语言大模型 / LLM - arXivDaily 专题

2504.04753 2025-04-11 cs.CV 50%

CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images

Cheng Chen, Jiacheng Wei, Tianrun Chen, Chi Zhang, Xiaofeng Yang, Shangzhan Zhang, Bingchen Yang, Chuan-Sheng Foo, Guosheng Lin, Qixing Huang, Fayao Liu

专题命中后训练与偏好优化：preference optimization(abstract)

Comments Accepted to CVPR2025

2409.16879 2025-04-04 cs.RO 50%

GRACE: Generating Socially Appropriate Robot Actions Leveraging LLMs and Human Explanations

Fethiye Irmak Dogan, Umut Ozyurt, Gizem Cinar, Hatice Gunes

专题命中后训练与偏好优化：LLM(abstract)

Comments 2025 IEEE International Conference on Robotics & Automation (ICRA), Supplementary video: https://youtu.be/GTNCC1GkiQ4

2503.22590 2025-03-31 quant-ph 50%

Accelerated VQE: Parameter Recycling for Similar Recurring Problem Instances

Tobias Rohe, Maximilian Balthasar Mansky, Michael Kölle, Jonas Stein, Leo Sünkel, Claudia Linnhoff-Popien

专题命中后训练与偏好优化：post-training(abstract)

2503.15265 2025-03-20 cs.CV 50%

DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning

Ruowen Zhao, Junliang Ye, Zhengyi Wang, Guangce Liu, Yiwen Chen, Yikai Wang, Jun Zhu

专题命中后训练与偏好优化：preference optimization(abstract)

Comments Project page: https://zhaorw02.github.io/DeepMesh/

2502.18965 2025-02-27 cs.IR 50%

OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment

Jiaxin Deng, Shiyao Wang, Kuo Cai, Lejian Ren, Qigen Hu, Weifeng Ding, Qiang Luo, Guorui Zhou

专题命中后训练与偏好优化：preference optimization(abstract)

2407.06141 2025-02-25 cs.CV 50%

CHAMP: Conformalized 3D Human Multi-Hypothesis Pose Estimators

Harry Zhang, Luca Carlone

专题命中后训练与偏好优化：post-training(abstract)

2502.09285 2025-02-14 cs.CV cs.CY 50%

EmoAssist: Emotional Assistant for Visual Impairment Community

Xingyu Qi, He Li, Linjie Li, Zhenyu Wu

专题命中后训练与偏好优化：preference optimization(abstract)

2407.21035 2025-01-17 cs.CV 50%

Direct Unlearning Optimization for Robust and Safe Text-to-Image Models

Yong-Hyun Park, Sangdoo Yun, Jin-Hwa Kim, Junho Kim, Geonhui Jang, Yonghyun Jeong, Junghyo Jo, Gayoung Lee

专题命中后训练与偏好优化：preference optimization(abstract)

Comments This paper has been accepted for NeurIPS 2024

2406.11280 2025-01-09 cs.CV 50%

ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO

Daechul Ahn, Yura Choi, San Kim, Youngjae Yu, Dongyeop Kang, Jonghyun Choi

专题命中后训练与偏好优化：preference optimization(abstract)

Comments AAAI 2025

2501.00345 2025-01-03 math.NA cs.NA math.AP 50%

The discrete inverse conductivity problem solved by the weights of an interpretable neural network

Elena Beretta, Maolin Deng, Alberto Gandolfi, Bangti Jin

专题命中后训练与偏好优化：post-training(abstract)

Comments 31 pages, 12 figures

2412.09551 2024-12-13 cs.CV 50%

Video Creation by Demonstration

Yihong Sun, Hao Zhou, Liangzhe Yuan, Jennifer J. Sun, Yandong Li, Xuhui Jia, Hartwig Adam, Bharath Hariharan, Long Zhao, Ting Liu

专题命中后训练与偏好优化：foundation model(abstract)

Comments Project page at https://delta-diffusion.github.io/

2406.07449 2024-11-12 stat.ME stat.ML 50%

Boosted Conformal Prediction Intervals

Ran Xie, Rina Foygel Barber, Emmanuel J. Candès

专题命中后训练与偏好优化：post-training(abstract)

2410.23039 2024-10-31 cs.RO cs.CV 50%

Neural Attention Field: Emerging Point Relevance in 3D Scenes for One-Shot Dexterous Grasping

