← Search

yilun chen

47 accepted papers

2026

MM-ACT: Learn from Multimodal Parallel Generation to Act

CVPR 2026

A generalist robotic policy needs both semantic understanding for task planning and the ability to interact with the environment through predictive capabilities. To tackle this, we present MM-ACT, a unified Vision-Language-Action (VLA) model that integrates text, image, and action in shared token sp

Cited by 0SourcecodeScholar
2026

NavDP: Learning Sim-To-Real Navigation Diffusion Policy with Privileged Information Guidance

ICRA 2026poster

Learning to navigate in dynamic and complex open-world environments is a critical yet challenging capability for autonomous robots. Existing approaches often rely on cascaded modular frameworks, which require extensive hyperparameter tuning or learning from limited real-world demonstration data. In …

2026

Open-Vocabulary Object-Goal Navigation by Generalizing Semantic Mapping with Dense CLIP

ICRA 2026poster

Object-oriented embodied navigation tasks require agents to locate specific objects, either defined by category or images, in unseen environments. While recent methods have made progress in extending closed-set models to open-vocabulary scenarios with foundation models, they typically rely on traini…

Cited by 0Scholar
2026

Re^3Sim: Generating High-Fidelity Simulation Data Via 3D-Photorealistic Real-To-Sim for Robotic Manipulation

ICRA 2026poster

Real-world data collection for robotics is costly and resource-intensive, requiring skilled operators and expensive hardware. Simulations offer a scalable alternative but often fail to achieve sim-to-real generalization due to geometric and visual gaps. To address these challenges, we propose a 3D-p…

Cited by 0Scholar
2026

Rhythm: Learning Interactive Whole-Body Control for Dual Humanoids

RSS 2026poster

Realizing interactive whole-body control for multi-humanoid systems is critical for unlocking complex collaborative capabilities in shared environments. Although recent advancements have significantly enhanced the agility of individual robots, bridging the gap to physically coupled multi-humanoid in…

Cited by 1SourceScholar
2026

RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulation

ICLR 2026poster

Large language and vision-language models have inspired end-to-end vision-language-action (VLA) systems in robotics, yet existing robot datasets remain costly, embodiment-specific, and insufficient, limiting robustness and generalization. Recent approaches address this by adopting a plan-then-execut…

Cited by 0SourcecodeScholar
2026

Spatially Guided Training for Vision-Language-Action Model

ICLR 2026poster

Large vision–language models (VLMs) excel at multimodal understanding but fall short when extended to embodied tasks, where instructions must be transformed into low-level motor actions. We introduce SP-VLA, a dual-system **V**ision–**L**anguage–**A**ction framework that leverages **S**patial **P**r…

Cited by 0SourceScholar
2026

StreamVLN: Streaming Vision-And-Language Navigation Via SlowFast Context Modeling

ICRA 2026poster

Vision-and-Language Navigation (VLN) in real-world settings requires agents to process continuous visual streams and generate actions with low latency grounded in language instructions. While Video-based Large Language Models (Video-LLMs) have driven recent progress, current VLN methods based on Vid…

2026

Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling

AAAI 2026technical

Recent vision-language-action (VLA) models built on pretrained vision-language models (VLMs) have demonstrated strong performance in robotic manipulation. However, these models remain constrained by the single-frame image paradigm and fail to fully leverage the temporal information offered by multi-

Cited by 0SourcePDFScholar
2026

Unveiling the Surprising Efficacy of Navigation Understanding in End-To-End Autonomous Driving

ICRA 2026poster

Global navigation information and local scene understanding are two crucial components of autonomous driving systems. However, our experimental results indicate that many end-to-end autonomous driving systems tend to over-rely on local scene understanding while failing to utilize global navigation i…

2026

Vision-Language-Action Instruction Tuning: From Understanding to Manipulation

ICLR 2026poster

To operate effectively in the real world, robots should integrate multimodal reasoning with precise action generation. However, existing vision-language-action (VLA) models often sacrifice one for the other, narrow their abilities to task-specific manipulation data, and suffer catastrophic forgettin…

Cited by 0SourcecodeScholar
2026

VistaBot: View-Robust Robot Manipulation Via Spatiotemporal-Aware View Synthesis

ICRA 2026poster

Recently, end-to-end robotic manipulation models have gained significant attention for their generalizability and scalability. However, they often suffer from limited robustness to camera viewpoint changes when training with a fixed camera. In this paper, we propose VistaBot, a novel framework that …

2026

X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model

ICLR 2026poster

Successful generalist Vision-Language-Action (VLA) models that rely on effective training across diverse robotic platforms with large-scale, cross-embodiment, heterogeneous datasets. To facilitate and leverage the heterogeneity in rich, diverse robotic data sources, we propose a novel Soft Prompt ap…

Cited by 0SourcecodeScholar
2025

A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning

CVPR 2025poster

Pre-trained vision models (PVMs) are fundamental to modern robotics, yet their optimal configuration remains unclear. Through systematic evaluation, we find that while DINO and iBOT outperform MAE across visuomotor control and perception tasks, they struggle when trained on non-(single-)object-centr…

