← Search

Xiao Ma

39 accepted papers

2026

Environment-Driven Online LiDAR-Camera Extrinsic Calibration (I)

ICRA 2026poster

LiDAR-camera extrinsic calibration (LCEC) is crucial for multi-modal data fusion in autonomous robotic systems. Existing methods, whether target-based or target-free, typically rely on customized calibration targets or fixed scene types, which limit their applicability in real-world scenarios. To ad…

Cited by 0Scholar
2026

RoboOmni: Actions Are Just Another Modality for Your Vision-Language Models

ICML 2026poster

Integrating Vision-Language Models (VLMs) into robotics has facilitated the development of generalizable Vision-Language Action (VLA) policies. However, unified discrete frameworks lag behind decoupled continuous designs due to limitations in action chunking and temporal modeling. To address this, w…

Cited by 0SourceScholar
2026

Target-Aware Invertible Encoder with Reconstruction Guidance for Infrared Small Target Detection

CVPR 2026

Modern detectors typically deepen backbones and rely on aggressive downsampling to harvest high-level semantics. But this severely degrades low-energy infrared tiny targets via rescale-induced information loss. This work introduces InvDet, a target-aware invertible encoder that unifies information p

Cited by 0SourceScholar
2026

WMPO: World Model-based Policy Optimization for Vision-Language-Action Models

ICLR 2026poster

Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation, but their reliance on expert demonstrations limits their ability to learn from failures and perform self-corrections. Reinforcement learning (RL) addresses these through self-improving interact…

Cited by 0SourcecodeScholar
2025

BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models

NeurIPS 2025poster

Recently, leveraging pre-trained vision-language models (VLMs) for building vision-language-action (VLA) models has emerged as a promising approach to effective robot manipulation learning. However, only few methods incorporate 3D signals into VLMs for action prediction, and they do not fully levera…

Cited by 0SourcecodeScholar
2025

CODA: Repurposing Continuous VAEs for Discrete Tokenization

ICCV 2025poster

Discrete visual tokenizers transform images into a sequence of tokens, enabling token-based visual generation akin to language models. However, this process is inherently challenging, as it requires both compressing visual signals into a compact representation and discretizing them into a fixed set…

Cited by 0SourcePDFScholar
2025

Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation

NeurIPS 2025poster

We present Chain-of-Action (CoA), a novel visuomotor policy paradigm built upon Trajectory Autoregressive Modeling. Unlike conventional approaches that predict next step action(s) forward, CoA generates an entire trajectory by explicit backward reasoning with task-specific goals through an action-le…

Cited by 0SourceScholar
2025

Effective Tuning Strategies for Generalist Robot Manipulation Policies

ICRA 2025

Generalist robot manipulation policies (GMPs) have the potential to generalize across a wide range of tasks, devices, and environments. However, existing policies continue to struggle with out-of-distribution scenarios due to the inherent difficulty of collecting sufficient action data to cover exte

Cited by 9SourceScholar
2025

Human-assisted Robotic Policy Refinement via Action Preference Optimization

NeurIPS 2025poster

Establishing a reliable and iteratively refined robotic system is essential for deploying real-world applications. While Vision-Language-Action (VLA) models are widely recognized as the foundation model for such robotic deployment, their reliance on offline expert demonstrations critically limi…

Cited by 0SourcecodeScholar
2025

ProcWorld: Benchmarking Large Model Planning in Reachability-Constrained Environments

EMNLP 2025

We introduce ProcWorld, a large-scale benchmark for partially observable embodied spatial reasoning and long-term planning with large language models (LLM) and vision language models (VLM). ProcWorld features a wide range of challenging embodied navigation and object manipulation tasks, covering 16

Cited by 0SourcePDFScholar
2025

Safety Alignment Should be Made More Than Just a Few Tokens Deep

ICLR 2025oral

The safety alignment of current Large Language Models (LLMs) is vulnerable. Simple attacks, or even benign fine-tuning, can jailbreak aligned models. We note that many of these vulnerabilities are related to a shared underlying issue: safety alignment can take shortcuts, wherein the alignment adapts…

2024

BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark

CoRL 2024poster

We introduce BiGym, a new benchmark and learning environment for mobile bi-manual demo-driven robotic manipulation. BiGym features 40 diverse tasks set in home environments, ranging from simple target reaching to complex kitchen cleaning. To capture the real-world performance accurately, we provide…

Cited by 10SourceScholar
2024

Collaborative Weakly Supervised Video Correlation Learning for Procedure-Aware Instructional Video Analysis

AAAI 2024technical

Video Correlation Learning (VCL), which aims to analyze the relationships between videos, has been widely studied and applied in various general video tasks. However, applying VCL to instructional videos is still quite challenging due to their intrinsic procedural temporal structure. Specifically, p…

Cited by 5SourcePDFScholar
2024

Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation

CVPR 2024poster

This paper introduces Hierarchical Diffusion Policy (HDP) a hierarchical agent for multi-task robotic manipulation. HDP factorises a manipulation policy into a hierarchical structure: a high-level task-planning agent which predicts a distant next-best end-effector pose (NBP) and a low-level goal-con…

Cited by 46SourcePDFScholar
2024

MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning

NeurIPS 2024spotlight

Video causal reasoning aims to achieve a high-level understanding of video content from a causal perspective. However, current video reasoning tasks are limited in scope, primarily executed in a question-answering paradigm and focusing on short videos containing only a single event and simple causal…

2024

Model-Based Label-to-Image Diffusion for Semi-Supervised Choroidal Vessel Segmentation

