AIConfPaper
← Search

Chun-Yi Lee

34 accepted papers

2026

Feasibility-Guided Planning Over Multi-Specialized Locomotion Policies

Ying-Sheng Luo, Lu-Ching Wang, Hanjaya Mandala, Yu-Lun Chou, Guilherme Henrique Galelli Christmann, Yu-Chung Chen +3
ICRA 2026poster

Planning over unstructured terrain presents a significant challenge in the field of legged robotics. Although recent works in reinforcement learning have yielded various locomotion strategies, planning over multiple experts remains a complex issue. Existing approaches encounter several constraints: …

Cited by 0Source ↗PDF ↗Scholar ↗
2026

The Lie We Tell: Correcting the Euclidean Fallacy in Vision Language Action Policies via Score Matching on Tangent Space

Bing-Cheng Chuang, I-Hsuan Chu, Bor Jiun Lin, Yang YuanFu, Min Sun, Chun-Yi Lee
ICML 2026poster

Diffusion-based Vision-Language-Action policies achieve remarkable success in robotic manipulation, yet commit a fundamental geometric error we term the \textbf{Euclidean Fallacy}: representing SE(3) poses as flat $\mathbb{R}^{12}$ vectors. This approximation induces (1) manifold drift violating SO(…

Cited by 0Source ↗Scholar ↗
2025

3D Gaussian Splatting with Grouped Uncertainty for Unconstrained Images

Hao-Yu Hou, Chia-Chi Hsu, Yu-Chen Huang, Mu-Yi Shen, Wei-Fang Sun, Cheng Sun +3
ICASSP 2025accepted

3D Gaussian Splatting (3DGS) [1] is a promising method for 3D reconstruction and novel view synthesis. However, training it with unconstrained images presents challenges due to transient objects that cause undesired floaters and ghosting artifacts. Although related works using Neural Radiance Fields…

Cited by 0Source ↗Scholar ↗
2025

A Key to Effective Multi-task Learning: Separate Query Selection for Task-Synergized Handling and Node Utilization

Shan-Ya Yang, Hao-Chung Cheng, Chien-Yao Wang, Jia-Ching Wang, Chun-Yi Lee
ICASSP 2025accepted

In the realm of computer vision, effectively handling multi-tasks simultaneously presents a challenge that necessitates innovative solutions. To better address multiple vision problems, we introduce SeTano, an integrated Graph Neural Network (GNN)-based framework. This framework comprises a Dynamic…

Cited by 0Source ↗Scholar ↗
2025

Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking

Chen-Hao Chao, Wei-Fang Sun, Hanwen Liang, Chun-Yi Lee, Rahul Krishnan
NeurIPS 2025poster

Masked diffusion models (MDM) are powerful generative models for discrete data that generate samples by progressively unmasking tokens in a sequence. Each token can take one of two states: masked or unmasked. We observe that token sequences often remain unchanged between consecutive sampling steps;…

Cited by 0Source ↗Scholar ↗
2025

EAMamba: Efficient All-Around Vision State Space Model for Image Restoration

Yu-Cheng Lin, Yu-Syuan Xu, Hao-Wei Chen, Hsien-Kai Kuo, Chun-Yi Lee
ICCV 2025poster

Image restoration is a key task in low-level computer vision that aims to reconstruct high-quality images from degraded inputs. The emergence of Vision Mamba, which draws inspiration from the advanced state space model Mamba, marks a significant advancement in this field. Vision Mamba demonstrates e…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling

Jia-Hua Lee, Bor-Jiun Lin, Wei-Fang Sun, Chun-Yi Lee
NeurIPS 2025spotlight

World models represent a promising approach for training reinforcement learning agents with significantly improved sample efficiency. While most world model methods primarily rely on sequences of discrete latent variables to model environment dynamics, this compression often neglects critical visual…

Cited by 0Source ↗code ↗Scholar ↗
2025

FROSS: Faster-Than-Real-Time Online 3D Semantic Scene Graph Generation from RGB-D Images

Hao-Yu Hou, Chun-Yi Lee, Motoharu Sonogashira, Yasutomo Kawanishi
ICCV 2025poster

The ability to abstract complex 3D environments into simplified and structured representations is crucial across various domains. 3D semantic scene graphs (SSGs) achieve this by representing objects as nodes and their interrelationships as edges, facilitating high-level scene understanding. Existing…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Retraining-free Merging of Sparse MoE via Hierarchical Clustering

I-Chun Chen, Hsu-Shen Liu, Wei-Fang Sun, Chen-Hao Chao, Yen-Chang Hsu, Chun-Yi Lee
ICML 2025poster

Sparse Mixture-of-Experts (SMoE) models represent a significant advancement in large language model (LLM) development through their efficient parameter utilization. These models achieve substantial performance improvements at reduced inference costs. However, the deployment of SMoE models faces cons…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Boosting Flow-based Generative Super-Resolution Models via Learned Prior