2025

Bench4Merge: A Comprehensive Benchmark for Merging in Realistic Dense Traffic with Micro-Interactive Vehicles

IROS 2025

While the capabilities of autonomous driving have advanced rapidly, merging into dense traffic remains a significant challenge, many motion planning methods for this scenario have been proposed but it is hard to evaluate them. Most existing closed-loop simulators rely on rule-based controls for othe

Cited by 0SourcecodeScholar
2025

CoopDETR: A Unified Cooperative Perception Framework for 3D Detection via Object Query

ICRA 2025

Cooperative perception enhances the individual perception capabilities of autonomous vehicles (AVs) by providing a comprehensive view of the environment. However, balancing perception performance and transmission costs remains a significant challenge. Current approaches that transmit regionlevel fea

Cited by 9SourceScholar
2025

Dual-AEB: Synergizing Rule-Based and Multimodal Large Language Models for Effective Emergency Braking

ICRA 2025

Automatic Emergency Braking (AEB) systems are a crucial component in ensuring the safety of passengers in autonomous vehicles. Conventional AEB systems primarily rely on closed-set perception modules to recognize traffic conditions and assess collision risks. To enhance the adaptability of AEB syste

Cited by 3SourcecodeScholar
2025

Enhancing Indoor Occupancy Prediction via Sparse Query-Based Multi-Level Consistent Knowledge Distillation

RA-L 2025

Occupancy prediction provides critical geometric and semantic understanding for robotics but faces efficiency-accuracy trade-offs. Current dense methods suffer computational waste on empty voxels, while sparse query-based approaches lack robustness in diverse and complex indoor scenes. In this paper

Cited by 1SourceScholar
2025

GENMANIP: LLM-driven Simulation for Generalizable Instruction-Following Manipulation

CVPR 2025poster

Robotic manipulation in real-world settings remains challenging, especially regarding robust generalization. Existing simulation platforms lack sufficient support for exploring how policies adapt to varied instructions and scenarios. Thus, they lag behind the growing interest in instruction-followin…

Cited by 0SourcePDFScholar
2025

Language-to-Space Programming for Training-Free 3D Visual Grounding

EMNLP 2025

3D visual grounding (3DVG) is challenging due to the need to understand 3D spatial relations. While supervised approaches have achieved superior performance, they are constrained by the scarcity and high annotation costs of 3D vision-language datasets. Training-free approaches based on LLMs/VLMs eli

2025

LiON: Learning Point-Wise Abstaining Penalty for LiDAR Outlier DetectioN Using Diverse Synthetic Data

AAAI 2025technical

LiDAR-based semantic scene understanding is an important module in the modern autonomous driving perception stack. However, identifying outlier points in a LiDAR point cloud is challenging as LiDAR point clouds lack semantically-rich information. While former SOTA methods adopt heuristic architectur…

2025

MoMoE: Mixture of Moderation Experts Framework for AI-Assisted Online Governance

EMNLP 2025

Large language models (LLMs) have shown great potential in flagging harmful content in online communities. Yet, existing approaches for moderation require a separate model for every community and are opaque in their decision-making, limiting real-world adoption. We introduce Mixture of Moderation Ex

2025

Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities

ICCV 2025poster

Recent Vision-and-Language Navigation (VLN) advancements are promising, but their idealized assumptions about robot movement and control fail to reflect physically embodied deployment challenges. To bridge this gap, we introduce VLN-PE, a physically realistic VLN platform supporting humanoid, quadru…

2025

RoboGround: Robotic Manipulation with Grounded Vision-Language Priors

CVPR 2025poster

Recent advancements in robotic manipulation have highlighted the potential of intermediate representations for improving policy generalization. In this work, we explore grounding masks as an effective intermediate representation, balancing two key advantages: (1) effective spatial guidance that spec…

Cited by 0SourcePDFScholar
2025

SLM-Mod: Small Language Models Surpass LLMs at Content Moderation

NAACL 2025long

Large language models (LLMs) have shown promise in many natural language understanding tasks, including content moderation. However, these models can be expensive to query in real-time and do not allow for a community-specific approach to content moderation. To address these challenges, we explore t…

2025

Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving

ICLR 2025poster

Understanding world dynamics is crucial for planning in autonomous driving. Recent methods attempt to achieve this by learning a 3D occupancy world model that forecasts future surrounding scenes based on current observation. However, 3D occupancy labels are still required to produce promising result…

2024

Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers

NeurIPS 2024poster

Recent advancements in 3D Large Language Models (LLMs) have demonstrated promising capabilities for 3D scene understanding. However, previous methods exhibit deficiencies in general referencing and grounding capabilities for intricate scene comprehension. In this paper, we introduce the use of objec…

2024

EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection

ICRA 2024poster

In autonomous driving, cooperative perception makes use of multi-view cameras from both vehicles and infrastructure, providing a global vantage point with rich semantic context of road conditions beyond a single vehicle viewpoint. Currently, two major challenges persist in vehicle-infrastructure coo…

Cited by 7SourcecodeScholar
2024

MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations

NeurIPS 2024poster

With the emergence of LLMs and their integration with other data modalities, multi-modal 3D perception attracts more attention due to its connectivity to the physical world and makes rapid progress. However, limited by existing datasets, previous works mainly focus on understanding object properties…

