← Search

Pengfei Li

52 accepted papers

2026

MeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving

CVPR 2026

Generative models have shown great potential in trajectory planning. Recent studies demonstrate that anchor-guided generative models are effective in modeling the uncertainty of driving behaviors and improving overall performance. However, these methods rely on discrete anchor vocabularies that must

Cited by 0SourcecodeScholar
2026

OccLLaMA: A Unified Occupancy-Language-Action World Model for Enhancing Motion Planning Via Multi-Task Learning

ICRA 2026poster

Scene understanding via multi-modal large language models and scene forecasting with world models have advanced the development of autonomous driving. The former maps visual inputs to driving-specific outputs, neglecting spatial reasoning and world dynamics. The latter captures world dynamics, lacki…

Cited by 0codeScholar
2026

On Revisiting Entropy for Identifying Mislabeled Medical Images

ICML 2026poster

Mislabeled samples in training datasets severely degrade the performance of deep networks, as overparameterized models tend to memorize erroneous labels. We address this challenge by proposing a novel approach for mislabeled data detection that leverages training dynamics. Our method is grounded in …

Cited by 0SourceScholar
2026

RedSage: A Cybersecurity Generalist LLM

ICLR 2026poster

Cybersecurity operations demand assistant LLMs that support diverse workflows without exposing sensitive data. Existing solutions either rely on proprietary APIs with privacy risks or on open models lacking domain adaptation. To bridge this gap, we curate 11.8B tokens of cybersecurity-focused contin…

Cited by 0SourcecodeScholar
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

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

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 …

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

Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration

NeurIPS 2025poster

Heterogeneous Large Language Model (LLM) fusion integrates the strengths of multiple source LLMs with different architectures into a target LLM with low computational overhead. While promising, existing methods suffer from two major limitations: 1) **reliance on real data from limited domain** for k…

Cited by 0SourceScholar
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

Fast and Slow Gradient Approximation for Binary Neural Network Optimization

AAAI 2025technical

Binary Neural Networks (BNNs) have garnered significant attention due to their immense potential for deployment on edge devices. However, the non-differentiability of the quantization function poses a challenge for the optimization of BNNs, as its derivative cannot be backpropagated. To address this…

2025

LASS: A Novel and Economical Data Augmentation Framework Based on Language Models for Debiasing Opinion Summarization

COLING 2025main

As more than 70% of reviews in the existing opinion summary data set are positive, current opinion summarization approaches are hesitant to generate negative summaries given the input of negative texts. To address such sentiment bias, a direct approach without the reliance on a specific structure is…

Cited by 0SourcePDFScholar
2025

LLM-PySC2: Starcraft II learning environment for Large Language Models

NeurIPS 2025poster

The tremendous potential has been demonstrated by large language models (LLMs) in intelligent decision-making problems, with unprecedented capabilities shown across diverse applications ranging from gaming AI systems to complex strategic planning frameworks. However, the StarCraft II platform, which…

Cited by 0SourcecodeScholar
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

MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception

CVPR 2025poster

Advanced driver assistance systems require a comprehensive understanding of the driver's mental/physical state and traffic context but existing works often neglect the potential benefits of joint learning between these tasks. This paper proposes MMTL-UniAD, a unified multi-modal multi-task learning…

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…

2025

World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model

ICCV 2025poster

End-to-end autonomous driving directly generates planning trajectories from raw sensor data, yet it typically relies on costly perception supervision to extract scene information. A critical research challenge arises: constructing an informative driving world model to enable perception annotation-fr…

2024

Exploring Adversarial Robustness of Deep State Space Models

NeurIPS 2024poster

Deep State Space Models (SSMs) have proven effective in numerous task scenarios but face significant security challenges due to Adversarial Perturbations (APs) in real-world deployments. Adversarial Training (AT) is a mainstream approach to enhancing Adversarial Robustness (AR) and has been validate…

2024

GaussianGrasper: 3D Language Gaussian Splatting for Open-Vocabulary Robotic Grasping

RA-L 2024

Constructing a 3D scene capable of accommodating open-ended language queries, is a pivotal pursuit in the domain of robotics, which facilitates robots in executing object manipulations based on human language directives. To achieve this, some research efforts have been dedicated to the development o

Cited by 102SourcecodeScholar
2024

ModWaveMLP: MLP-Based Mode Decomposition and Wavelet Denoising Model to Defeat Complex Structures in Traffic Forecasting

AAAI 2024technical

Traffic prediction is the core issue of Intelligent Transportation Systems. Recently, researchers have tended to use complex structures, such as transformer-based structures, for tasks such as traffic prediction. Notably, traffic data is simpler to process compared to text and images, which raises q…