Qianxu Wang, Congyue Deng, Tyler Ga Wei Lum, Yuanpei Chen, Yaodong Yang, Jeannette Bohg, Yixin Zhu, Leonidas Guibas

专题命中后训练与偏好优化：post-training(abstract)

2402.17465 2024-10-22 cs.CR cs.CV 50%

Model X-ray:Detecting Backdoored Models via Decision Boundary

Yanghao Su, Jie Zhang, Ting Xu, Tianwei Zhang, Weiming Zhang, Nenghai Yu

专题命中后训练与偏好优化：post-training(abstract)

2312.06726 2024-09-05 cs.CV 50%

Filter & Align: Leveraging Human Knowledge to Curate Image-Text Data

Lei Zhang, Fangxun Shu, Tianyang Liu, Sucheng Ren, Hao Jiang, Cihang Xie

专题命中后训练与偏好优化：foundation model(abstract)

2406.02833 2024-08-13 cs.CV 50%

DenoDet: Attention as Deformable Multi-Subspace Feature Denoising for Target Detection in SAR Images

Yimian Dai, Minrui Zou, Yuxuan Li, Xiang Li, Kang Ni, Jian Yang

专题命中后训练与偏好优化：post-training(abstract)

2408.04447 2024-08-09 cs.CE 50%

Reinforcement Learning from Human Feedback for Lane Changing of Autonomous Vehicles in Mixed Traffic

Yuting Wang, Lu Liu, Maonan Wang, Xi Xiong

专题命中后训练与偏好优化：RLHF(abstract)

2407.12272 2024-07-18 cs.HC 50%

Assessing the Feasibility, and Efficacy of Virtual Reality Navigational Training for Older Adults

Tong Bill Xu, Armin Mostafavi, Walter R. Boot, Sara Czaja, Saleh Kalantari

专题命中后训练与偏好优化：post-training(abstract)

2407.03917 2024-07-08 cs.CV 50%

Timestep-Aware Correction for Quantized Diffusion Models

Yuzhe Yao, Feng Tian, Jun Chen, Haonan Lin, Guang Dai, Yong Liu, Jingdong Wang

专题命中后训练与偏好优化：post-training(abstract)

Comments ECCV 2024

2404.04852 2024-06-12 cs.RO 50%

EnQuery: Ensemble Policies for Diverse Query-Generation in Preference Alignment of Robot Navigation

Jorge de Heuvel, Florian Seiler, Maren Bennewitz

专题命中后训练与偏好优化：RLHF(abstract)

2405.16134 2024-05-31 cs.CV 50%

Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack

Mingli Zhu, Siyuan Liang, Baoyuan Wu

专题命中后训练与偏好优化：post-training(abstract)

2404.08273 2024-05-21 cs.CV cs.CR 50%

Struggle with Adversarial Defense? Try Diffusion

Yujie Li, Yanbin Wang, Haitao Xu, Bin Liu, Jianguo Sun, Zhenhao Guo, Wenrui Ma

专题命中后训练与偏好优化：post-training(abstract)

2404.05666 2024-04-09 cs.CV 50%

YaART: Yet Another ART Rendering Technology

Sergey Kastryulin, Artem Konev, Alexander Shishenya, Eugene Lyapustin, Artem Khurshudov, Alexander Tselousov, Nikita Vinokurov, Denis Kuznedelev, Alexander Markovich, Grigoriy Livshits, Alexey Kirillov, Anastasiia Tabisheva, Liubov Chubarova, Marina Kaminskaia, Alexander Ustyuzhanin, Artemii Shvetsov, Daniil Shlenskii, Valerii Startsev, Dmitrii Kornilov, Mikhail Romanov, Artem Babenko, Sergei Ovcharenko, Valentin Khrulkov

专题命中后训练与偏好优化：RLHF(abstract)

Comments Prompts and additional information are available on the project page, see https://ya.ru/ai/art/paper-yaart-v1

2403.10325 2024-03-18 math.DS 50%

Data-driven cold starting of good reservoirs

Lyudmila Grigoryeva, Boumediene Hamzi, Felix P. Kemeth, Yannis Kevrekidis, G Manjunath, Juan-Pablo Ortega, Matthys J. Steynberg

专题命中后训练与偏好优化：post-training(abstract)

