Related papers: FATE: Closed-Loop Feasibility-Aware Task Generatio…

Training robotic policies directly in the real world is expensive and unscalable. Although generative simulation enables large-scale data synthesis, current approaches often fail to generate logically coherent long-horizon tasks and…

Task embedding, a meta-learning technique that captures task-specific information, has gained popularity, especially in areas such as multi-task learning, model editing, and interpretability. However, it faces challenges with the emergence…

Large Language Models (LLMs) exhibit remarkable capabilities in the hierarchical decomposition of complex tasks through semantic reasoning. However, their application in embodied systems faces challenges in ensuring reliable execution of…

Large language model (LLM) applications are increasingly executed as heterogeneous multi-stage workflows rather than isolated inference calls. In these workflow directed acyclic graphs (DAGs), scheduling decisions affect not only the…

Large Language Models (LLMs) have proven immensely beneficial in education by capturing vast amounts of literature-based information, allowing them to generate context without relying on external sources. In this paper, we propose a…

Due to the difficulty of acquiring extensive real-world data, robot simulation has become crucial for parallel training and sim-to-real transfer, highlighting the importance of scalable simulated robotic tasks. Foundation models have…

This paper aims to develop a framework that enables a robot to execute tasks based on visual information, in response to natural language instructions for Fetch-and-Carry with Object Grounding (FCOG) tasks. Although there have been many…

Robotic manipulation in unstructured environments requires systems that can generalize across diverse tasks while maintaining robust and reliable performance. We introduce {GVF-TAPE}, a closed-loop framework that combines generative visual…

Recent advances in large language models (LLMs) have demonstrated impressive capabilities in formal theorem proving, particularly on contest-based mathematical benchmarks like the IMO. However, these contests do not reflect the depth,…

Embodied Artificial Intelligence (AI) has recently attracted significant attention as it bridges AI with the physical world. Modern embodied AI systems often combine a Large Language Model (LLM)-based planner for high-level task planning…

Large Language Models (LLMs) have shown great promise in tool-making, yet existing frameworks often struggle to efficiently construct reliable toolsets and are limited to single-task settings. To address these challenges, we propose GATE…

Recent work has shown that inference-time reasoning and reflection can improve text-to-image generation without retraining. However, existing approaches often rely on implicit, holistic critiques or unconstrained prompt rewrites, making…

Vision-language models (VLMs) have shown remarkable general capabilities, yet embodied agents built on them fail at complex tasks, often skipping critical steps, proposing invalid actions, and repeating mistakes. These failures arise from a…

Learning long-horizon embodied behaviors from synthetic data remains challenging because generated scenes are often physically implausible, language-driven programs frequently "succeed" without satisfying task semantics, and high-level…

In recent years, the Robotics field has initiated several efforts toward building generalist robot policies through large-scale multi-task Behavior Cloning. However, direct deployments of these policies have led to unsatisfactory…

Tool-using LLM agents fail through trajectories rather than only final responses, as they may execute unsafe tool calls, follow injected instructions, comply with harmful requests, or over-refuse benign tasks despite producing a seemingly…

Reinforcement learning (RL) is a promising approach for robotic manipulation, but it can suffer from low sample efficiency and requires extensive exploration of large state-action spaces. Recent methods leverage the commonsense knowledge…

We introduce Adaptive Procedural Task Generation (APT-Gen), an approach to progressively generate a sequence of tasks as curricula to facilitate reinforcement learning in hard-exploration problems. At the heart of our approach, a task…

Multi-hop QA benchmarks frequently reward Large Language Models (LLMs) for spurious correctness, masking ungrounded or flawed reasoning steps. To shift toward rigorous reasoning, we propose SAFE, a dynamic benchmarking framework that…

As large language models (LLMs) advance, it becomes more challenging to reliably evaluate their output due to the high costs of human evaluation. To make progress towards better LLM autoraters, we introduce FLAMe, a family of Foundational…