2024

MonoOcc: Digging into Monocular Semantic Occupancy Prediction

ICRA 2024poster

Monocular Semantic Occupancy Prediction aims to infer the complete 3D geometry and semantic information of scenes from only 2D images. It has garnered significant attention, particularly due to its potential to enhance the 3D perception of autonomous vehicles. However, existing methods rely on a com…

Cited by 31SourcecodeScholar
2024

Opinions Are Not Always Positive: Debiasing Opinion Summarization with Model-Specific and Model-Agnostic Methods

COLING 2024main

As in the existing opinion summary data set, more than 70% are positive texts, the current opinion summarization approaches are reluctant to generate the negative opinion summary given the input of negative opinions. To address such sentiment bias, two approaches are proposed through two perspective…

Cited by 1SourcePDFScholar
2024

P-MapNet: Far-Seeing Map Generator Enhanced by Both SDMap and HDMap Priors

RA-L 2024

Autonomous vehicles are gradually entering city roads today, with the help of high-definition maps (HDMaps). However, the reliance on HDMaps prevents autonomous vehicles from stepping into regions without this expensive digital infrastructure. This fact drives many researchers to study online HDMap

Cited by 62SourceScholar
2024

PECR: Parameter-Efficient Transfer Learning with Cross-Modal Representation Learning for Remote Sensing Visual Question Answering

ICASSP 2024accepted

Remote sensing (RS) visual question answering (VQA) aims to provide accurate answers to questions related to RS images. Transformer-based models have gradually become popular to solve RS VQA tasks. Due to the ever-growing model size, full-parameter training of the model becomes prohibitively costly.…

Cited by 0SourceScholar
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…

2023

3D Implicit Transporter for Temporally Consistent Keypoint Discovery

ICCV 2023oral

Keypoint-based representation has proven advantageous in various visual and robotic tasks. However, the existing 2D and 3D methods for detecting keypoints mainly rely on geometric consistency to achieve spatial alignment, neglecting temporal consistency. To address this issue, the Transporter method…

Cited by 16PDFcodeScholar
2023

ADAPT: Action-aware Driving Caption Transformer

ICRA 2023poster

End-to-end autonomous driving has great potential in the transportation industry. However, the lack of transparency and interpretability of the automatic decision-making process hinders its industrial adoption in practice. There have been some early attempts to use attention maps or cost volume for…

Cited by 90SourcecodeScholar
2023

Anytime-Competitive Reinforcement Learning with Policy Prior

NeurIPS 2023poster

This paper studies the problem of Anytime-Competitive Markov Decision Process (A-CMDP). Existing works on Constrained Markov Decision Processes (CMDPs) aim to optimize the expected reward while constraining the expected cost over random dynamics, but the cost in a specific episode can still be unsat…

Cited by 2SourcePDFScholar
2023

DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection

ICCV 2023poster

In this paper, we study the problem of semi-supervised 3D object detection, which is of great importance considering the high annotation cost for cluttered 3D indoor scenes. We resort to the robust and principled framework of self-teaching, which has triggered notable progress for semi-supervised le…

Cited by 18PDFcodeScholar
2023

From Semi-supervised to Omni-supervised Room Layout Estimation Using Point Clouds

ICRA 2023poster

Room layout estimation is a long-existing robotic vision task that benefits both environment sensing and motion planning. However, layout estimation using point clouds (PCs) still suffers from data scarcity due to annotation difficulty. As such, we address the semi-supervised setting of this task ba…

Cited by 20SourcecodeScholar
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
2023

LATITUDE: Robotic Global Localization with Truncated Dynamic Low-pass Filter in City-scale NeRF

ICRA 2023poster

Neural Radiance Fields (NeRFs) have made great success in representing complex 3D scenes with high-resolution details and efficient memory. Nevertheless, current NeRF - based pose estimators have no initial pose prediction and are prone to local optima during optimization. In this paper, we present…

Cited by 43SourcecodeScholar
2023

LODE: Locally Conditioned Eikonal Implicit Scene Completion from Sparse LiDAR

ICRA 2023poster

Scene completion refers to obtaining dense scene representation from an incomplete perception of complex 3D scenes. This helps robots detect multi-scale obstacles and analyse object occlusions in scenarios such as autonomous driving. Recent advances show that implicit representation learning can be…

Cited by 30SourcecodeScholar
2023

Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees

ICML 2023poster

Many problems, such as online ad display, can be formulated as online bipartite matching. The crucial challenge lies in the nature of sequentially-revealed online item information, based on which we make irreversible matching decisions at each step. While numerous expert online algorithms have been…

