3 papers
cs.CV2026
VL-DPO: Vision-Language-Guided Finetuning for Preference-Aligned Autonomous Driving
Zhefan Xu, Ghassen Jerfel, Marina Haliem +3
The rapid growth of autonomous driving datasets has enabled the scaling of powerful motion forecasting models. While large-scale pretraining provides strong performance, the standa…
cs.LG2024
EPO: Hierarchical LLM Agents with Environment Preference Optimization
Qi Zhao, Haotian Fu, Chen Sun +1
Long-horizon decision-making tasks present significant challenges for LLM-based agents due to the need for extensive planning over multiple steps. In this paper, we propose a hiera…
cs.CV2024
Vamos: Versatile Action Models for Video Understanding
Shijie Wang, Qi Zhao, Minh Quan Do +3
What makes good representations for video understanding, such as anticipating future activities, or answering video-conditioned questions? While earlier approaches focus on end-to-…