arXivDaily arXiv每日学术速递 周一至周五更新

大厂专区

Intel(英特尔)

共收录 218
2509.22319 2025-10-02 cs.LG cs.AI

Progressive Weight Loading: Accelerating Initial Inference and Gradually Boosting Performance on Resource-Constrained Environments

Hyunwoo Kim, Junha Lee, Mincheol Choi, Jeonghwan Lee, Jaeshin Cho

机构 * Intel(英特尔) Yonsei University(延世大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.23156 2025-09-30 cs.LG

CrystalGym: A New Benchmark for Materials Discovery Using Reinforcement Learning

Prashant Govindarajan, Mathieu Reymond, Antoine Clavaud, Mariano Phielipp, Santiago Miret, Sarath Chandar

机构 * Chandar Research Lab(昌达研究实验室) Mila – Quebec AI Institute(魁北克人工智能研究所) Polytechnique Montréal(蒙特利尔理工学院) Université de Montréal(蒙特利尔大学) Intel(英特尔) Canada CIFAR AI Chair(加拿大CIFAR人工智能主席)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.21955 2025-09-29 cs.RO cs.LG math.ST stat.TH

Learnable Conformal Prediction with Context-Aware Nonconformity Functions for Robotic Planning and Perception

Divake Kumar, Sina Tayebati, Francesco Migliarba, Ranganath Krishnan, Amit Ranjan Trivedi

机构 * University of Illinois at Chicago(伊利诺伊大学香槟分校) Intel Labs(英特尔实验室)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.17615 2025-09-23 cs.CV

From Benchmarks to Reality: Advancing Visual Anomaly Detection by the VAND 3.0 Challenge

Lars Heckler-Kram, Ashwin Vaidya, Jan-Hendrik Neudeck, Ulla Scheler, Dick Ameln, Samet Akcay, Paula Ramos

机构 * MVTec Software GmbH(MVTec软件公司) Technical University of Munich(慕尼黑技术大学) Intel(英特尔) Voxel51

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.05748 2025-09-23 eess.SP cs.LG

Learning to Slice Wi-Fi Networks: A State-Augmented Primal-Dual Approach

Yiğit Berkay Uslu, Roya Doostnejad, Alejandro Ribeiro, Navid NaderiAlizadeh

机构 * University of Pennsylvania(宾夕法尼亚大学) Intel Corporation(英特尔公司) Duke University(杜克大学)

Journal ref GLOBECOM 2024 - 2024 IEEE Global Communications Conference Proceedings

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.12466 2025-09-23 cs.LG cs.AI cs.CL cs.PL cs.SE

EquiBench: Benchmarking Large Language Models' Reasoning about Program Semantics via Equivalence Checking

Anjiang Wei, Jiannan Cao, Ran Li, Hongyu Chen, Yuhui Zhang, Ziheng Wang, Yuan Liu, Thiago S. F. X. Teixeira, Diyi Yang, Ke Wang, Alex Aiken

机构 * Stanford University(斯坦福大学) MIT(麻省理工学院) Google(谷歌) Nanjing University(南京大学) Intel(英特尔)

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.11103 2025-09-22 cs.CV cs.AI

Pruning the Paradox: How CLIP's Most Informative Heads Enhance Performance While Amplifying Bias

Avinash Madasu, Vasudev Lal, Phillip Howard

机构 * Intel Labs(英特尔实验室) Oracle(Oracle公司) Thoughtworks(Thoughtworks公司)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.11277 2025-09-19 cs.CV cs.LG

Probing the Representational Power of Sparse Autoencoders in Vision Models

Matthew Lyle Olson, Musashi Hinck, Neale Ratzlaff, Changbai Li, Phillip Howard, Vasudev Lal, Shao-Yen Tseng

机构 * Oracle Intel Labs(英特尔实验室) Oregon State University(俄勒冈州立大学) Thoughtworks

Comments ICCV 2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.12590 2025-09-19 cs.CV cs.LG

Debias your Large Multi-Modal Model at Test-Time via Non-Contrastive Visual Attribute Steering

Neale Ratzlaff, Matthew Lyle Olson, Musashi Hinck, Estelle Aflalo, Shao-Yen Tseng, Vasudev Lal, Phillip Howard

机构 * Oracle Intel Labs(英特尔实验室) Thoughtworks

Comments 10 pages, 6 Figures, 8 Tables. arXiv admin note: text overlap with arXiv:2410.13976

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.09061 2025-09-18 cs.DC cs.AI cs.PF

EdgeProfiler: A Fast Profiling Framework for Lightweight LLMs on Edge Using Analytical Model

Alyssa Pinnock, Shakya Jayakody, Kawsher A Roxy, Md Rubel Ahmed

机构 * University of Central Florida(中央佛罗里达大学) Intel Corporation(英特尔公司) Louisiana Tech University(路易斯安那理工大学)

