Related papers: Plan, Eliminate, and Track -- Language Models are …
Recent breakthroughs of pretrained language models have shown the effectiveness of self-supervised learning for a wide range of natural language processing (NLP) tasks. In addition to standard syntactic and semantic NLP tasks, pretrained…
Recently, pre-trained language models (LMs) have achieved strong performance when fine-tuned on difficult benchmarks like SuperGLUE. However, performance can suffer when there are very few labeled examples available for fine-tuning. Pattern…
We propose a method that enables large language models (LLMs) to control embodied agents through the generation of control policies that directly map continuous observation vectors to continuous action vectors. At the outset, the LLMs…
Large Action Models (LAMs) for AI Agents offer incredible potential but face challenges due to the need for high-quality training data, especially for multi-steps tasks that involve planning, executing tool calls, and responding to…
Large Transformer-based language models such as BERT have led to broad performance improvements on many NLP tasks. Domain-specific variants of these models have demonstrated excellent performance on a variety of specialised tasks. In legal…
For effective human-robot interaction, robots need to understand, plan, and execute complex, long-horizon tasks described by natural language. Recent advances in large language models (LLMs) have shown promise for translating natural…
Robust coordination is critical for effective decision-making in multi-agent systems, especially under partial observability. A central question in Multi-Agent Reinforcement Learning (MARL) is whether to engineer communication protocols or…
Coordinating heterogeneous robot teams from free-form natural-language instructions is hard. Language-only planners struggle with long-horizon coordination and hallucination, while purely formal methods require closed-world models. We…
As robotic systems become increasingly integrated into complex real-world environments, there is a growing need for approaches that enable robots to understand and act upon natural language instructions without relying on extensive…
Large language models (LLMs) have recently demonstrated the potential in acting as autonomous agents for sequential decision-making tasks. However, most existing methods either take actions greedily without planning or rely on static plans…
Large Language Models (LLMs) have opened transformative possibilities for human-robot collaboration. However, enabling real-time collaboration requires both low latency and robust reasoning, and most LLMs suffer from high latency. To…
Pretrained language models have become the standard approach for many NLP tasks due to strong performance, but they are very expensive to train. We propose a simple and efficient learning framework, TLM, that does not rely on large-scale…
Autonomous agents, which perceive environments and take actions to achieve goals, have become increasingly feasible with the advancements in large language models (LLMs). However, current powerful agents often depend on sophisticated prompt…
Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown the capability to generalize to unseen tasks. Previous work has shown that scaling the number of training…
Large Language Models (LLMs) have shown remarkable performance in various basic natural language tasks. For completing the complex task, we still need a plan for the task to guide LLMs to generate the specific solutions step by step. LLMs…
Object-goal navigation is a crucial engineering task for the community of embodied navigation; it involves navigating to an instance of a specified object category within unseen environments. Although extensive investigations have been…
Inspired by the insights in cognitive science with respect to human memory and reasoning mechanism, a novel evolvable LLM-based (Large Language Model) agent framework is proposed as REMEMBERER. By equipping the LLM with a long-term…
The control of robots for manipulation tasks generally relies on visual input. Recent advances in vision-language models (VLMs) enable the use of natural language instructions to condition visual input and control robots in a wider range of…
Robotic assembly tasks remain an open challenge due to their long horizon nature and complex part relations. Behavior trees (BTs) are increasingly used in robot task planning for their modularity and flexibility, but creating them manually…
Large language models (LLMs) have achieved success in acting as agents, which interact with environments through tools such as search engines. However, LLMs are optimized for language generation instead of tool use during training or…