiments validate that $χ_{0}$ surpasses the state-of-the-art $π_{0.5}$ in success rate by nearly 250%, with only 20-hour data and 8 A100 GPUs. Code, data and models will be released to facilitate the community.

cs.RO↗

arXiv2024

Programmable simulation of high-order exceptional point with a trapped ion

The nontrivial degeneracies in non-Hermitian systems, exceptional points (EPs), have attracted extensive attention due to intriguing phenomena. Compared with commonly observed second-order EPs, high-order EPs show rich physics due to their extended dimension and parameter space, ranging from the coalescence of EPs into higher order to potential applications in topological properties. However, these features also pose challenges in controlling multiple coherent and dissipative elements in a scaled system. Here we experimentally demonstrate a native programmable control to simulate a high-order non-Hermitian Hamiltonian in a multi-dimensional trapped ion system. We simulate a series of non-Hermitian systems with varied parameters and observe the coalescence of second-order EPs into a fourth-order EP. Our results pave the way for scalable quantum simulation of high-dimensional dissipative systems and can be beneficial for the application of high-order EPs in quantum sensing and quantum control.

quant-ph↗

arXiv2024

Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video

Temporal Sentence Grounding in Video (TSGV) is troubled by dataset bias issue, which is caused by the uneven temporal distribution of the target moments for samples with similar semantic components in input videos or query texts. Existing methods resort to utilizing prior knowledge about bias to artificially break this uneven distribution, which only removes a limited amount of significant language biases. In this work, we propose the bias-conflict sample synthesis and adversarial removal debias strategy (BSSARD), which dynamically generates bias-conflict samples by explicitly leveraging potentially spurious correlations between single-modality features and the temporal position of the target moments. Through adversarial training, its bias generators continuously introduce biases and generate bias-conflict samples to deceive its grounding model. Meanwhile, the grounding model continuously eliminates the introduced biases, which requires it to model multi-modality alignment information. BSSARD will cover most kinds of coupling relationships and disrupt language and visual biases simultaneously. Extensive experiments on Charades-CD and ActivityNet-CD demonstrate the promising debiasing capability of BSSARD. Source codes are available at https://github.com/qzhb/BSSARD.

cs.CV↗

arXiv2017

A Robust Fiber-based Frequency Synchronization System Immune to Dramatic Temperature Fluctuation

Fiber-based frequency synchronization system is sensitive to temperature change because of the limited isolation and nonlinear effect of RF components in the system. In order to make it suitable for the use of large-scale scientific and engineering projects in which the ambient temperature of the fiber link changes dramatically, we designed a non-harmonic frequency dissemination system immune to temperature fluctuation. After the lab tests in which the ambient temperature of fiber fluctuates 40 degrees centigrade per day and 20 degrees centigrade per hour respectively, the relative frequency stabilities of this system reached 4.0 E-14/s and 3.0 E-16/1E4 s. It is demonstrated that the proposed non-harmonic scheme shows a strong robustness to the complicated working environment with dramatic temperature fluctuation.

physics.ins-det↗

arXiv2015

Portable Microwave Frequency Dissemination in Free Space and Implications on Ground-Satellite Synchronization

Frequency dissemination and synchronization in free space plays an important role in global navigation satellite system, radio astronomy and synthetic aperture radar. In this paper, we demonstrate a portable radio frequency dissemination scheme via free space using microwave antennas. The setup has a good environment adaptability and high dissemination stability. The frequency signal is disseminated at different distances ranging from 10 to 640 m with a fixed 10 Hz locking bandwidth, and the scaling law of dissemination stability on distance and averaging time is discussed. The preliminary extrapolation shows that the dissemination stability may reach $1\times10^{-12}/s$ in ground-to-satellite synchronization, which far exceeds all present methods, and is worthy for further study.

physics.ins-det↗