Li-Yuan Tsao, Yi-Chen Lo, Chia-Che Chang, Hao-Wei Chen, Roy Tseng, Chien Feng +1
CVPR 2024poster

Flow-based super-resolution (SR) models have demonstrated astonishing capabilities in generating high-quality images. However these methods encounter several challenges during image generation such as grid artifacts exploding inverses and suboptimal results due to a fixed sampling temperature. To ov…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2024

Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)

Tsu-Ching Hsiao, Hao-Wei Chen, Hsuan-Kung Yang, Chun-Yi Lee
CVPR 2024poster

Addressing pose ambiguity in 6D object pose estimation from single RGB images presents a significant challenge particularly due to object symmetries or occlusions. In response we introduce a novel score-based diffusion method applied to the SE(3) group marking the first application of diffusion mode…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2024

Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning

Chia-Cheng Chiang, Li-Cheng Lan, Wei-Fang Sun, Chien Feng, Cho-Jui Hsieh, Chun-Yi Lee
ICML 2024poster

In this paper, we focus on single-demonstration imitation learning (IL), a practical approach for real-world applications where acquiring multiple expert demonstrations is costly or infeasible and the ground truth reward function is not available. In contrast to typical IL settings with multiple dem…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

HGAP: Boosting Permutation Invariant and Permutation Equivariant in Multi-Agent Reinforcement Learning via Graph Attention Network

Bor-Jiun Lin, Chun-Yi Lee
ICML 2024poster

Graph representation has gained widespread application across various machine learning domains, attributed to its ability to discern correlations among input nodes. In the realm of Multi- agent Reinforcement Learning (MARL), agents are tasked with observing other entities within their environment to…

Cited by 1Source ↗PDF ↗Scholar ↗
2024

Language-Guided Pattern Formation for Swarm Robotics with Multi-Agent Reinforcement Learning

Hsu-Shen Liu, So Kuroki, Tadashi Kozuno, Wei-Fang Sun, Chun-Yi Lee
IROS 2024poster

This paper explores leveraging the vast knowledge encoded in Large Language Models (LLMs) to tackle pattern formation challenges for swarm robotics systems. A new framework, named LGPF (Language-Guided Pattern Formation), is proposed to address these challenges. The framework breaks down the pattern…

Cited by 2Source ↗Scholar ↗
2024

Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow

Chen-Hao Chao, Chien Feng, Wei-Fang Sun, Cheng-Kuang Lee, Simon See, Chun-Yi Lee
NeurIPS 2024poster

Existing Maximum-Entropy (MaxEnt) Reinforcement Learning (RL) methods for continuous action spaces are typically formulated based on actor-critic frameworks and optimized through alternating steps of policy evaluation and policy improvement. In the policy evaluation steps, the critic is updated to c…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2024

Reprojection Errors as Prompts for Efficient Scene Coordinate Regression

Ting-Ru Liu*, Hsuan-Kung Yang, Jou-Min Liu, Chun-Wei Huang, Tsung-Chih Chiang, Quan Kong +2
ECCV 2024poster

"Scene coordinate regression (SCR) methods have emerged as a promising area of research due to their potential for accurate visual localization. However, many existing SCR approaches train on samples from all image regions, including dynamic objects and texture-less areas. Utilizing these areas for…

Cited by 1Source ↗PDF ↗Scholar ↗
2024

Visual Forecasting as a Mid-level Representation for Avoidance

Hsuan-Kung Yang, Tsung-Chih Chiang, Ting-Ru Liu, Chun-Wei Huang, Jou-Min Liu, Chun-Yi Lee
IROS 2024poster

The challenge of navigation in environments with dynamic objects continues to be a central issue in the study of autonomous agents. While predictive methods hold promise, their reliance on precise state information makes them less practical for real-world implementation. This study presents visual f…

Cited by 0Source ↗Scholar ↗
2023

Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolution

Hao-Wei Chen, Yu-Syuan Xu, Min-Fong Hong, Yi-Min Tsai, Hsien-Kai Kuo, Chun-Yi Lee
CVPR 2023poster

Implicit neural representation demonstrates promising ability in representing images with arbitrary resolutions recently. In this paper, we present Local Implicit Transformer (LIT) that integrates attention mechanism and frequency encoding technique into local implicit image function. We design a cr…

Cited by 48Source ↗PDF ↗code ↗Scholar ↗
2023

Local Implicit Normalizing Flow for Arbitrary-Scale Image Super-Resolution

Jie-En Yao, Li-Yuan Tsao, Yi-Chen Lo, Roy Tseng, Chia-Che Chang, Chun-Yi Lee
CVPR 2023poster

Flow-based methods have demonstrated promising results in addressing the ill-posed nature of super-resolution (SR) by learning the distribution of high-resolution (HR) images with the normalizing flow. However, these methods can only perform a predefined fixed-scale SR, limiting their potential in r…

