相关论文: Dynamic Horizon Value Estimation for Model-based R…

Dynamic portfolio optimization is the process of sequentially allocating wealth to a collection of assets in some consecutive trading periods, based on investors' return-risk profile. Automating this process with machine learning remains a…

Reinforcement learning from large-scale offline datasets provides us with the ability to learn policies without potentially unsafe or impractical exploration. Significant progress has been made in the past few years in dealing with the…

To accommodate rapid changes in the real world, the cognition system of humans is capable of continually learning concepts. On the contrary, conventional deep learning models lack this capability of preserving previously learned knowledge.…

Reinforcement learning algorithms can acquire policies for complex tasks autonomously. However, the number of samples required to learn a diverse set of skills can be prohibitively large. While meta-reinforcement learning methods have…

Real-time multi-view 3D reconstruction is a mission-critical application for key edge-native use cases, such as fire rescue, where timely and accurate 3D scene modeling enables situational awareness and informed decision-making. However,…

Time-aware data valuation enhances training efficiency and model robustness, as early detection of harmful samples could prevent months of wasted computation. However, existing methods rely on model retraining or convergence assumptions or…

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…

Image scoring is a crucial task in numerous real-world applications. To trust a model's judgment, understanding its rationale is essential. This paper proposes a novel training method for Vision Language Models (VLMs) to generate not only…

Planning is a powerful approach to reinforcement learning with several desirable properties. However, it requires a model of the world, which is not readily available in many real-life problems. In this paper, we propose to learn a world…

The rapid progress of multimodal large language models (MLLMs) calls for more reliable evaluation protocols. Existing static benchmarks suffer from the potential risk of data contamination and saturation, leading to inflated or misleading…

Video generative models are increasingly used as world models for robotics, where a model generates a future visual rollout conditioned on the current observation and task instruction, and an inverse dynamics model (IDM) converts the…

Residual-based adaptive strategies are widely used in scientific machine learning but remain largely heuristic. We introduce a unifying variational framework that formalizes these methods by integrating convex transformations of the…

Generative models such as diffusion have been employed as world models in offline reinforcement learning to generate synthetic data for more effective learning. Existing work either generates diffusion models one-time prior to training or…

Multi-scene reinforcement learning involves training the RL agent across multiple scenes / levels from the same task, and has become essential for many generalization applications. However, the inclusion of multiple scenes leads to an…

Learning continuous control in high-dimensional sparse reward settings, such as robotic manipulation, is a challenging problem due to the number of samples often required to obtain accurate optimal value and policy estimates. While many…

Object detection in aerial imagery presents a significant challenge due to large scale variations among objects. This paper proposes an evolutionary reinforcement learning agent, integrated within a coarse-to-fine object detection…

Recent methods for reinforcement learning from images use auxiliary tasks to learn image features that are used by the agent's policy or Q-function. In particular, methods based on contrastive learning that induce linearity of the latent…

Data augmentation has been shown to effectively improve the performance of multimodal machine learning models. This paper introduces a generative model for data augmentation by leveraging the correlations among multiple modalities.…

Debiased inference for high-dimensional regression models has received substantial recent attention to ensure regularized estimators have valid inference. All existing methods focus on achieving Neyman orthogonality through explicitly…

Prompt-based continual learning provides a rehearsal-free solution by tuning small sets of parameters while keeping pre-trained models frozen. To meet the complex demands of sequential tasks, it is crucial to integrate task-specific…