2023

Robust Learning for Smoothed Online Convex Optimization with Feedback Delay

NeurIPS 2023poster

We study a general form of Smoothed Online Convex Optimization, a.k.a. SOCO, including multi-step switching costs and feedback delay. We propose a novel machine learning (ML) augmented online algorithm, Robustness-Constrained Learning (RCL), which combines untrusted ML predictions with a trusted exp…

Cited by 4SourcePDFScholar
2023

STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation

ICRA 2023poster

Self-supervised depth estimation draws a lot of attention recently as it can promote the 3D sensing capa-bilities of self-driving vehicles. However, it intrinsically relies upon the photometric consistency assumption, which hardly holds during nighttime. Although various supervised night-time image…

Cited by 49SourcecodeScholar
2023

Unsupervised Road Anomaly Detection with Language Anchors

ICRA 2023poster

Road anomaly detection is critical to safe autonomous driving, because current road scene understanding models are usually trained in a closed-set manner and fail to identify unknown objects. What's worse, it is difficult, if not impossible, to collect a large-scale dataset with anomaly annotations.…

Cited by 23SourcecodeScholar
2022

Constrained Update Projection Approach to Safe Policy Optimization

NeurIPS 2022accept

Safe reinforcement learning (RL) studies problems where an intelligent agent has to not only maximize reward but also avoid exploring unsafe areas. In this study, we propose CUP, a novel policy optimization method based on Constrained Update Projection framework that enjoys rigorous safety guarantee…

2022

Graph Masked Autoencoder Enhanced Predictor for Neural Architecture Search

IJCAI 2022poster

Performance estimation of neural architecture is a crucial component of neural architecture search (NAS). Meanwhile, neural predictor is a current mainstream performance estimation method. However, it is a challenging task to train the predictor with few architecture evaluations for efficient NAS. I…

2022

Policy Optimization with Stochastic Mirror Descent

AAAI 2022technical

Improving sample efficiency has been a longstanding goal in reinforcement learning. This paper proposes VRMPO algorithm: a sample efficient policy gradient method with stochastic mirror descent. In VRMPO, a novel variance-reduced policy gradient estimator is presented to improve sample efficiency. W…

Cited by 40SourcePDFScholar
2022

TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation

NeurIPS 2022accept

Current referring expression comprehension algorithms can effectively detect or segment objects indicated by nouns, but how to understand verb reference is still under-explored. As such, we study the challenging problem of task oriented detection, which aims to find objects that best afford an actio…

2022

Universal Conditional Masked Language Pre-training for Neural Machine Translation

ACL 2022long

Pre-trained sequence-to-sequence models have significantly improved Neural Machine Translation (NMT). Different from prior works where pre-trained models usually adopt an unidirectional decoder, this paper demonstrates that pre-training a sequence-to-sequence model but with a bidirectional decoder c…

2021

ACT: an Attentive Convolutional Transformer for Efficient Text Classification

AAAI 2021technical

Recently, Transformer has been demonstrating promising performance in many NLP tasks and showing a trend of replacing Recurrent Neural Network (RNN). Meanwhile, less attention is drawn to Convolutional Neural Network (CNN) due to its weak ability in capturing sequential and long-distance dependencie…

Cited by 56SourcePDFScholar
2021

CARE: Commonsense-Aware Emotional Response Generation with Latent Concepts

AAAI 2021technical

Rationality and emotion are two fundamental elements of humans. Endowing agents with rationality and emotion has been one of the major milestones in AI. However, in the field of conversational AI, most existing models only specialize in one aspect and neglect the other, which often leads to dull or…

2021

On Convergence of Gradient Expected Sarsa(λ)

AAAI 2021technical

We study the convergence of Expected Sarsa(λ) with function approximation. We show that with off-line es- timate (multi-step bootstrapping) to ExpectedSarsa(λ) is unstable for off-policy learning. Furthermore, based on convex-concave saddle-point framework, we propose a con- vergent Gradient Expecte…

Cited by 4SourcePDFScholar
2020

DIDFuse: Deep Image Decomposition for Infrared and Visible Image Fusion

IJCAI 2020poster

Infrared and visible image fusion, a hot topic in the field of image processing, aims at obtaining fused images keeping the advantages of source images. This paper proposes a novel auto-encoder (AE) based fusion network. The core idea is that the encoder decomposes an image into background and detai…

2020

Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry

ECCV 2020poster

Epipolar constraints are at the core of feature matching and depth estimation in current multi-person multi-camera 3D human pose estimation methods. Despite the satisfactory performance of this formulation in sparser crowd scenes, its effectiveness is frequently challenged under denser crowd circums…