相关论文: In-Context Planning with Latent Temporal Abstracti…

We prove under practical assumptions that Rotary Positional Embedding (RoPE) introduces an intrinsic distance-dependent bias in attention scores that limits RoPE's ability to model long-context. RoPE extension methods may alleviate this…

Planning - the ability to analyze the structure of a problem in the large and decompose it into interrelated subproblems - is a hallmark of human intelligence. While deep reinforcement learning (RL) has shown great promise for solving…

General-purpose robots require diverse repertoires of behaviors to complete challenging tasks in real-world unstructured environments. To address this issue, goal-conditioned reinforcement learning aims to acquire policies that can reach…

Informative path planning (IPP) is an important planning paradigm for various real-world robotic applications such as environment monitoring. IPP involves planning a path that can learn an accurate belief of the quantity of interest, while…

Sequences of interdependent geometric constraints are central to many multi-agent Task and Motion Planning (TAMP) problems. However, existing methods for handling such constraint sequences struggle with partially ordered tasks and dynamic…

Modern learning systems increasingly rely on amortized learning - the idea of reusing computation or inductive biases shared across tasks to enable rapid generalization to novel problems. This principle spans a range of approaches,…

Tabular foundation models have shown strong performance across various tabular learning tasks via in-context learning, offering robust generalization without any downstream finetuning. However, their inference-time costs remain high,…

Random delays weaken the temporal correspondence between actions and subsequent state feedback, making it difficult for agents to identify the true propagation process of action effects. In cross-task scenarios, changes in task objectives…

Goal-conditioned planning benefits from learned low-dimensional representations of rich observations. While compact latent representations typically learned from variational autoencoders or inverse dynamics enable goal-conditioned decision…

In-context learning is a surprising and important phenomenon that emerged when modern language models were scaled to billions of learned parameters. Without modifying a large language model's weights, it can be tuned to perform various…

This work studies offline Reinforcement Learning (RL) in a class of non-Markovian environments called Regular Decision Processes (RDPs). In RDPs, the unknown dependency of future observations and rewards from the past interactions can be…

We present an approach for Task-Motion Planning (TMP) using Iterative Deepened AND/OR Graph Networks (TMP-IDAN) that uses an AND/OR graph network based novel abstraction for compactly representing the task-level states and actions. While…

Recent progress in imitation learning has been enabled by policy architectures that scale to complex visuomotor tasks, multimodal distributions, and large datasets. However, these methods often rely on learning from large amount of expert…

We introduce an algorithm for model-based hierarchical reinforcement learning to acquire self-contained transition and reward models suitable for probabilistic planning at multiple levels of abstraction. We call this framework Planning with…

We consider manipulation problems in constrained and cluttered settings, which require several regrasps at unknown locations. We propose to inform an optimization-based task and motion planning (TAMP) solver with possible regrasp areas and…

Modern large vision-language models (LVLMs) convert each input image into a large set of tokens that far outnumber the text tokens. Although this improves visual perception, it also introduces severe image token redundancy. Because image…

In this paper, we propose a novel approach for agent motion prediction in cluttered environments. One of the main challenges in predicting agent motion is accounting for location and context-specific information. Our main contribution is…

Generalist Vision-Language-Action models are currently hindered by the scarcity of robotic data compared to the abundance of human video demonstrations. Existing Latent Action Models attempt to leverage video data but often suffer from…

In this paper, we propose Text-Aware Pre-training (TAP) for Text-VQA and Text-Caption tasks. These two tasks aim at reading and understanding scene text in images for question answering and image caption generation, respectively. In…

Neural implicit mapping has emerged as a powerful paradigm for robotic navigation and scene understanding. However, real-world robotic deployment requires continual adaptation to changing environments under strict memory and computation…