相关论文: Post-Training and Test-Time Scaling of Generative …

With the rapid advancement of large language models and vision-language models, employing large models as Web Agents has become essential for automated web interaction. However, training Web Agents with reinforcement learning faces critical…

We propose the use of latent space generative world models to address the covariate shift problem in autonomous driving. A world model is a neural network capable of predicting an agent's next state given past states and actions. By…

In contemporary autonomous driving testing, virtual simulation has become an important approach due to its efficiency and cost effectiveness. However, existing methods usually rely on reinforcement learning to generate risky scenarios,…

Unsupervised neural combinatorial optimization (NCO) enables learning powerful solvers without access to ground-truth solutions. Existing approaches fall into two disjoint paradigms: models trained for generalization across instances, and…

Deep reinforcement learning (DRL) has been demonstrated to be effective for several complex decision-making applications such as autonomous driving and robotics. However, DRL is notoriously limited by its high sample complexity and its lack…

Post-training has become effective for high-level generation, but its role in low-level vision remains underexplored. Existing image restoration methods often rely on fixed pixel-wise fitting to ground-truth images, which can lead to…

Accurately simulating diverse behaviors of heterogeneous agents in various scenarios is fundamental to autonomous driving simulation. This task is challenging due to the multi-modality of behavior distribution, the high-dimensionality of…

In spite of remarkable progress in deep latent variable generative modeling, training still remains a challenge due to a combination of optimization and generalization issues. In practice, a combination of heuristic algorithms (such as…

When learning to behave in a stochastic environment where safety is critical, such as driving a vehicle in traffic, it is natural for human drivers to plan fallback strategies as a backup to use if ever there is an unexpected change in the…

Reinforcement learning is commonly associated with training of reward-maximizing (or cost-minimizing) agents, in other words, controllers. It can be applied in model-free or model-based fashion, using a priori or online collected system…

Autoregressive models have shown superior performance and efficiency in image generation, but remain constrained by high computational costs and prolonged training times in video generation. In this study, we explore methods to accelerate…

Reinforcement learning (RL) has garnered increasing attention in text-to-image (T2I) generation. However, most existing RL approaches are tailored to either diffusion models or autoregressive models, overlooking an important alternative:…

This paper introduces TempSamp-R1, a new reinforcement fine-tuning framework designed to improve the effectiveness of adapting multimodal large language models (MLLMs) to video temporal grounding tasks. We reveal that existing reinforcement…

Vision-Language-Action (VLA) models show strong potential for general-purpose robotic manipulation, yet their closed-loop reliability often degrades under local deployment conditions. Existing evaluations typically treat test episodes as…

Learning robust driving policies from large-scale, real-world datasets is a central challenge in autonomous driving, as online data collection is often unsafe and impractical. While Behavioral Cloning (BC) offers a straightforward approach…

Model-based next state prediction and state value prediction are slow to converge. To address these challenges, we do the following: i) Instead of a neural network, we do model-based planning using a parallel memory retrieval system (which…

Most of the learning-based algorithms for bitrate adaptation are limited to offline learning, which inevitably suffers from the simulation-to-reality gap. Online learning can better adapt to dynamic real-time communication scenes but still…

Most modern approaches to quadruped locomotion focus on using Deep Reinforcement Learning (DRL) to learn policies from scratch, in an end-to-end manner. Such methods often fail to scale, as every new problem or application requires…

Combinatorial optimization problems involving multiple agents are notoriously challenging due to their NP-hard nature and the necessity for effective agent coordination. Despite advancements in learning-based methods, existing approaches…

Recent work on enhancing the reasoning abilities of large language models (LLMs) has introduced explicit length control as a means of constraining computational cost while preserving accuracy. However, existing approaches rely on…