Author name cluster

Tian Xia

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

17 papers

2 author rows

AAAI Conference 2026 Conference Paper

Double Rounding: Nearly Lossless Adaptive Bit Switching for QAT

Haiduo Huang
Zhenhua Liu
Tian Xia
Pengju Ren

Model quantization is widely applied for compressing and accelerating deep neural networks (DNNs). However, conventional Quantization-Aware Training (QAT) focuses on training DNNs with uniform bit-width. The bit-width settings vary across different hardware and transmission demands, which induces considerable training and storage costs. Hence, the scheme of one-shot joint training multiple precisions is proposed to address this issue. Previous works either store a larger FP32 model to switch between different precision models for higher accuracy or store a smaller INT8 model but compromise accuracy due to using shared quantization parameters. In this paper, we introduce the Double Rounding quantization method, which fully utilizes the quantized representation range to accomplish nearly lossless bit-switching while reducing storage by using the highest integer precision instead of full precision. Furthermore, we observe a competitive interference among different precisions during one-shot joint training, primarily due to inconsistent gradients of quantization scales during backward propagation. To tackle this problem, we propose an Adaptive Learning Rate Scaling (AdaScale) technique that dynamically adapts learning rates for various precisions to optimize the training process. Additionally, we extend our Double Rounding to one-shot mixed precision training and develop a Hessian-Aware Stochastic Bit-switching (HessBit) strategy. Experimental results on the ImageNet-1K classification demonstrate that our methods have enough advantages to state-of-the-art one-shot joint QAT in both multi-precision and mixed-precision. We validate the feasibility of our method on detection and segmentation tasks, as well as on LLMs task.

PDF Details DOI

AAAI Conference 2026 Conference Paper

PartialNet: Compute Less, Perform Better

Haiduo Huang
Tian Xia
Wenzhe Zhao
Pengju Ren

Achieving a balance between low parameter count, reduced FLOPs, and high accuracy and throughput remains a central challenge in neural network design. To address this, we propose the partial channel mechanism (PCM), which leverages the inherent redundancy in feature map channels. PCM divides feature map channels into multiple groups, each processed by distinct operations such as convolution, attention, pooling, or identity mapping. Building on this, we introduce partial attention convolution (PATConv), a novel module that efficiently fuses convolution and visual attention within a unified framework. Our results demonstrate that PATConv can fully replace both standard convolution and visual attention modules, leading to significant reductions in parameters and FLOPs. Furthermore, PATConv enables three efficient visual attention variants: Partial Channel Attention, Partial Spatial Attention, and Partial Self-Attention. To further optimize the allocation of channel splits, we propose dynamic {partial convolution (DPConv), which adaptively learns the optimal split ratio for each layer, achieving a better trade-off between speed and accuracy. By integrating PATConv and DPConv, we develop a new hybrid network family, PartialNet, which achieves superior top-1 accuracy and inference speed on ImageNet-1K, and demonstrates strong performance on COCO detection and segmentation tasks.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Phys-Liquid: A Physics-Informed Dataset for Estimating 3D Geometry and Volume of Transparent Deformable Liquids

Ke Ma
Yizhou Fang
Jean-Baptiste Weibel
Shuai Tan
Xinggang Wang
Yang Xiao
Yi Fang
Tian Xia

Estimating the geometric and volumetric properties of transparent deformable liquids is challenging due to optical complexities and dynamic surface deformations induced by container movements. Autonomous robots performing precise liquid manipulation tasks—such as dispensing, aspiration, and mixing—must handle containers in ways that inevitably induce these deformations, complicating accurate liquid state assessment. Current datasets lack comprehensive physics-informed simulation data representing realistic liquid behaviors under diverse dynamic scenarios. To bridge this gap, we introduce Phys-Liquid, a physics-informed dataset comprising 97,200 simulation images and corresponding 3D meshes, capturing liquid dynamics across multiple laboratory scenes, lighting conditions, liquid colors, and container rotations. To validate the realism and effectiveness of Phys-Liquid, we propose a four-stage reconstruction and estimation pipeline involving liquid segmentation, multi-view mask generation, 3D mesh reconstruction, and real-world scaling. Experimental results demonstrate improved accuracy and consistency in reconstructing liquid geometry and volume, outperforming existing benchmarks. The dataset and associated validation methods facilitate future advancements in transparent liquid perception tasks.

