arXiv subjects

Zhanqi Zhang

Publications and source records attributed to Zhanqi Zhang.

9 recordsLinked to original sources

arXiv2026

Dexterity-BEV: Aligning 3D World and Actions for Generalizable Robot Policies Learning

End-to-end manipulation policies, combined with web-scale pretrained Vision-Language Models (VLMs), show the promise for generalizable and dexterous robotic manipulation. However, they inherit two key limitations from 2D foundation models: 1) the reliance on 2D RGB inputs that ignores the intrinsically 3D nature of manipulation; and 2) the lack of spatial 3D alignment between input-output spaces as well as across diverse robot embodiments, camera setups, and trajectory datasets. In this paper, we present a series of contributions to address these issues. First, we introduce aligned vertex map and vertex spectrum -- a pixel-wise 3D representation that elevates 2D visual inputs to 3D, using camera calibration and optional depth. This novel input representation marries 3D awareness with the generalization of 2D large VLMs. Then, we propose to align the inputs and outputs of manipulation policies by expressing per-pixel 3D information of each camera view and robot actions to a shared coordinate. Based on this, we designate a canonical Bird's-Eye-View (BEV) alignment frame and innovatively propose to construct BEV images, producing a view-invariant representation robust to camera pose variations. To enable training and evaluation at scale, we develop a comprehensive data processing pipeline to perform such alignments; we also introduce a novel temporal alignment scheme for trajectories across diverse robots, human operators, and datasets. These contributions collectively mitigate input and output spatial-temporal misalignments, improving the consistency and generalization for real-world manipulation. Pretrained checkpoint, source code and data processing pipeline are available in https://hnuzhy.github.io/projects/Dex-BEV.

cs.RO↗

arXiv2026

The Position Curse: LLMs Struggle to Locate the Last Few Items in a List

Modern large language models (LLMs) can find a needle in a haystack (locating a single relevant fact buried among hundreds of thousands of irrelevant tokens) with near-saturated accuracy, yet fail to retrieve the last few items in a short list. We call this failure the Position Curse. For instance, even in a two-line code snippet, Claude Opus 4.6 misidentifies the second-to-last line most of the time. To characterize this failure, we evaluated two complementary queries: given a position in a sequence (of letters or words), retrieve the corresponding item; and given an item, return its position. Each position is specified as a forward or backward offset from an anchor, either an endpoint of the list (its start or end) or another item in the list. Across both open-source and frontier closed-source models, backward retrieval substantially lags forward retrieval. To test whether this capability can be rescued by post-training, we constructed PosBench, a position-focused training dataset. LoRA fine-tuning improves both forward and backward retrieval and generalizes to a held-out code-understanding benchmark (PyIndex), yet absolute performance remains far from saturated. As LLM coding agents increasingly operate over large codebases where precise indexing becomes essential for code understanding and editing, position-based retrieval emerges as a key capability for future pretraining objectives and model design.

cs.LG↗

arXiv2026

ALIGN: Adversarial Learning for Generalizable Speech Neuroprosthesis

Intracortical brain-computer interfaces (BCIs) can decode speech from neural activity with high accuracy when trained on data pooled across recording sessions. In realistic deployment, however, models must generalize to new sessions without labeled data, and performance often degrades due to cross-session nonstationarities (e.g., electrode shifts, neural turnover, and changes in user strategy). In this paper, we propose ALIGN, a session-invariant learning framework based on multi-domain adversarial neural networks for semi-supervised cross-session adaptation. ALIGN trains a feature encoder jointly with a phoneme classifier and a domain classifier operating on the latent representation. Through adversarial optimization, the encoder is encouraged to preserve task-relevant information while suppressing session-specific cues. We evaluate ALIGN on intracortical speech decoding and find that it generalizes consistently better to previously unseen sessions, improving both phoneme error rate and word error rate relative to baselines. These results indicate that adversarial domain alignment is an effective approach for mitigating session-level distribution shift and enabling robust longitudinal BCI decoding.

cs.LG↗

arXiv2025

See Once, Then Act: Vision-Language-Action Model with Task Learning from One-Shot Video Demonstrations

Developing robust and general-purpose manipulation policies represents a fundamental objective in robotics research. While Vision-Language-Action (VLA) models have demonstrated promising capabilities for end-to-end robot control, existing approaches still exhibit limited generalization to tasks beyond their training distributions. In contrast, humans possess remarkable proficiency in acquiring novel skills by simply observing others performing them once. Inspired by this capability, we propose ViVLA, a generalist robotic manipulation policy that achieves efficient task learning from a single expert demonstration video at test time. Our approach jointly processes an expert demonstration video alongside the robot's visual observations to predict both the demonstrated action sequences and subsequent robot actions, effectively distilling fine-grained manipulation knowledge from expert behavior and transferring it seamlessly to the agent. To enhance the performance of ViVLA, we develop a scalable expert-agent pair data generation pipeline capable of synthesizing paired trajectories from easily accessible human videos, further augmented by curated pairs from publicly available datasets. This pipeline produces a total of 892,911 expert-agent samples for training ViVLA. Experimental results demonstrate that our ViVLA is able to acquire novel manipulation skills from only a single expert demonstration video at test time. Our approach achieves over 30% improvement on unseen LIBERO tasks and maintains above 35% gains with cross-embodiment videos. Real-world experiments demonstrate effective learning from human videos, yielding more than 38% improvement on unseen tasks.

