Related papers: Driving Beyond Privilege: Distilling Dense-Reward …

Toddlers evolve from free exploration with sparse feedback to exploiting prior experiences for goal-directed learning with denser rewards. Drawing inspiration from this Toddler-Inspired Reward Transition, we set out to explore the…

Despite significant advancements in the field of multi-agent navigation, agents still lack the sophistication and intelligence that humans exhibit in multi-agent settings. In this paper, we propose a framework for learning a human-like…

Diffusion and flow models achieve State-Of-The-Art (SOTA) generative performance, yet many practically important behaviors such as fine-grained prompt fidelity, compositional correctness, and text rendering are weakly specified by score or…

Distillation-based learning boosts the performance of the miniaturized neural network based on the hypothesis that the representation of a teacher model can be used as structured and relatively weak supervision, and thus would be easily…

We explore the methodology and theory of reward-directed generation via conditional diffusion models. Directed generation aims to generate samples with desired properties as measured by a reward function, which has broad applications in…

Autonomous driving is an important and safety-critical task, and recent advances in LLMs/VLMs have opened new possibilities for reasoning and planning in this domain. However, large models demand substantial GPU memory and exhibit high…

Diffusion models generate high-quality images through progressive denoising but are computationally intensive due to large model sizes and repeated sampling. Knowledge distillation, which transfers knowledge from a complex teacher to a…

Intelligent agents must pursue their goals in complex environments with partial information and often limited computational capacity. Reinforcement learning methods have achieved great success by creating agents that optimize engineered…

Vision-Language-Action (VLA) models have demonstrated potential in autonomous driving. However, two critical challenges hinder their development: (1) Existing VLA architectures are typically based on imitation learning in open-loop setup…

We address the problem of fine-tuning diffusion models for reward-guided generation in biomolecular design. While diffusion models have proven highly effective in modeling complex, high-dimensional data distributions, real-world…

Knowledge distillation is used, in generative language modeling, to train a smaller student model using the help of a larger teacher model, resulting in improved capabilities for the student model. In this paper, we formulate a more general…

This work presents a case study of a learning-based approach for target driven map-less navigation. The underlying navigation model is an end-to-end neural network which is trained using a combination of expert demonstrations, imitation…

Traffic accident anticipation aims to accurately and promptly predict the occurrence of a future accident from dashcam videos, which is vital for a safety-guaranteed self-driving system. To encourage an early and accurate decision, existing…

Policy distillation, which transfers a teacher policy to a student policy has achieved great success in challenging tasks of deep reinforcement learning. This teacher-student framework requires a well-trained teacher model which is…

Deep reinforcement learning is an effective tool to learn robot control policies from scratch. However, these methods are notorious for the enormous amount of required training data which is prohibitively expensive to collect on real…

Deep search agents have emerged as a promising paradigm for addressing complex information-seeking tasks, but their training remains challenging due to sparse rewards, weak credit assignment, and limited labeled data. Self-play offers a…

Reinforcement learning (RL) shows great potential for optimizing multi-vehicle cooperative driving strategies through the state-action-reward feedback loop, but it still faces challenges such as low sample efficiency. This paper proposes a…

Diffusion probabilistic models have shown significant progress in video generation; however, their computational efficiency is limited by the large number of sampling steps required. Reducing sampling steps often compromises video quality…

We introduce DreamerAD, the first latent world model framework that enables efficient reinforcement learning for autonomous driving by compressing diffusion sampling from 100 steps to 1 - achieving 80x speedup while maintaining visual…

Real-world driving involves intricate interactions among vehicles navigating through dense traffic scenarios. Recent research focuses on enhancing the interaction awareness of autonomous vehicles to leverage these interactions in…