大模型推理能力 - arXivDaily 专题

2410.13303 2024-10-18 cs.LG cs.AI 62%

Hiformer: Hybrid Frequency Feature Enhancement Inverted Transformer for Long-Term Wind Power Prediction

Chongyang Wan, Shunbo Lei, Yuan Luo

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

2410.12492 2024-10-17 cs.CL cs.LG 62%

End-to-end Planner Training for Language Modeling

Nathan Cornille, Florian Mai, Jingyuan Sun, Marie-Francine Moens

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.LG

Comments 14 pages

2410.11324 2024-10-16 cs.AI cs.CV cs.LG 62%

Diffusion-Based Offline RL for Improved Decision-Making in Augmented ARC Task

Yunho Kim, Jaehyun Park, Heejun Kim, Sejin Kim, Byung-Jun Lee, Sundong Kim

专题命中规划推理：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Preprint, Under review. Comments welcome

2410.10871 2024-10-16 cs.CL cs.AI 62%

Applying Refusal-Vector Ablation to Llama 3.1 70B Agents

Simon Lermen, Mateusz Dziemian, Govind Pimpale

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.AI

2410.00385 2024-10-16 cs.LG cs.AI cs.DB 62%

STGformer: Efficient Spatiotemporal Graph Transformer for Traffic Forecasting

Hongjun Wang, Jiyuan Chen, Tong Pan, Zheng Dong, Lingyu Zhang, Renhe Jiang, Xuan Song

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

2410.09038 2024-10-15 cs.CL cs.AI 62%

SimpleStrat: Diversifying Language Model Generation with Stratification

Justin Wong, Yury Orlovskiy, Michael Luo, Sanjit A. Seshia, Joseph E. Gonzalez

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.AI

2410.06508 2024-10-10 cs.LG cs.CL 62%

Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning

Xiyao Wang, Linfeng Song, Ye Tian, Dian Yu, Baolin Peng, Haitao Mi, Furong Huang, Dong Yu

专题命中规划推理：reasoning(abstract)；分类 cs.CL、cs.LG

2405.15194 2024-10-10 cs.LG cs.AI 62%

Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning

Siddhant Bhambri, Amrita Bhattacharjee, Durgesh Kalwar, Lin Guan, Huan Liu, Subbarao Kambhampati

专题命中规划推理：verifier(abstract)；分类 cs.AI、cs.LG

2410.03806 2024-10-08 cs.LG cs.CL 62%

Metadata Matters for Time Series: Informative Forecasting with Transformers

Jiaxiang Dong, Haixu Wu, Yuxuan Wang, Li Zhang, Jianmin Wang, Mingsheng Long

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.LG

2309.16397 2024-10-08 cs.LG cs.AI 62%

Uncertainty-Aware Decision Transformer for Stochastic Driving Environments

Zenan Li, Fan Nie, Qiao Sun, Fang Da, Hang Zhao

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

2410.02428 2024-10-04 cs.CL cs.AI 62%

Collective Critics for Creative Story Generation

Minwook Bae, Hyounghun Kim

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.AI

Comments EMNLP 2024 (36 pages)

2410.02231 2024-10-04 cs.AI cs.LG cs.SY eess.SY 62%

SEAL: SEmantic-Augmented Imitation Learning via Language Model

Chengyang Gu, Yuxin Pan, Haotian Bai, Hui Xiong, Yize Chen

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments 18 pages, 5 figures, in submission

2402.01107 2024-10-03 cs.LG cs.AI cs.DS 62%

Simulation of Graph Algorithms with Looped Transformers

Artur Back de Luca, Kimon Fountoulakis

专题命中规划推理：reasoning(abstract)；分类 cs.AI、cs.LG

Comments 55 pages, 3 figures

2410.00649 2024-10-02 cs.RO cs.AI cs.HC cs.LG 62%

LASMP: Language Aided Subset Sampling Based Motion Planner

Saswati Bhattacharjee, Anirban Sinha, Chinwe Ekenna

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments 8 pages, 9 figures

2406.14277 2024-09-30 cs.CL cs.AI 62%

QPaug: Question and Passage Augmentation for Open-Domain Question Answering of LLMs

Minsang Kim, Cheoneum Park, Seungjun Baek

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.AI

Comments The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), Findings

2405.03553 2024-09-30 cs.CL cs.AI 62%

AlphaMath Almost Zero: Process Supervision without Process

Guoxin Chen, Minpeng Liao, Chengxi Li, Kai Fan

专题命中规划推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Camera ready version for NeurIPS 2024

2409.17405 2024-09-27 cs.AI cs.LG 62%

AI Enabled Neutron Flux Measurement and Virtual Calibration in Boiling Water Reactors

Anirudh Tunga, Jordan Heim, Michael Mueterthies, Thomas Gruenwald, Jonathan Nistor

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Journal ref 13th Nuclear Plant Instrumentation, Control & Human-Machine Interface Technologies (NPIC&HMIT 2023)

2409.17126 2024-09-26 cs.RO cs.AI cs.LG 62%

Blox-Net: Generative Design-for-Robot-Assembly Using VLM Supervision, Physics Simulation, and a Robot with Reset

Andrew Goldberg, Kavish Kondap, Tianshuang Qiu, Zehan Ma, Letian Fu, Justin Kerr, Huang Huang, Kaiyuan Chen, Kuan Fang, Ken Goldberg

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments 8 pages, 7 Figures

2409.15794 2024-09-25 cs.LG cs.AI 62%

Towards Universal Large-Scale Foundational Model for Natural Gas Demand Forecasting

Xinxing Zhou, Jiaqi Ye, Shubao Zhao, Ming Jin, Zhaoxiang Hou, Chengyi Yang, Zengxiang Li, Yanlong Wen, Xiaojie Yuan

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

2409.14762 2024-09-24 cs.CL cs.AI 62%

Do Large Language Models have Problem-Solving Capability under Incomplete Information Scenarios?