Comments 21 pages, 9 figures

2310.14580 2024-01-17 cs.SD eess.AS 50%

Acoustic BPE for Speech Generation with Discrete Tokens

Feiyu Shen, Yiwei Guo, Chenpeng Du, Xie Chen, Kai Yu

专题命中后训练与偏好优化：language model(abstract)

Comments 5 pages, 2 figures; accepted to ICASSP 2024

2312.08048 2024-01-12 cs.CV 50%

Compositional Inversion for Stable Diffusion Models

Xulu Zhang, Xiao-Yong Wei, Jinlin Wu, Tianyi Zhang, Zhaoxiang Zhang, Zhen Lei, Qing Li

专题命中后训练与偏好优化：post-training(abstract)

Comments This paper was accepted by AAAI 2024

2312.15037 2023-12-27 cs.CV 50%

Latents2Semantics: Leveraging the Latent Space of Generative Models for Localized Style Manipulation of Face Images

Snehal Singh Tomar, A. N. Rajagopalan

专题命中后训练与偏好优化：post-training(abstract)

Comments Accepted as an oral paper at the AAAI-24 Workshop on AI for Digital Human

2312.09152 2023-12-15 cs.HC 50%

Evaluating Augmented Reality Communication: How Can We Teach Procedural Skill in AR?

Manuel Rebol, Krzysztof Pietroszek, Neal Sikka, Claudia Ranniger, Colton Hood, Adam Rutenberg, Puja Sasankan, Christian Gütl

专题命中后训练与偏好优化：post-training(abstract)

Comments https://doi.org/10.1145/3611659.3615685

Journal ref Proceedings of the 29th ACM Symposium on Virtual Reality Software and Technology (VRST 2023)

2308.04132 2023-08-11 cs.MM cs.NI 50%

Optimizing Adaptive Video Streaming with Human Feedback

Tianchi Huang, Rui-Xiao Zhang, Chenglei Wu, Lifeng Sun

专题命中后训练与偏好优化：RLHF(abstract)

Comments ACM Multimedia 2023

2303.13571 2023-03-27 cs.CV eess.IV 50%

Inheriting Bayer's Legacy-Joint Remosaicing and Denoising for Quad Bayer Image Sensor

Haijin Zeng, Kai Feng, Jiezhang Cao, Shaoguang Huang, Yongqiang Zhao, Hiep Luong, Jan Aelterman, Wilfried Philips

专题命中后训练与偏好优化：post-training(abstract)

1. 后训练与偏好优化 4541 篇

CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images

GRACE: Generating Socially Appropriate Robot Actions Leveraging LLMs and Human Explanations

Accelerated VQE: Parameter Recycling for Similar Recurring Problem Instances

DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning

OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment

CHAMP: Conformalized 3D Human Multi-Hypothesis Pose Estimators

EmoAssist: Emotional Assistant for Visual Impairment Community

Direct Unlearning Optimization for Robust and Safe Text-to-Image Models

ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO

The discrete inverse conductivity problem solved by the weights of an interpretable neural network

Video Creation by Demonstration

Boosted Conformal Prediction Intervals

Neural Attention Field: Emerging Point Relevance in 3D Scenes for One-Shot Dexterous Grasping

Model X-ray:Detecting Backdoored Models via Decision Boundary

Filter & Align: Leveraging Human Knowledge to Curate Image-Text Data

DenoDet: Attention as Deformable Multi-Subspace Feature Denoising for Target Detection in SAR Images

Reinforcement Learning from Human Feedback for Lane Changing of Autonomous Vehicles in Mixed Traffic

Assessing the Feasibility, and Efficacy of Virtual Reality Navigational Training for Older Adults

Timestep-Aware Correction for Quantized Diffusion Models

EnQuery: Ensemble Policies for Diverse Query-Generation in Preference Alignment of Robot Navigation

Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack

Struggle with Adversarial Defense? Try Diffusion

YaART: Yet Another ART Rendering Technology

Data-driven cold starting of good reservoirs

Acoustic BPE for Speech Generation with Discrete Tokens

Compositional Inversion for Stable Diffusion Models

Latents2Semantics: Leveraging the Latent Space of Generative Models for Localized Style Manipulation of Face Images

Evaluating Augmented Reality Communication: How Can We Teach Procedural Skill in AR?

Optimizing Adaptive Video Streaming with Human Feedback

Inheriting Bayer's Legacy-Joint Remosaicing and Denoising for Quad Bayer Image Sensor