PDF Details DOI

ICML Conference 2025 Conference Paper

Diffusion Counterfactual Generation with Semantic Abduction

Rajat Rasal
Avinash Kori
Fabio De Sousa Ribeiro
Tian Xia
Ben Glocker

Counterfactual image generation presents significant challenges, including preserving identity, maintaining perceptual quality, and ensuring faithfulness to an underlying causal model. While existing auto-encoding frameworks admit semantic latent spaces which can be manipulated for causal control, they struggle with scalability and fidelity. Advancements in diffusion models present opportunities for improving counterfactual image editing, having demonstrated state-of-the-art visual quality, human-aligned perception and representation learning capabilities. Here, we present a suite of diffusion-based causal mechanisms, introducing the notions of spatial, semantic and dynamic abduction. We propose a general framework that integrates semantic representations into diffusion models through the lens of Pearlian causality to edit images via a counterfactual reasoning process. To the best of our knowledge, ours is the first work to consider high-level semantic identity preservation for diffusion counterfactuals and to demonstrate how semantic control enables principled trade-offs between faithful causal control and identity preservation.

Details

NeurIPS Conference 2025 Conference Paper

GeGS-PCR: Fast and Robust Color 3D Point Cloud Registration with Two-Stage Geometric-3DGS Fusion

Jiayi Tian
Haiduo Huang
Tian Xia
Wenzhe Zhao
Pengju Ren

We address the challenge of point cloud registration using color information, where traditional methods relying solely on geometric features often struggle in low-overlap and incomplete scenarios. To overcome these limitations, we propose GeGS-PCR, a novel two-stage method that combines geometric, color, and Gaussian information for robust registration. Our approach incorporates a dedicated color encoder that enhances color features by extracting multi-level geometric and color data from the original point cloud. We introduce the Geometric-3DGS module, which encodes the local neighborhood information of colored superpoints to ensure a globally invariant geometric-color context. Leveraging LORA optimization, we maintain high performance while preserving the expressiveness of 3DGS. Additionally, fast differentiable rendering is utilized to refine the registration process, leading to improved convergence. To further enhance performance, we propose a joint photometric loss that exploits both geometric and color features. This enables strong performance in challenging conditions with extremely low point cloud overlap. We validate our method by colorizing the Kitti dataset as ColorKitti and testing on both Color3DMatch and Color3DLoMatch datasets. Our method achieves state-of-the-art performance with Registration Recall at 99. 9%, Relative Rotation Error as low as 0. 013, and Relative Translation Error as low as 0. 024, improving precision by at least a factor of 2.

PDF Details

IJCAI Conference 2025 Conference Paper

MiniMal: Hard-Label Adversarial Attack Against Static Malware Detection with Minimal Perturbation

Chengyi Li
Zhiyuan Jiang
Yongjun Wang
Tian Xia
Yayuan Zhang
Yuhang Mao

Static malware detectors based on machine learning are integral to contemporary antivirus systems, but they are vulnerable to adversarial attacks. While existing research has demonstrated success with adversarial attacks in black-box hard-label scenarios, challenges such as high perturbation rates and incomplete retention of functional integrity remain. To address these issues, we propose a novel black-box hard-label attack method, MiniMal. MiniMal begins with initialized adversarial examples and utilizes binary search and particle swarm optimization algorithms to streamline the perturbation content, significantly reducing the perturbation rate of the adversarial examples. Furthermore, we propose a functionality verification method grounded in file format parsing and control flow graph comparisons to ensure the functional integrity of the adversarial examples. Experimental results indicate that MiniMal achieves an attack success rate of over 98% against three leading machine learning detectors, improving performance by approximately 4. 8% to 7. 1% compared to state-of-the-art methods. MiniMal reduces perturbation rates to below 40%, making them 9 to 11 times lower than those of previous methods. Additionally, functional verification via Cuckoo Sandbox revealed that the adversarial examples generated by MiniMal retained 100% functional integrity, even with various modifications applied.

PDF Details DOI

TMLR Journal 2024 Journal Article

UniCtrl: Improving the Spatiotemporal Consistency of Text-to-Video Diffusion Models via Training-Free Unified Attention Control

Tian Xia
Xuweiyi Chen
Sihan Xu

Video Diffusion Models have been developed for video generation, usually integrating text and image conditioning to enhance control over the generated content. Despite the progress, ensuring consistency across frames remains a challenge, particularly when using text prompts as control conditions. To address this problem, we introduce UniCtrl, a novel, plug-and-play method that is universally applicable to improve the spatiotemporal consistency and motion diversity of videos generated by text-to-video models without additional training. UniCtrl ensures semantic consistency across different frames through cross-frame self-attention control, and meanwhile, enhances the motion quality and spatiotemporal consistency through motion injection and spatiotemporal synchronization. Our experimental results demonstrate UniCtrl's efficacy in enhancing various text-to-video models, confirming its effectiveness and universality.