cs.RO↗

arXiv2025

PIE: Perception and Interaction Enhanced End-to-End Motion Planning for Autonomous Driving

End-to-end motion planning is promising for simplifying complex autonomous driving pipelines. However, challenges such as scene understanding and effective prediction for decision-making continue to present substantial obstacles to its large-scale deployment. In this paper, we present PIE, a pioneering framework that integrates advanced perception, reasoning, and intention modeling to dynamically capture interactions between the ego vehicle and surrounding agents. It incorporates a bidirectional Mamba fusion that addresses data compression losses in multimodal fusion of camera and LiDAR inputs, alongside a novel reasoning-enhanced decoder integrating Mamba and Mixture-of-Experts to facilitate scene-compliant anchor selection and optimize adaptive trajectory inference. PIE adopts an action-motion interaction module to effectively utilize state predictions of surrounding agents to refine ego planning. The proposed framework is thoroughly validated on the NAVSIM benchmark. PIE, without using any ensemble and data augmentation techniques, achieves an 88.9 PDM score and 85.6 EPDM score, surpassing the performance of prior state-of-the-art methods. Comprehensive quantitative and qualitative analyses demonstrate that PIE is capable of reliably generating feasible and high-quality ego trajectories.

cs.RO↗

arXiv2025

On the Metric Dimension of Generalized Petersen Graphs $P(n,3)$

The metric dimension of a graph $G$ is defined as the minimum number of vertices in a subset $S\subset V(G)$ such that all other vertices are uniquely determined by their distances to the vertices in $S$, and is denoted by $\dim(G)$. In this paper, we study the metric dimension of generalized Petersen graphs $P(n,3)$. The notions of good and bad vertices, which are introduced in Imran et al. (2014, Ars. Combinatoria 117, 113-130), are instrumental in determining the lower bound of the metric dimension for certain types of graphs. We propose an approach, based on these notions, to determine the lower bound of $\dim(P(n,3))$. Moreover, we shall prove that $\dim(P(n,3))=4$, where $n\equiv2,3,4,5 \,\,(\text{mod}\,\, 6)$ and is sufficiently large.

math.CO↗

arXiv2024

DRAMA: An Efficient End-to-end Motion Planner for Autonomous Driving with Mamba

Motion planning is a challenging task to generate safe and feasible trajectories in highly dynamic and complex environments, forming a core capability for autonomous vehicles. In this paper, we propose DRAMA, the first Mamba-based end-to-end motion planner for autonomous vehicles. DRAMA fuses camera, LiDAR Bird's Eye View images in the feature space, as well as ego status information, to generate a series of future ego trajectories. Unlike traditional transformer-based methods with quadratic attention complexity for sequence length, DRAMA is able to achieve a less computationally intensive attention complexity, demonstrating potential to deal with increasingly complex scenarios. Leveraging our Mamba fusion module, DRAMA efficiently and effectively fuses the features of the camera and LiDAR modalities. In addition, we introduce a Mamba-Transformer decoder that enhances the overall planning performance. This module is universally adaptable to any Transformer-based model, especially for tasks with long sequence inputs. We further introduce a novel feature state dropout which improves the planner's robustness without increasing training and inference times. Extensive experimental results show that DRAMA achieves higher accuracy on the NAVSIM dataset compared to the baseline Transfuser, with fewer parameters and lower computational costs.

cs.RO↗

arXiv2018

On the quasisymmetric minimality of homogeneous perfect sets

Z. Wen and J. Wu introduced the notion of homogeneous perfect sets as a generalization of Cantor type sets and determined their exact Hausdorff dimension based on the length of their fundamental intervals and the gaps between them. In this paper, we considered the minimality of the homogeneous perfect sets with Hausdorff dimension 1 and proved they are 1-dimensional quasisymmetrically minimal under some conditions.

math.MG↗

arXiv2018

Three strongly hyperbolic metrics on ptolemy spaces

Recently, strongly hyperbolic space as certain analytic enhancements of Gromov hyperbolic space was introduced by B. Nica and J. Spakula. In this note, we prove that the log-metric log(1+d) on a Ptolemy space (X,d) is a strongly hyperbolic metric. Using our result, we construct three metrics on a Ptolemy metric space and prove they are strongly hyperbolic.

math.MG↗