ICASSP 2024accepted

Current successful choroidal vessel segmentation methods rely on large amounts of voxel-level annotations on the 3D optical coherence tomography images, which are hard and time-consuming. Semi-supervised learning solves this issue by enabling model learning from both unlabeled data and a limited amo…

Cited by 0SourceScholar
2024

Responding to the Call: Exploring Automatic Music Composition Using a Knowledge-Enhanced Model

AAAI 2024technical

Call-and-response is a musical technique that enriches the creativity of music, crafting coherent musical ideas that mirror the back-and-forth nature of human dialogue with distinct musical characteristics. Although this technique is integral to numerous musical compositions, it remains largely unch…

2024

TimeCraft: Navigate Weakly-Supervised Temporal Grounded Video Question Answering via Bi-directional Reasoning

ECCV 2024poster

"Video reasoning typically operates within the Video Question-Answering (VQA) paradigm, which demands that the models understand and reason about video content from temporal and causal perspectives. Traditional supervised VQA methods gain this capability through meticulously annotated QA datasets, w…

2024

Weighting Online Decision Transformer with Episodic Memory for Offline-to-Online Reinforcement Learning

ICRA 2024poster

Offline reinforcement learning (RL) has been shown to be successfully modeled as a sequence modeling problem, drawing inspiration from the success of Transformers. Offline RL is often limited by the quality of the offline dataset, so offline-to-online RL is a more realistic setting. Online decision…

Cited by 2SourceScholar
2023

DaxBench: Benchmarking Deformable Object Manipulation with Differentiable Physics

ICLR 2023top-5%

Deformable object manipulation (DOM) is a long-standing challenge in robotics and has attracted significant interest recently. This paper presents DaXBench, a differentiable simulation framework for DOM. While existing work often focuses on a specific type of deformable objects, DaXBench supports fl…

2023

DiffMimic: Efficient Motion Mimicking with Differentiable Physics

ICLR 2023poster

Motion mimicking is a foundational task in physics-based character animation. However, most existing motion mimicking methods are built upon reinforcement learning (RL) and suffer from heavy reward engineering, high variance, and slow convergence with hard explorations. Specifically, they usually ta…

2023

Efficient Diffusion Policies For Offline Reinforcement Learning

NeurIPS 2023poster

Offline reinforcement learning (RL) aims to learn optimal policies from offline datasets, where the parameterization of policies is crucial but often overlooked. Recently, Diffsuion-QL significantly boosts the performance of offline RL by representing a policy with a diffusion model, whose success r…

2023

Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting

EMNLP 2023long main

A crucial challenge for generative large language models (LLMs) is diversity: when a user's prompt is under-specified, models may follow implicit assumptions while generating a response, which may result in homogenization of the responses, as well as certain demographic groups being under-represente…

Cited by 0SourceScholar
2023

InsActor: Instruction-driven Physics-based Characters

NeurIPS 2023poster

Generating animation of physics-based characters with intuitive control has long been a desirable task with numerous applications. However, generating physically simulated animations that reflect high-level human instructions remains a difficult problem due to the complexity of physical environments…

2023

Mutual Information Regularized Offline Reinforcement Learning

NeurIPS 2023poster

The major challenge of offline RL is the distribution shift that appears when out-of-distribution actions are queried, which makes the policy improvement direction biased by extrapolation errors. Most existing methods address this problem by penalizing the policy or value for deviating from the beha…

2023

RPM: Generalizable Multi-Agent Policies for Multi-Agent Reinforcement Learning

ICLR 2023poster

Despite the recent advancement in multi-agent reinforcement learning (MARL), the MARL agents easily overfit the training environment and perform poorly in evaluation scenarios where other agents behave differently. Obtaining generalizable policies for MARL agents is thus necessary but challenging ma…

Cited by 2SourcePDFScholar
2020

Balanced Meta-Softmax for Long-Tailed Visual Recognition

NeurIPS 2020poster

Deep classifiers have achieved great success in visual recognition. However, real-world data is long-tailed by nature, leading to the mismatch between training and testing distributions. In this paper, we show that the Softmax function, though used in most classification tasks, gives a biased gradie…

2020

Contrastive Variational Reinforcement Learning for Complex Observations

CoRL 2020

Deep reinforcement learning (DRL) has achieved significant success in various robot tasks: manipulation, navigation, etc. However, complex visual observations in natural environments remains a major challenge. This paper presents Contrastive Variational Reinforcement Learning (CVRL), a model-based m

2020

Discriminative Particle Filter Reinforcement Learning for Complex Partial observations

ICLR 2020poster

Deep reinforcement learning is successful in decision making for sophisticated games, such as Atari, Go, etc. However, real-world decision making often requires reasoning with partial information extracted from complex visual observations. This paper presents Discriminative Particle Filter Reinfor…

Cited by 45SourcecodeScholar
2020

Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction

ECCV 2020poster

Understanding crowd motion dynamics is critical to real-world applications, e.g., surveillance systems and autonomous driving. This is challenging because it requires effectively modeling the socially aware crowd spatial interaction and complex temporal dependencies. We believe attention is the most…

2019

Differentiable Algorithm Networks for Composable Robot Learning

RSS 2019poster

This paper introduces the Differentiable Algorithm Network (DAN), a composable architecture for robot learning systems. A DAN is composed of neural network modules, each encoding a differentiable robot algorithm and an associated model; and it is trained end-to-end from data. DAN combines the streng…

Cited by 81SourcePDFScholar