PDF Details

AAAI Conference 2023 Conference Paper

Constrained Market Share Maximization by Signal-Guided Optimization

Bo Hui
Yuchen Fang
Tian Xia
Sarp Aykent
Wei-Shinn Ku

With the rapid development of the airline industry, maximizing the market share with a constrained budget is an urgent econometric problem for an airline. We investigate the problem by adjusting flight frequencies on different flight routes. Owing to the large search space of solutions and the difficulty of predicting the market, this problem is in general daunting to solve. This paper proposes a novel two-stage optimization method to address the challenges. On the higher level, we use a signal to guide the optimization process toward a constrained satisfying solution. On the lower level, we consider the consecutive itineraries in real scenarios and model the unseen correlations between routes in itineraries for market share prediction. In theory, we prove the convergence of our optimization approach. In the experiment, we empirically verify the superiority of both our prediction model and optimization approach over existing works with large-scale real-world data. Our code has been released at: https://github.com/codingAndBS/AirlineMarket.

PDF Details DOI

ICML Conference 2023 Conference Paper

High Fidelity Image Counterfactuals with Probabilistic Causal Models

Fabio De Sousa Ribeiro
Tian Xia
Miguel Monteiro
Nick Pawlowski
Ben Glocker

We present a general causal generative modelling framework for accurate estimation of high fidelity image counterfactuals with deep structural causal models. Estimation of interventional and counterfactual queries for high-dimensional structured variables, such as images, remains a challenging task. We leverage ideas from causal mediation analysis and advances in generative modelling to design new deep causal mechanisms for structured variables in causal models. Our experiments demonstrate that our proposed mechanisms are capable of accurate abduction and estimation of direct, indirect and total effects as measured by axiomatic soundness of counterfactuals.

Details

NeurIPS Conference 2023 Conference Paper

SaVeNet: A Scalable Vector Network for Enhanced Molecular Representation Learning

Sarp Aykent
Tian Xia

Geometric representation learning of molecules is challenging yet essential for applications in multiple domains. Despite the impressive breakthroughs made by geometric deep learning in various molecular representation learning tasks, effectively capturing complicated geometric features across spatial dimensions is still underexplored due to the significant difficulties in modeling efficient geometric representations and learning the inherent correlation in 3D structural modeling. These include computational inefficiency, underutilization of vectorial embeddings, and limited generalizability to integrate various geometric properties. To address the raised concerns, we introduce an efficient and effective framework, Scalable Vector Network (SaVeNet), designed to accommodate a range of geometric requirements without depending on costly embeddings. In addition, the proposed framework scales effectively with introduced direction noise. Theoretically, we analyze the desired properties (i. e. , invariance and equivariant) and framework efficiency of the SaVeNet. Empirically, we conduct a comprehensive series of experiments to evaluate the efficiency and expressiveness of the proposed model. Our efficiency-focused experiments underscore the model's empirical superiority over existing methods. Experimental results on synthetic and real-world datasets demonstrate the expressiveness of our model, which achieves state-of-the-art performance across various tasks within molecular representation learning.

PDF Details

ICRA Conference 2020 Conference Paper

Learning Multi-Robot Decentralized Macro-Action-Based Policies via a Centralized Q-Net

Yuchen Xiao
Joshua Hoffman
Tian Xia
Christopher Amato

In many real-world multi-robot tasks, high-quality solutions often require a team of robots to perform asynchronous actions under decentralized control. Decentralized multi-agent reinforcement learning methods have difficulty learning decentralized policies because of the environment appearing to be non-stationary due to other agents also learning at the same time. In this paper, we address this challenge by proposing a macro-action-based decentralized multi-agent double deep recurrent Q-net (MacDec-MADDRQN) which trains each decentralized Q-net using a centralized Q-net for action selection. A generalized version of MacDec-MADDRQN with two separate training environments, called Parallel-MacDec-MADDRQN, is also presented to leverage either centralized or decentralized exploration. The advantages and the practical nature of our methods are demonstrated by achieving near-centralized results in simulation and having real robots accomplish a warehouse tool delivery task in an efficient way.

Details

AAAI Conference 2020 Short Paper

Multi-Agent/Robot Deep Reinforcement Learning with Macro-Actions (Student Abstract)

Yuchen Xiao
Joshua Hoffman
Tian Xia
Christopher Amato

We consider the challenges of learning multi-agent/robot macro-action-based deep Q-nets including how to properly update each macro-action value and accurately maintain macro-action-observation trajectories. We address these challenges by ﬁrst proposing two fundamental frameworks for learning macro-action-value function and joint macro-actionvalue function. Furthermore, we present two new approaches of learning decentralized macro-action-based policies, which involve a new double Q-update rule that facilitates the learning of decentralized Q-nets by using a centralized Q-net for action selection. Our approaches are evaluated both in simulation and on real robots.

