Related papers: Autoregressive Action Sequence Learning for Roboti…

Despite the success of sequence-to-sequence approaches in automatic speech recognition (ASR) systems, the models still suffer from several problems, mainly due to the mismatch between the training and inference conditions. In the…

Continuous visual autoregressive (AR) models have demonstrated promising performance in image generation. However, the heavy autoregressive inference burden imposes significant overhead. In Large Language Models (LLMs), speculative decoding…

Long-horizon robotic manipulation remains challenging for reinforcement learning (RL) because sparse rewards provide limited guidance for credit assignment. Practical policy improvement thus relies on richer intermediate supervision, such…

Work-in-Progress (WiP) prediction is critical for predictive process monitoring, enabling accurate anticipation of workload fluctuations and optimized operational planning. This paper proposes a retrieval-augmented, multi-agent framework…

Language agents have shown impressive problem-solving skills within defined settings and brief timelines. Yet, with the ever-evolving complexities of open-world simulations, there's a pressing need for agents that can flexibly adapt to…

This paper addresses the cooperative Multi-Vehicle Dynamic Pickup and Delivery Problem with Stochastic Requests (MVDPDPSR) and proposes an end-to-end centralized decision-making framework based on sequence-to-sequence, named Multi-Agent…

Vision-Language-Action systems follow instructions to execute multi-step tasks in multimodal environments. Recent VLA approaches typically rely on post-hoc correction mechanisms or operate under fixed task decompositions and alignment…

Reinforcement learning (RL) can be formulated as a sequence modeling problem, where models predict future actions based on historical state-action-reward sequences. Current approaches typically require long trajectory sequences to model the…

This paper presents a hybrid robot cognitive architecture, CRAM, that enables robot agents to accomplish everyday manipulation tasks. It addresses five key challenges that arise when carrying out everyday activities. These include (i) the…

Actions are more than just movements and trajectories: we cook to eat and we hold a cup to drink from it. A thorough understanding of videos requires going beyond appearance modeling and necessitates reasoning about the sequence of…

The goal of modern sequential recommender systems is often formulated in terms of next-item prediction. In this paper, we explore the applicability of generative transformer-based models for the Top-K sequential recommendation task, where…

To achieve general-purpose utility, we argue that robots must evolve from passive executors into active Information Retrieval users. In strictly zero-shot settings where no prior demonstrations exist, robots face a critical information gap,…

Autoregressive (AR) models are highly effective for image generation, yet their standard maximum-likelihood estimation training lacks direct optimization for sample quality and diversity. While reinforcement learning (RL) has been used to…

The subject of this paper is reinforcement learning. Policies are considered here that produce actions based on states and random elements autocorrelated in subsequent time instants. Consequently, an agent learns from experiments that are…

Autoregressive language models are constrained by their inherently sequential nature, generating one token at a time. This paradigm limits inference speed and parallelism, especially during later stages of generation when the direction and…

This paper addresses the challenge of human-guided navigation for mobile collaborative robots under simultaneous proximity regulation and safety constraints. We introduce Adaptive Reinforcement and Model Predictive Control Switching (ARMS),…

Autoregressive models (ARMs) currently hold state-of-the-art performance in likelihood-based modeling of image and audio data. Generally, neural network based ARMs are designed to allow fast inference, but sampling from these models is…

Autoregressive models, such as the GPT family, use a fixed order, usually left-to-right, to generate sequences. However, this is not a necessity. In this paper, we challenge this assumption and show that by simply adding a positional…

Rapid learning requires flexible representations to quickly adopt to new evidence. We develop a novel class of models called Attentive Recurrent Comparators (ARCs) that form representations of objects by cycling through them and making…

AI agents have become increasingly adept at complex tasks such as coding, reasoning, and multimodal understanding. However, building generalist systems requires moving beyond individual agents to collective inference -- a paradigm where…