Cited by 40Source ↗PDF ↗code ↗Scholar ↗
2023

On Investigating the Conservative Property of Score-Based Generative Models

Chen-Hao Chao, Wei-Fang Sun, Bo-Wun Cheng, Chun-Yi Lee
ICML 2023poster

Existing Score-Based Models (SBMs) can be categorized into constrained SBMs (CSBMs) or unconstrained SBMs (USBMs) according to their parameterization approaches. CSBMs model probability density functions as Boltzmann distributions, and assign their predictions as the negative gradients of some scala…

Cited by 19Source ↗PDF ↗code ↗Scholar ↗
2023

Training Energy-Based Normalizing Flow with Score-Matching Objectives

Chen-Hao Chao, Wei-Fang Sun, Yen-Chang Hsu, Zsolt Kira, Chun-Yi Lee
NeurIPS 2023poster

In this paper, we establish a connection between the parameterization of flow-based and energy-based generative models, and present a new flow-based modeling approach called energy-based normalizing flow (EBFlow). We demonstrate that by optimizing EBFlow with score-matching objectives, the computati…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2022

Denoising Likelihood Score Matching for Conditional Score-based Data Generation

Chen-Hao Chao, Wei-Fang Sun, Bo-Wun Cheng, Yi-Chen Lo, Chia-Che Chang, Yu-Lun Liu +3
ICLR 2022poster

Many existing conditional score-based data generation methods utilize Bayes' theorem to decompose the gradients of a log posterior density into a mixture of scores. These methods facilitate the training procedure of conditional score models, as a mixture of scores can be separately estimated using a…

Cited by 44Source ↗PDF ↗code ↗Scholar ↗
2022

Investigation of Factorized Optical Flows as Mid-Level Representations

Hsuan-Kung Yang, Tsu-Ching Hsiao, Ting-Hsuan Liao, Hsu-Shen Liu, Li-Yuan Tsao, Tzu-Wen Wang +4
IROS 2022poster

In this paper, we introduce a new concept of incorporating factorized flow maps as mid-level representations, for bridging the perception and the control modules in modular learning based robotic frameworks. To investigate the advantages of factorized flow maps and examine their interplay with the o…

Cited by 2Source ↗Scholar ↗
2022

S2F2: Single-Stage Flow Forecasting for Future Multiple Trajectories Prediction

Yu-Wen Chen, Hsuan-Kung Yang, Chu-Chi Chiu, Chun-Yi Lee
ECCV 2022poster

"In this work, we present a single-stage framework, named S2F2, for forecasting multiple human trajectories from raw video images by predicting future optical flows. S2F2 differs from the previous two-stage approaches in that it performs detection, Re-ID, and forecasting of multiple pedestrians at t…

Cited by 4Source ↗PDF ↗Scholar ↗
2021

DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning

Wei-Fang Sun, Cheng-Kuang Lee, Chun-Yi Lee
ICML 2021spotlight

In fully cooperative multi-agent reinforcement learning (MARL) settings, the environments are highly stochastic due to the partial observability of each agent and the continuously changing policies of the other agents. To address the above issues, we integrate distributional RL and value function fa…

Cited by 61Source ↗PDF ↗code ↗Scholar ↗
2021

Reducing the Deployment-Time Inference Control Costs of Deep Reinforcement Learning Agents via an Asymmetric Architecture

Chin-Jui Chang, Yu-Wei Chu, Chao-Hsien Ting, Hao-Kang Liu, Zhang-Wei Hong, Chun-Yi Lee
ICRA 2021poster

Deep reinforcement learning (DRL) has been demonstrated to provide promising results in several challenging decision making and control tasks. However, the required inference costs of deep neural networks (DNNs) could prevent DRL from being applied to mobile robots which cannot afford high energy-co…

Cited by 2Source ↗Scholar ↗
2019

Adversarial Active Exploration for Inverse Dynamics Model Learning

Zhang-Wei Hong, Tsu-Jui Fu, Tzu-Yun Shann, Chun-Yi Lee
CoRL 2019

We present an adversarial active exploration for inverse dynamics model learning, a simple yet effective learning scheme that incentivizes exploration in an environment without any human intervention. Our framework consists of a deep reinforcement learning (DRL) agent and an inverse dynamics model c

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2018

Diversity-Driven Exploration Strategy for Deep Reinforcement Learning

Zhang-Wei Hong, Tzu-Yun Shann, Shih-Yang Su, Yi-Hsiang Chang, Tsu-Jui Fu, Chun-Yi Lee
NeurIPS 2018poster

Efficient exploration remains a challenging research problem in reinforcement learning, especially when an environment contains large state spaces, deceptive local optima, or sparse rewards. To tackle this problem, we present a diversity-driven approach for exploration, which can be easily combined…

Cited by 153Source ↗PDF ↗code ↗Scholar ↗