PDF Details

IJCAI Conference 2015 Conference Paper

A Direct Boosting Approach for Semi-supervised Classification

Shaodan Zhai
Tian Xia
Zhongliang Li
Shaojun Wang

We introduce a semi-supervised boosting approach (SSDBoost), which directly minimizes the classification errors and maximizes the margins on both labeled and unlabeled samples, without resorting to any upper bounds or approximations. A twostep algorithm based on coordinate descent/ascent is proposed to implement SSDBoost. Experiments on a number of UCI datasets and synthetic data show that SSDBoost gives competitive or superior results over the state-of-the-art supervised and semi-supervised boosting algorithms in the cases that the labeled data is limited, and it is very robust in noisy cases.

PDF Details

NeurIPS Conference 2013 Conference Paper

Direct 0-1 Loss Minimization and Margin Maximization with Boosting

Shaodan Zhai
Tian Xia
Ming Tan
Shaojun Wang

We propose a boosting method, DirectBoost, a greedy coordinate descent algorithm that builds an ensemble classifier of weak classifiers through directly minimizing empirical classification error over labeled training examples; once the training classification error is reduced to a local coordinatewise minimum, DirectBoost runs a greedy coordinate ascent algorithm that continuously adds weak classifiers to maximize any targeted arbitrarily defined margins until reaching a local coordinatewise maximum of the margins in a certain sense. Experimental results on a collection of machine-learning benchmark datasets show that DirectBoost gives consistently better results than AdaBoost, LogitBoost, LPBoost with column generation and BrownBoost, and is noise tolerant when it maximizes an n'th order bottom sample margin.

PDF Details

ICRA Conference 2013 Conference Paper

Model-based telerobotic control with virtual fixtures for satellite servicing tasks

Tian Xia
Simon Léonard
Isha Kandaswamy
Amy A. Blank
Louis L. Whitcomb
Peter Kazanzides

Our goal is to develop new methods for telerobotic on-orbit servicing of spacecraft under ground-based supervisory control of human operators to perform tasks in the presence of uncertainty and telemetry time delay of several seconds. We propose a new delay tolerant control methodology, using virtual fixtures, hybrid position/force control, task frame formalism, and environment modeling, that is robust to modeling and registration errors. The task model is represented by graphical primitives and virtual fixtures on the teleoperation master and by a hybrid position/force controller on the slave robot. The virtual fixtures guide the operator through a model-based simulation of the task, and the goal of the slave controller is to reproduce this action (after a few seconds of delay) or, if measurements are not consistent with the models, to stop motion and alert the operator. This approach is suitable for tasks in unstructured environments, such as servicing of existing on-orbit spacecraft that were not designed for servicing. We introduce the overall control concept, its main components, and an example application in which the remote slave robot cuts the tape that secures a flap of multi-layer insulation over the access panel of a satellite mockup.

Details

IROS Conference 2012 Conference Paper

Augmented reality environment with virtual fixtures for robotic telemanipulation in space

Tian Xia
Simon Léonard
Anton Deguet
Louis L. Whitcomb
Peter Kazanzides

This paper presents an augmented reality framework, implemented on the master console of a modified da Vinci® surgical robot, that enables the operator to design and implement assistive virtual fixtures during teleoperation. Our specific goal is to facilitate teleoperation with large time delays, such as the delay of several seconds that occurs with ground-based control of robotic systems in earth orbit. The virtual fixtures give immediate visual feedback and motion guidance to the operator, while the remote slave performs motions consistent with those constraints. This approach is suitable for tasks in unstructured environments, such as servicing of existing on-orbit spacecraft that were not designed for servicing. We conducted a pilot study by teleoperating a remote slave robot for a thermal barrier blanket cutting task using virtual fixtures with and without time delay. The results show that virtual fixtures reduce the time required to complete the task while also eliminating significant manipulation errors, such as tearing the blanket. The improvement in performance is especially dramatic when a simulated time delay (4 seconds) is introduced.

Details

IROS Conference 2011 Conference Paper

A constrained optimization approach to virtual fixtures for multi-robot collaborative teleoperation

Tian Xia
Ankur Kapoor
Peter Kazanzides
Russell H. Taylor

This paper presents a constrained optimization framework that enables the implementation of multi-robot constraints, as virtual fixtures, to assist human operators, in a teleoperated scenario. The collaborative constraints guide the motion of multiple robots such that the spatial and temporal relationships are maintained between them, while following human input motion objectives. We demonstrate this control architecture for the task of manipulating a surgical knot to a target point. The teleoperation system uses four arms from a da Vinci Surgical System® (two master manipulators and two slave manipulators), with custom electronics and software. It extends previous work, which focused on a cooperatively controlled system where the motions of two robots were directly controlled by user-applied forces. Our current system enables us to effectively evaluate the accuracy of the knot positioning task and completion time in a clinically realistic setup for Minimally Invasive Surgery

Details