Direct Preference Optimization-Enhanced Multi-Guided Diffusion Model for Traffic Scenario Generation
Diffusion-based models are recognized for their effectiveness in using real-world driving data to generate realistic and diverse traffic scenarios. These models employ guided sampling to incorporate specific traffic preferences and enhance scenario realism. However, guiding the sampling process to conform to traffic rules and preferences can result in deviations from real-world traffic priors and potentially leading to unrealistic behaviors. To address this challenge, we introduce a multi-guided diffusion model that utilizes a novel training strategy to closely adhere to traffic priors, even when employing various combinations of guides. This model adopts a multi-task learning framework, enabling a single diffusion model to process various guide inputs. For increased guided sampling precision, our model is fine-tuned using the Direct Preference Optimization (DPO) algorithm. This algorithm optimizes preferences based on guide scores, effectively navigating the complexities and challenges associated with the expensive and often non-differentiable gradient calculations during the guided sampling fine-tuning process. Evaluated using the nuScenes dataset our model provides a strong baseline for balancing realism, diversity and controllability in the traffic scenario generation.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityMulti-Task LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Reasoning Matters: Mitigate Hallucination in Multimodal Large Reasoning Models via Reasoning-Conditioned Preference Optimization
Multimodal Large Reasoning Models introduce the reasoning paradigm, demonstrating strong capabilities on complex vision-language tasks. However, they still suffer from severe hallucinations. Existing training-based metho…
Multimodal ReasoningAnswer GenerationImproving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization
LLMs have shown immense potential for code translation, yet they often struggle to ensure both syntactic correctness and semantic consistency. While preference-based learning offers a promising alignment strategy, it is …
Contrastive LearningCode TranslationPreference-Guided Diffusion for Multi-Objective Offline Optimization
Offline multi-objective optimization aims to identify Pareto-optimal solutions given a dataset of designs and their objective values. In this work, we propose a preference-guided diffusion model that generates Pareto-opt…
DiversityPEA-DPO: Perception-Enhanced Alignment Direct Preference Optimization for MLLMs Alignment
Direct Preference Optimization (DPO) has emerged as an effective approach for aligning large language models (LLMs) with human preferences. However, its adaptation to multimodal settings remains unexplored. Through repre…
Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization
Iterative preference optimization has recently become one of the de-facto training paradigms for large language models (LLMs), but the performance is still underwhelming due to too much noisy preference data yielded in t…