Related papers: Long-horizon Embodied Planning with Implicit Logic…

Retrieval-Augmented Generation (RAG) models frequently encounter hallucination phenomena when integrating external information with internal parametric knowledge. Empirical studies demonstrate that the disequilibrium between external…

An interactive robot framework accomplishes long-horizon task planning and can easily generalize to new goals and distinct tasks, even during execution. However, most traditional methods require predefined module design, making it hard to…

This paper presents a self-supervised Learning from Learned Hallucination (LfLH) method to learn fast and reactive motion planners for ground and aerial robots to navigate through highly constrained environments. The recent Learning from…

Multimodal large language models (MLLMs) have attracted increasing attention in the past few years, but they may still generate descriptions that include objects not present in the corresponding images, a phenomenon known as object…

Large Vision-Language Models (LVLMs) integrate image encoders with Large Language Models (LLMs) to process multi-modal inputs and perform complex visual tasks. However, they often generate hallucinations by describing non-existent objects…

Learning from long-horizon demonstrations with complex action sequences presents significant challenges for visual imitation learning, particularly in understanding temporal relationships of actions and spatial relationships between…

To break the context limits of large language models (LLMs) that bottleneck reasoning accuracy and efficiency, we propose the Thread Inference Model (TIM), a family of LLMs trained for recursive and decompositional problem solving, and…

Multimodal Large Language Models (MLLMs) have shown impressive reasoning abilities and general intelligence in various domains. It inspires researchers to train end-to-end MLLMs or utilize large models to generate policies with…

Goal-conditioned hierarchical reinforcement learning (HRL) decomposes complex reaching tasks into a sequence of simple subgoal-conditioned tasks, showing significant promise for addressing long-horizon planning in large-scale environments.…

Language models (LMs) have demonstrated their capability in possessing commonsense knowledge of the physical world, a crucial aspect of performing tasks in everyday life. However, it remains unclear **whether LMs have the capacity to…

In the realm of data-driven AI technology, the application of open-source large language models (LLMs) in robotic task planning represents a significant milestone. Recent robotic task planning methods based on open-source LLMs typically…

Current methods in training and benchmarking vision models exhibit an over-reliance on passive, curated datasets. Although models trained on these datasets have shown strong performance in a wide variety of tasks such as classification,…

Large Language Models (LLMs) have shown promise in solving natural language-described planning tasks, but their direct use often leads to inconsistent reasoning and hallucination. While hybrid LLM-symbolic planning pipelines have emerged as…

Language model (LM)-based agents have demonstrated promising capabilities in automating complex tasks from natural language instructions, yet they continue to struggle with long-horizon planning and reasoning. To address this, we propose an…

Learning from Hallucination (LfH) is a recent machine learning paradigm for autonomous navigation, which uses training data collected in completely safe environments and adds numerous imaginary obstacles to make the environment densely…

Large language model (LLM)-based agents have demonstrated remarkable capabilities in decision-making tasks, but struggle significantly with complex, long-horizon planning scenarios. This arises from their lack of macroscopic guidance,…

Large Vision-Language Models (VLMs) have achieved remarkable success across diverse multimodal tasks but remain vulnerable to hallucinations rooted in inherent language bias. Despite recent progress, existing hallucination mitigation…

Despite growing interest in active inference for robotic control, its application to complex, long-horizon tasks remains untested. We address this gap by introducing a fully hierarchical active inference architecture for goal-directed…

Recent advances in large language models (LLMs) have enabled agents to autonomously execute complex, long-horizon tasks, yet planning remains a primary bottleneck for reliable task execution. Existing methods typically fall into two…

Vision-Language Models (VLMs) have made significant strides in static image understanding but continue to face critical hurdles in spatiotemporal reasoning. A major bottleneck is "multi-image reasoning hallucination", where a massive…