Comments 4 figures, 7 pages, IEEE conference template

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.08872 2025-09-18 cs.CV cs.AI cs.CL

xGen-MM (BLIP-3): A Family of Open Large Multimodal Models

Le Xue, Manli Shu, Anas Awadalla, Jun Wang, An Yan, Senthil Purushwalkam, Honglu Zhou, Viraj Prabhu, Yutong Dai, Michael S Ryoo, Shrikant Kendre, Jieyu Zhang, Shaoyen Tseng, Gustavo A Lujan-Moreno, Matthew L Olson, Musashi Hinck, David Cobbley, Vasudev Lal, Can Qin, Shu Zhang, Chia-Chih Chen, Ning Yu, Juntao Tan, Tulika Manoj Awalgaonkar, Shelby Heinecke, Huan Wang, Yejin Choi, Ludwig Schmidt, Zeyuan Chen, Silvio Savarese, Juan Carlos Niebles, Caiming Xiong, Ran Xu

机构 * Salesforce AI Research(Salesforce AI研究院) Intel Labs(英特尔实验室) University of Washington(华盛顿大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.19988 2025-09-18 cs.RO cs.AI cs.CL cs.CV cs.LG

Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics

Minttu Alakuijala, Reginald McLean, Isaac Woungang, Nariman Farsad, Samuel Kaski, Pekka Marttinen, Kai Yuan

机构 * Department of Computer Science, Aalto University(艾尔沃斯大学计算机科学系) Department of Computer Science, Toronto Metropolitan University(多伦多 Metropolitan 大学计算机科学系) Department of Computer Science, University of Manchester(曼彻斯特大学计算机科学系) Intel Corporation(英特尔公司)

Comments 14 pages in the main text, 22 pages including references and supplementary materials. 3 figures and 3 tables in the main text, 6 figures and 3 tables in supplementary materials

Journal ref Transactions on Machine Learning Research (TMLR) (02/2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.13218 2025-09-17 cs.LG

FOSSIL: Regret-minimizing weighting for robust learning under imbalance and small data

J. Cha, J. Lee, J. Cho, J. Shin

机构 * Gwinnett Technical College(金尼特技术学院) Intel Corporation(英特尔公司) Prairie View A&M University(普里奥里视黑人大学) Ohio State University(俄亥俄州立大学)

Comments 24 pages, 6 figures, submitted to ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.08679 2025-09-17 cs.CV

ByDeWay: Boost Your multimodal LLM with DEpth prompting in a Training-Free Way

Rajarshi Roy, Devleena Das, Ankesh Banerjee, Arjya Bhattacharjee, Kousik Dasgupta, Subarna Tripathi

机构 * Kalyani Government Engineering College(卡利尼政府工程学院) Intel Labs(英特尔实验室)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.11270 2025-09-16 cs.RO cs.AI

Embodied Intelligence in Disassembly: Multimodal Perception Cross-validation and Continual Learning in Neuro-Symbolic TAMP

Ziwen He, Zhigang Wang, Yanlong Peng, Pengxu Chang, Hong Yang, Ming Chen

机构 * School of Mechanical Engineering, Shanghai Jiao Tong University(上海交通大学机械工程学院) Intel Labs China(英特尔中国实验室) Intel Asia Pacific R&D Ltd(英特尔亚太研发有限公司)

Comments 8 pages, 3 figures. Accepted at CASE2025. This arXiv version contains minor corrections

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.10702 2025-09-16 cs.AR cs.LG

DOSA: Differentiable Model-Based One-Loop Search for DNN Accelerators

Charles Hong, Qijing Huang, Grace Dinh, Mahesh Subedar, Yakun Sophia Shao

机构 * University of California, Berkeley(加州大学伯克利分校) NVIDIA(NVIDIA公司) Intel Labs(英特尔实验室)

Comments Published at MICRO 2023

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.01976 2025-09-11 cs.CL cs.AI cs.LG cs.PF

CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing

Wenhao Zheng, Yixiao Chen, Weitong Zhang, Souvik Kundu, Yun Li, Zhengzhong Liu, Eric P. Xing, Hongyi Wang, Huaxiu Yao

机构 * The University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校) Intel(英特尔) Carnegie Mellon University(卡内基梅隆大学) Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·拉希德人工智能大学) Rutgers University(罗格斯大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.07646 2025-09-10 cs.RO

Decoding RobKiNet: Insights into Efficient Training of Robotic Kinematics Informed Neural Network

Yanlong Peng, Zhigang Wang, Ziwen He, Pengxu Chang, Chuangchuang Zhou, Yu Yan, Ming Chen

机构 * School of Mechanical Engineering, Shanghai Jiao Tong University(上海交通大学机械工程学院) Intel Labs China(英特尔中国实验室) Henan Academy of Sciences(河南省科学院) Intel CCG FIS(英特尔中国区研究院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.15836 2025-09-09 cs.CL cs.AI

Soft Token Attacks Cannot Reliably Audit Unlearning in Large Language Models

Haokun Chen, Sebastian Szyller, Weilin Xu, Nageen Himayat

机构 * Ludwig Maximilian University of Munich(慕尼黑路德维希-马克西米利安大学) Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心) Aalto University(艾尔沃斯大学) Intel Labs(英特尔实验室)

Comments EMNLP 2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.03775 2025-09-05 cs.GR cs.CV

ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction

Sankeerth Durvasula, Sharanshangar Muhunthan, Zain Moustafa, Richard Chen, Ruofan Liang, Yushi Guan, Nilesh Ahuja, Nilesh Jain, Selvakumar Panneer, Nandita Vijaykumar

机构 * University of Toronto(多伦多大学) Intel(英特尔)

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.01228 2025-09-05 cs.DC cs.LG

ConServe: Fine-Grained GPU Harvesting for LLM Online and Offline Co-Serving

Yifan Qiao, Shu Anzai, Shan Yu, Haoran Ma, Shuo Yang, Yang Wang, Miryung Kim, Yongji Wu, Yang Zhou, Jiarong Xing, Joseph E. Gonzalez, Ion Stoica, Harry Xu

机构 * UC Berkeley(伯克利大学) UCLA(洛杉矶大学) Rice University(里奇大学) UC Davis(戴维斯大学) Intel(英特尔公司)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.02474 2025-09-03 cs.GR cs.CV cs.LG

Unifi3D: A Study on 3D Representations for Generation and Reconstruction in a Common Framework

Nina Wiedemann, Sainan Liu, Quentin Leboutet, Katelyn Gao, Benjamin Ummenhofer, Michael Paulitsch, Kai Yuan

机构 * Intel Corporation(英特尔公司)

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.07446 2025-07-08 cs.AI cs.CL cs.LG stat.ML

A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment

Raanan Y. Rohekar, Yaniv Gurwicz, Sungduk Yu, Estelle Aflalo, Vasudev Lal

机构 * Intel Labs(英特尔实验室)

Comments International Conference on Machine Learning (ICML), 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2108.01512 2025-07-08 cs.LG cond-mat.dis-nn cond-mat.other cond-mat.str-el cs.NE

Spatial Analysis of Physical Reservoir Computers

Jake Love, Jeroen Mulkers, Robin Msiska, George Bourianoff, Jonathan Leliaert, Karin Everschor-Sitte

机构 * Faculty of Physics, University of Duisburg-Essen(物理系,杜伊斯堡-埃森大学) DyNaMat, Department of Solid State Sciences, Ghent University(DyNaMat,固态科学系,根特大学) Senior Principle Engineer, Intel Corp. (Retired)(高级原则工程师,英特尔公司(退休)) Faculty of Physics(物理系) Center for Nanointegration Duisburg-Essen (CENIDE), University of Duisburg-Essen(杜伊斯堡-埃森纳米集成中心(CENIDE),杜伊斯堡-埃森大学)

Comments 7 Pages, 5 Figures

Journal ref Phys. Rev. Applied 20, 044057 (2023)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.06315 2025-07-04 cs.CR cs.AI

Threat Modeling for AI: The Case for an Asset-Centric Approach

Jose Sanchez Vicarte, Marcin Spoczynski, Mostafa Elsaid

机构 * Intel Security Research(英特尔安全研究) Intel Labs(英特尔实验室)

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.01750 2025-07-03 eess.AS cs.SD

Generalizable Detection of Audio Deepfakes

Jose A. Lopez, Georg Stemmer, Héctor Cordourier Maruri

机构 * Intel Labs(英特尔实验室)

Comments 8 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.01182 2025-07-03 cs.CV

Rapid Salient Object Detection with Difference Convolutional Neural Networks

Zhuo Su, Li Liu, Matthias Müller, Jiehua Zhang, Diana Wofk, Ming-Ming Cheng, Matti Pietikäinen

机构 * College of Computer Science, Nankai University(南开大学计算机科学学院) Center for Machine Vision and Signal Analysis (CMVS), University of Oulu(奥卢大学机器视觉与信号分析中心) Intel Labs(英特尔实验室) College of Electronic Science and Technology, NUDT(国防科技大学电子科学学院)

Comments 16 pages, accepted in TPAMI

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.18251 2025-06-26 cs.GR cs.AI cs.CV

Morse: Dual-Sampling for Lossless Acceleration of Diffusion Models

Chao Li, Jiawei Fan, Anbang Yao

机构 * Intel Labs China(英特尔中国实验室)

Comments Fixed a prompt typo in Figure 18 of the Appendix. This work is accepted to ICML 2025. The project page: https://github.com/deep-optimization/Morse

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.09316 2025-06-18 cs.LG

On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention

Yeonju Ro, Zhenyu Zhang, Souvik Kundu, Zhangyang Wang, Aditya Akella

机构 * The University of Texas at Austin(德克萨斯大学奥斯汀分校) Intel Labs(英特尔实验室)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.12953 2025-06-17 cs.LG cs.AI cs.CL

Forecasting Time Series with LLMs via Patch-Based Prompting and Decomposition

Mayank Bumb, Anshul Vemulapalli, Sri Harsha Vardhan Prasad Jella, Anish Gupta, An La, Ryan A. Rossi, Hongjie Chen, Franck Dernoncourt, Nesreen K. Ahmed, Yu Wang

机构 * University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校) Adobe(Adobe公司) Dolby Labs(Dolby实验室) Intel(英特尔公司) University of Oregon(俄勒冈大学)

详情

展开后加载摘要…

URL PDF HTML 收藏