2024

PointLLM: Empowering Large Language Models to Understand Point Clouds

ECCV 2024oral

"The unprecedented advancements in Large Language Models (LLMs) have shown a profound impact on natural language processing but are yet to fully embrace the realm of 3D understanding. This paper introduces PointLLM, a preliminary effort to fill this gap, empowering LLMs to understand point clouds an…

2024

TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes

ECCV 2024poster

"3D dense captioning stands as a cornerstone in achieving a comprehensive understanding of 3D scenes through natural language. It has recently witnessed remarkable achievements, particularly in indoor settings. However, the exploration of 3D dense captioning in outdoor scenes is hindered by two majo…

2024

VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding

CoRL 2024poster

3D visual grounding is crucial for robots, requiring integration of natural language and 3D scene understanding. Traditional methods depend on supervised learning with 3D point clouds are limited by scarce datasets. Recently zero-shot methods leveraging LLMs have been proposed to address the data is…

Cited by 9SourcecodeScholar
2024

What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights

NeurIPS 2024poster

Severe data imbalance naturally exists among web-scale vision-language datasets. Despite this, we find CLIP pre-trained thereupon exhibits notable robustness to the data imbalance compared to supervised learning, and demonstrates significant effectiveness in learning generalizable representations. W…

2023

FocalFormer3D: Focusing on Hard Instance for 3D Object Detection

ICCV 2023poster

False negatives (FN) in 3D object detection, e.g., missing predictions of pedestrians, vehicles, or other obstacles, can lead to potentially dangerous situations in autonomous driving. While being fatal, this issue is understudied in many current 3D detection methods. In this work, we propose Hard I…

Cited by 123PDFcodeScholar
2023

INT2: Interactive Trajectory Prediction at Intersections

ICCV 2023poster

Motion forecasting is an important component in autonomous driving systems. One of the most challenging problems in motion forecasting is interactive trajectory prediction, whose goal is to jointly forecasts the future trajectories of interacting agents. To this end, we present a large-scale interac…

Cited by 10PDFcodeScholar
2022

TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection With Transformers

CVPR 2022poster

LiDAR and camera are two important sensors for 3D object detection in autonomous driving. Despite the increasing popularity of sensor fusion in this field, the robustness against inferior image conditions, e.g., bad illumination and sensor misalignment, is under-explored. Existing fusion methods are…

Cited by 806PDFcodeScholar
2022

Unifying Voxel-based Representation with Transformer for 3D Object Detection

NeurIPS 2022accept

In this work, we present a unified framework for multi-modality 3D object detection, named UVTR. The proposed method aims to unify multi-modality representations in the voxel space for accurate and robust single- or cross-modality 3D detection. To this end, the modality-specific space is first desig…

2021

A Light-Weight Semantic Map for Visual Localization towards Autonomous Driving

ICRA 2021poster

Accurate localization is of crucial importance for autonomous driving tasks. Nowadays, we have seen a lot of sensor-rich vehicles (e.g. Robo-taxi) driving on the street autonomously, which rely on high-accurate sensors (e.g. Lidar and RTK GPS) and high-resolution map. However, low-cost production ca…

Cited by 128SourceScholar
2020

AVP-SLAM: Semantic Visual Mapping and Localization for Autonomous Vehicles in the Parking Lot

IROS 2020poster

Autonomous valet parking is a specific application for autonomous vehicles. In this task, vehicles need to navigate in narrow, crowded and GPS-denied parking lots. Accurate localization ability is of great importance. Traditional visual-based methods suffer from tracking lost due to texture-less reg…

Cited by 162SourceScholar
2019

Attention-based Hierarchical Deep Reinforcement Learning for Lane Change Behaviors in Autonomous Driving

IROS 2019poster

Performing safe and efficient lane changes is a crucial feature for creating fully autonomous vehicles. Recent advances have demonstrated successful lane following behavior using deep reinforcement learning, yet the interactions with other vehicles on-road for lane changes are rarely considered. In…

Cited by 139SourceScholar
2019

Fast Point R-CNN

ICCV 2019poster

We present a unified, efficient and effective framework for point-cloud based 3D object detection. Our two-stage approach utilizes both voxel representation and raw point cloud data to exploit respective advantages. The first stage network, with voxel representation as input, only consists of light…

Cited by 511PDFScholar
2019

Interactive Trajectory Prediction for Autonomous Driving via Recurrent Meta Induction Neural Network

ICRA 2019poster

Interactive driving is challenging but essential for autonomous cars in dense traffic or urban areas. Proper interaction requires understanding and prediction of future trajectories of all neighboring cars around a target vehicle. Current solutions typically assume a certain distribution or stochast…

Cited by 17SourceScholar
2018

Cascaded Pyramid Network for Multi-Person Pose Estimation

CVPR 2018poster

The topic of multi-person pose estimation has beenlargely improved recently, especially with the developmentof convolutional neural network. However, there still exista lot of challenging cases, such as occluded keypoints, in-visible keypoints and complex background, which cannot bewell addr…