Yuyan Chen, Tianhao Yu, Yueze Li, Songzhou Yan, Sijia Liu, Jiaqing Liang, Yanghua Xiao

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.AI

Comments Accepted to ACL 2024 (Findings)

2402.12275 2024-09-24 cs.AI cs.CL 62%

WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment

Hao Tang, Darren Key, Kevin Ellis

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.AI

2409.11820 2024-09-19 cs.AI cs.LG cs.SY eess.SY 62%

Optimizing Job Shop Scheduling in the Furniture Industry: A Reinforcement Learning Approach Considering Machine Setup, Batch Variability, and Intralogistics

Malte Schneevogt, Karsten Binninger, Noah Klarmann

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments 18 pages, 8 pages

2311.15649 2024-09-16 cs.RO cs.AI cs.LG 62%

RoboGPT: an intelligent agent of making embodied long-term decisions for daily instruction tasks

Yaran Chen, Wenbo Cui, Yuanwen Chen, Mining Tan, Xinyao Zhang, Dongbin Zhao, He Wang

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

2409.07964 2024-09-13 cs.NI cs.AI cs.LG 62%

WirelessAgent: Large Language Model Agents for Intelligent Wireless Networks

Jingwen Tong, Jiawei Shao, Qiong Wu, Wei Guo, Zijian Li, Zehong Lin, Jun Zhang

专题命中规划推理：reasoning(abstract)；分类 cs.AI、cs.LG

2409.07341 2024-09-12 cs.LG cs.AI cs.RO 62%

Online Decision MetaMorphFormer: A Casual Transformer-Based Reinforcement Learning Framework of Universal Embodied Intelligence

Luo Ji, Runji Lin

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments 12 pages, 6 figures

2409.03284 2024-09-06 cs.AI cs.CL cs.IR 62%

iText2KG: Incremental Knowledge Graphs Construction Using Large Language Models

Yassir Lairgi, Ludovic Moncla, Rémy Cazabet, Khalid Benabdeslem, Pierre Cléau

专题命中规划推理：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Accepted at The International Web Information Systems Engineering conference (the WISE conference) 2024

2409.02148 2024-09-05 eess.SY cs.AI cs.LG cs.SY math.OC 62%

Optimal Power Grid Operations with Foundation Models

Alban Puech, Jonas Weiss, Thomas Brunschwiler, Hendrik F. Hamann

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

2409.00070 2024-09-04 cs.CL cs.AI 62%

Learning to Plan Long-Term for Language Modeling

Florian Mai, Nathan Cornille, Marie-Francine Moens

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.AI

Comments preprint

2403.03870 2024-08-28 cs.CL cs.LG 62%

Learning to Decode Collaboratively with Multiple Language Models

Shannon Zejiang Shen, Hunter Lang, Bailin Wang, Yoon Kim, David Sontag

专题命中规划推理：reasoning(abstract)；分类 cs.CL、cs.LG

Comments 16 pages, 4 figures, 11 tables

2405.20962 2024-08-26 cs.CY cs.AI cs.CL 62%

Large Language Models are Zero-Shot Next Location Predictors

Ciro Beneduce, Bruno Lepri, Massimiliano Luca

专题命中规划推理：reasoning(abstract)；分类 cs.CL、cs.AI

1. 规划推理 11120 篇

Hiformer: Hybrid Frequency Feature Enhancement Inverted Transformer for Long-Term Wind Power Prediction

End-to-end Planner Training for Language Modeling

Diffusion-Based Offline RL for Improved Decision-Making in Augmented ARC Task

Applying Refusal-Vector Ablation to Llama 3.1 70B Agents

STGformer: Efficient Spatiotemporal Graph Transformer for Traffic Forecasting

SimpleStrat: Diversifying Language Model Generation with Stratification

Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning

Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning

Metadata Matters for Time Series: Informative Forecasting with Transformers

Uncertainty-Aware Decision Transformer for Stochastic Driving Environments

Collective Critics for Creative Story Generation

SEAL: SEmantic-Augmented Imitation Learning via Language Model

Simulation of Graph Algorithms with Looped Transformers

LASMP: Language Aided Subset Sampling Based Motion Planner

QPaug: Question and Passage Augmentation for Open-Domain Question Answering of LLMs

AlphaMath Almost Zero: Process Supervision without Process

AI Enabled Neutron Flux Measurement and Virtual Calibration in Boiling Water Reactors

Blox-Net: Generative Design-for-Robot-Assembly Using VLM Supervision, Physics Simulation, and a Robot with Reset

Towards Universal Large-Scale Foundational Model for Natural Gas Demand Forecasting

Do Large Language Models have Problem-Solving Capability under Incomplete Information Scenarios?

WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment

Optimizing Job Shop Scheduling in the Furniture Industry: A Reinforcement Learning Approach Considering Machine Setup, Batch Variability, and Intralogistics

RoboGPT: an intelligent agent of making embodied long-term decisions for daily instruction tasks

WirelessAgent: Large Language Model Agents for Intelligent Wireless Networks

Online Decision MetaMorphFormer: A Casual Transformer-Based Reinforcement Learning Framework of Universal Embodied Intelligence

iText2KG: Incremental Knowledge Graphs Construction Using Large Language Models

Optimal Power Grid Operations with Foundation Models

Learning to Plan Long-Term for Language Modeling

Learning to Decode Collaboratively with Multiple Language Models

Large Language Models are Zero-Shot Next Location Predictors