English
Related papers

Related papers: Debugging code world models

200 papers

World models (WMs) demonstrate strong capabilities in prediction, generation, and planning tasks. Existing WMs primarily focus on unstructured data and cannot leverage the ubiquitous structured data, often represented as graphs, in the…

Machine Learning · Computer Science 2025-07-15 Tao Feng , Yexin Wu , Guanyu Lin , Jiaxuan You

World action models (WAMs) provide a powerful generative framework for embodied control, yet transferring knowledge across heterogeneous WAMs remains challenging due to mismatched latent interfaces, high adaptation cost, and the rigidity of…

Robotics · Computer Science 2026-05-08 Yuhua Jiang , Yijun Guo , Hongbing Yang , Guojun Lei , Nuo Chen , Yinuo Zhang , Shaoqiang Yan , Bo Lin , Feifei Gao , Biqing Qi

Post-training is essential for turning pretrained generalist robot policies into reliable task-specific controllers, but existing human-in-the-loop pipelines remain tied to physical execution: each correction requires robot time, scene…

Robotics · Computer Science 2026-05-06 Yaxuan Li , Zhongyi Zhou , Yefei Chen , Yanjiang Guo , Jiaming Liu , Shanghang Zhang , Jianyu Chen , Yichen Zhu

Context lengths for models have grown rapidly, from thousands to millions of tokens in just a few years. The extreme context sizes of modern long-context models have made it difficult to construct realistic long-context benchmarks -- not…

Computation and Language · Computer Science 2025-10-23 Stefano Rando , Luca Romani , Alessio Sampieri , Luca Franco , John Yang , Yuta Kyuragi , Fabio Galasso , Tatsunori Hashimoto

A world model is an AI system that simulates how an environment evolves under actions, enabling planning through imagined futures rather than reactive perception. Current world models, however, suffer from visual conflation: the mistaken…

Artificial Intelligence · Computer Science 2026-01-23 Zhikang Chen , Tingting Zhu

Standard Chain-of-Thought (CoT) prompting empowers Large Language Models (LLMs) with reasoning capabilities, yet its reliance on linear natural language is inherently insufficient for effective world modeling in embodied tasks. While text…

Artificial Intelligence · Computer Science 2026-04-14 Hongyu Chen , Liang Lin , Guangrun Wang

Deploying learned control policies in real-world environments poses a fundamental challenge. When system dynamics change unexpectedly, performance degrades until models are retrained on new data. We introduce Reflexive World Models (RWM), a…

Machine Learning · Computer Science 2025-05-22 Carlos Stein Brito , Daniel McNamee

Imitation learning has emerged as a promising approach towards building generalist robots. However, scaling imitation learning for large robot foundation models remains challenging due to its reliance on high-quality expert demonstrations.…

Robotics · Computer Science 2025-05-26 Chuning Zhu , Raymond Yu , Siyuan Feng , Benjamin Burchfiel , Paarth Shah , Abhishek Gupta

To interact effectively with humans in the real world, it is important for agents to understand language that describes the dynamics of the environment--that is, how the environment behaves--rather than just task instructions specifying…

Computation and Language · Computer Science 2025-12-01 Anh Nguyen , Stefan Lee

Code Large Language Models (CLLMs) have exhibited outstanding performance in program synthesis, attracting the focus of the research community. The evaluation of CLLM's program synthesis capability has generally relied on manually curated…

Software Engineering · Computer Science 2025-05-13 Longtian Wang , Tianlin Li , Xiaofei Xie , Yuhan Zhi , Jian Wang , Chao Shen

Long contexts challenge transformers: attention scores dilute across thousands of tokens, critical information is often lost in the middle, and models struggle to adapt to novel patterns at inference time. Recent work on test-time…

Computation and Language · Computer Science 2026-01-21 Lingrui Mei , Shenghua Liu , Yiwei Wang , Yuyao Ge , Baolong Bi , Jiayu Yao , Jun Wan , Ziling Yin , Jiafeng Guo , Xueqi Cheng

This report documents the preparedness assessment of Code World Model (CWM), a model for code generation and reasoning about code from Meta. We conducted pre-release testing across domains identified in our Frontier AI Framework as…

Robotic manipulation policies often degrade over extended horizons, yet existing benchmarks provide limited insight into why such failures occur. Most prior benchmarks are either simulation-based or report aggregate success, making it…

Robotics · Computer Science 2026-04-21 Xueyao Chen , Jingkai Jia , Tong Yang , Yibo Fu , Wei Li , Wenqiang Zhang

This work addresses the problem of long-horizon task planning with the Large Language Model (LLM) in an open-world household environment. Existing works fail to explicitly track key objects and attributes, leading to erroneous decisions in…

Robotics · Computer Science 2024-04-23 Siwei Chen , Anxing Xiao , David Hsu

Does continued scaling of large language models (LLMs) yield diminishing returns? In this work, we show that short-task benchmarks may give an illusion of slowing progress, as even marginal gains in single-step accuracy can compound into…

Artificial Intelligence · Computer Science 2026-03-16 Akshit Sinha , Arvindh Arun , Shashwat Goel , Steffen Staab , Jonas Geiping

Existing large language models (LLMs) evaluations use fixed-difficulty benchmarks that cannot adapt as models improve, and rarely isolate specific cognitive processes. We introduce Working Memory Fidelity-Active Manipulation (WMF-AM), a…

Artificial Intelligence · Computer Science 2026-05-05 Dengzhe Hou , Lingyu Jiang , Deng Li , Zirui Li , Fangzhou Lin , Kazunori D Yamada

In model-based learning, the agent learns behaviors by simulating trajectories based on world model predictions. Standard world models typically learn a stationary transition function that maps states and actions to next states, when an…

Artificial Intelligence · Computer Science 2026-05-11 Qinshi Zhang , Weipeng Deng , Zhihan Jiang , Jiaming Qu , Qianren Li , Weitao Xu , Ray LC

Large language models (LLMs) have achieved remarkable results on tasks framed as reasoning problems, yet their true ability to perform procedural reasoning, executing multi-step, rule-based computations remains unclear. Unlike algorithmic…

Artificial Intelligence · Computer Science 2025-11-20 Mahdi Samiei , Mahdi Mansouri , Mahdieh Soleymani Baghshah

Vision-language model (VLM) shows promise for high-level planning in smart manufacturing, yet their deployment in dynamic workcells faces two critical challenges: (1) stateless operation, they cannot persistently track out-of-view states,…

Robotics · Computer Science 2026-02-18 Guoqin Tang , Qingxuan Jia , Gang Chen , Tong Li , Zeyuan Huang , Zihang Lv , Ning Ji

Large Language Models (LLMs) exhibit catastrophic performance degradation when processing contexts approaching certain critical thresholds, even when information remains relevant. This intelligence degradation-defined as over 30% drop in…

Computation and Language · Computer Science 2026-01-23 Weiwei Wang , Jiyong Min , Weijie Zou