English
Related papers

Related papers: Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of …

200 papers

Instruction tuning has emerged as a promising approach to enhancing large language models in following human instructions. It is shown that increasing the diversity and number of instructions in the training data can consistently enhance…

Computation and Language · Computer Science 2024-01-09 Shihao Liang , Runchu Tian , Kunlun Zhu , Yujia Qin , Huadong Wang , Xin Cong , Zhiyuan Liu , Xiaojiang Liu , Maosong Sun

Steering vectors are a lightweight method for controlling language model behavior by adding a learned bias to the activations at inference time. Although effective on average, steering effect sizes vary across samples and are unreliable for…

Computation and Language · Computer Science 2026-02-23 Joschka Braun

Large Language Models (LLMs) show promise as data analysis agents, but existing benchmarks overlook the iterative nature of the field, where experts' decisions evolve with deeper insights of the dataset. To address this, we introduce…

Computation and Language · Computer Science 2025-06-09 Hanyu Li , Haoyu Liu , Tingyu Zhu , Tianyu Guo , Zeyu Zheng , Xiaotie Deng , Michael I. Jordan

Many activity classifications segments data into fixed window size for feature extraction and classification. However, animal behaviors have various durations that do not match the predetermined window size. The dense labeling and dense…

Signal Processing · Electrical Eng. & Systems 2022-09-09 Zhuqing Zhao , Dong Ha , Abhishek Damle , Barbara Roqueto Dos , Robin White , Sook Ha

In this paper, we introduce UI-Genie, a self-improving framework addressing two key challenges in GUI agents: verification of trajectory outcome is challenging and high-quality training data are not scalable. These challenges are addressed…

Computation and Language · Computer Science 2025-05-28 Han Xiao , Guozhi Wang , Yuxiang Chai , Zimu Lu , Weifeng Lin , Hao He , Lue Fan , Liuyang Bian , Rui Hu , Liang Liu , Shuai Ren , Yafei Wen , Xiaoxin Chen , Aojun Zhou , Hongsheng Li

Most of the deep learning-based speech enhancement models are learned in a supervised manner, which implies that pairs of noisy and clean speech are required during training. Consequently, several noisy speeches recorded in daily life…

Sound · Computer Science 2021-10-13 Szu-Wei Fu , Cheng Yu , Kuo-Hsuan Hung , Mirco Ravanelli , Yu Tsao

As autonomous agents become adept at understanding and interacting with graphical user interface (GUI) environments, a new era of automated task execution is emerging. Recent studies have demonstrated that Reinforcement Learning (RL) can…

Artificial Intelligence · Computer Science 2026-03-16 Songqin Nong , Xiaoxuan Tang , Jingxuan Xu , Sheng Zhou , Jianfeng Chen , Tao Jiang , Wenhao Xu

Effectively adapting powerful pretrained foundation models to diverse tasks remains a key challenge in AI deployment. Current approaches primarily follow two paradigms:discrete optimization of text prompts through prompt engineering, or…

Computation and Language · Computer Science 2025-08-06 Xiaoming Hou , Jiquan Zhang , Zibin Lin , DaCheng Tao , Shengli Zhang

Recent advancements in vision-language models have increased interest in Device-Control Agents (DC agents) for managing graphical user interfaces (GUIs). With the growing complexity and integration of such agents into various applications,…

Artificial Intelligence · Computer Science 2025-09-29 Shaoqing Zhang , Kehai Chen , Zhuosheng Zhang , Rumei Li , Rongxiang Weng , Yang Xiang , Min Zhang

Large language models (LLMs) are increasingly deployed as tool-augmented agents capable of executing system-level operations. While existing benchmarks primarily assess textual alignment or task success, less attention has been paid to the…

Artificial Intelligence · Computer Science 2026-05-26 Shasha Yu , Fiona Carroll , Barry L. Bentley

We introduce GAIN (Goal-Aligned Decision-Making under Imperfect Norms), a benchmark designed to evaluate how large language models (LLMs) balance adherence to norms against business goals. Existing benchmarks typically focus on abstract…

Computation and Language · Computer Science 2026-03-20 Masayuki Kawarada , Kodai Watanabe , Soichiro Murakami

Complex, long-horizon planning and its combinatorial nature pose steep challenges for learning-based agents. Difficulties in such settings are exacerbated in low data regimes where over-fitting stifles generalization and compounding errors…

Machine Learning · Computer Science 2023-06-23 Joey Hejna , Pieter Abbeel , Lerrel Pinto

Despite the vast literature on Human Activity Recognition (HAR) with wearable inertial sensor data, it is perhaps surprising that there are few studies investigating semisupervised learning for HAR, particularly in a challenging scenario…

Machine Learning · Computer Science 2021-01-14 Govind Narasimman , Kangkang Lu , Arun Raja , Chuan Sheng Foo , Mohamed Sabry Aly , Jie Lin , Vijay Chandrasekhar

While large language models (LLMs) have exhibited impressive instruction-following capabilities, it is still unclear whether and to what extent they can respond to explicit constraints that might be entailed in various instructions. As a…

Computation and Language · Computer Science 2024-01-02 Yihan Chen , Benfeng Xu , Quan Wang , Yi Liu , Zhendong Mao

Natural language conveys information at varying levels of granularity, from fine-grained references to broad descriptions. While granularity is fundamental to human communication, existing measures mostly capture surface detail or sentence…

Computation and Language · Computer Science 2026-05-27 Lukas Ellinger , Alexander Fichtl , Miriam Anschütz , Georg Groh

Automated theorem proving with large language models in Lean 4 is commonly approached through either step-level tactic prediction with tree search or whole-proof generation. These two paradigms represent opposite granularities for…

Artificial Intelligence · Computer Science 2026-05-13 Shuo Xu , Jiakun Zhang , Junyu Lai , Chun Cao , Jingwei Xu

The field of meta-learning seeks to improve the ability of today's machine learning systems to adapt efficiently to small amounts of data. Typically this is accomplished by training a system with a parametrized update rule to improve a…

Machine Learning · Computer Science 2021-03-26 Lucas D. Lingle

Dialogue topic segmentation supports summarization, retrieval, memory management, and conversational continuity. Despite decades of work, evaluation practice remains dominated by strict boundary matching and F1-based metrics. Modern large…

Computation and Language · Computer Science 2026-01-01 Michael H. Coen

Recent research has shown the existence of significant redundancy in large Transformer models. One can prune the redundant parameters without significantly sacrificing the generalization performance. However, we question whether the…

Computation and Language · Computer Science 2022-02-15 Chen Liang , Haoming Jiang , Simiao Zuo , Pengcheng He , Xiaodong Liu , Jianfeng Gao , Weizhu Chen , Tuo Zhao

Reinforcement Learning (RL) agents deployed in real-world environments face degradation from sensor faults, actuator wear, and environmental shifts, yet lack intrinsic mechanisms to detect and diagnose these failures. We present an…

Artificial Intelligence · Computer Science 2025-09-15 Cameron Reid , Wael Hafez , Amirhossein Nazeri