Résultats de recherche auteurs

1

SARN: Structurally-Aware Recurrent Network for Spatio-Temporal Disaggregation Autoría: Han, Bin, Howe, Bill

Publié 2023

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
2

ML-EAT: A Multilevel Embedding Association Test for Interpretable and Transparent Social Science Autoría: Wolfe, Robert, Hiniker, Alexis, Howe, Bill

Publié 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
3

Reliable, Routable, and Reproducible: Collection of Pedestrian Pathways at Statewide Scale Autoría: Zhang, Yuxiang, Howe, Bill, Caspi, Anat

Publié 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
4

Are Data Experts Buying into Differentially Private Synthetic Data? Gathering Community Perspectives Autoría: Rosenblatt, Lucas, Howe, Bill, Stoyanovich, Julia

Publié 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
5

Characterizing LLM Abstention Behavior in Science QA with Context Perturbations Autoría: Wen, Bingbing, Howe, Bill, Wang, Lucy Lu

Publié 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
6

Towards Zero-Shot Annotation of the Built Environment with Vision-Language Models (Vision Paper) Autoría: Han, Bin, Yang, Yiwei, Caspi, Anat, Howe, Bill

Publié 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
7

Dataset Scale and Societal Consistency Mediate Facial Impression Bias in Vision-Language AI Autoría: Wolfe, Robert, Dangol, Aayushi, Hiniker, Alexis, Howe, Bill

Publié 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
8

Representation Bias of Adolescents in AI: A Bilingual, Bicultural Study Autoría: Wolfe, Robert, Dangol, Aayushi, Howe, Bill, Hiniker, Alexis

Publié 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
9

Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery Autoría: Clark, Nicholas, Shen, Hua, Howe, Bill, Mitra, Tanushree

Publié 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
10

Fragments to Facts: Partial-Information Fragment Inference from LLMs Autoría: Rosenblatt, Lucas, Han, Bin, Wolfe, Robert, Howe, Bill

Publié 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
11

Can Large Language Models Integrate Spatial Data? Empirical Insights into Reasoning Strengths and Computational Weaknesses Autoría: Han, Bin, Wolfe, Robert, Caspi, Anat, Howe, Bill

Publié 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
12

PathwayBench: Assessing Routability of Pedestrian Pathway Networks Inferred from Multi-City Imagery Autoría: Zhang, Yuxiang, Howe, Bill, Mehta, Sachin, Bolten, Nicholas-J, Caspi, Anat

Publié 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
13

Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMs Autoría: Xu, Chenjun, Wen, Bingbing, Han, Bin, Wolfe, Robert, Wang, Lucy Lu, Howe, Bill

Publié 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
14

STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes Autoría: Xu, Chenjun, Zhou, Zhennan, Su, Zhan, Howe, Bill, Wang, Lucy Lu, Wen, Bingbing

Publié 2026

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
15

Know Your Limits: A Survey of Abstention in Large Language Models Autoría: Wen, Bingbing, Yao, Jihan, Feng, Shangbin, Xu, Chenjun, Tsvetkov, Yulia, Howe, Bill, Wang, Lucy Lu

Publié 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
16

MixAtlas: Uncertainty-aware Data Mixture Optimization for Multimodal LLM Midtraining Autoría: Wen, Bingbing, Salekin, Sirajul, Kang, Feiyang, Howe, Bill, Wang, Lucy Lu, Movellan, Javier, Bilkhu, Manjot

Publié 2026

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
17

Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations? Autoría: Yang, Yiwei, Lee, Chung Peng, Feng, Shangbin, Zhao, Dora, Wen, Bingbing, Liu, Anthony Z., Tsvetkov, Yulia, Howe, Bill

Publié 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
18

Laboratory-Scale AI: Open-Weight Models are Competitive with ChatGPT Even in Low-Resource Settings Autoría: Wolfe, Robert, Slaughter, Isaac, Han, Bin, Wen, Bingbing, Yang, Yiwei, Rosenblatt, Lucas, Herman, Bernease, Brown, Eva, Qu, Zening, Weber, Nic, Howe, Bill

Publié 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
19

Understanding Privacy Norms Around LLM-Based Chatbots: A Contextual Integrity Perspective Autoría: Tran, Sarah, Lu, Hongfan, Slaughter, Isaac, Herman, Bernease, Dangol, Aayushi, Fu, Yue, Chen, Lufei, Gebreyohannes, Biniyam, Howe, Bill, Hiniker, Alexis, Weber, Nicholas, Wolfe, Robert

Publié 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:

SARN: Structurally-Aware Recurrent Network for Spatio-Temporal Disaggregation Autoría: Han, Bin, Howe, Bill

ML-EAT: A Multilevel Embedding Association Test for Interpretable and Transparent Social Science Autoría: Wolfe, Robert, Hiniker, Alexis, Howe, Bill

Reliable, Routable, and Reproducible: Collection of Pedestrian Pathways at Statewide Scale Autoría: Zhang, Yuxiang, Howe, Bill, Caspi, Anat

Are Data Experts Buying into Differentially Private Synthetic Data? Gathering Community Perspectives Autoría: Rosenblatt, Lucas, Howe, Bill, Stoyanovich, Julia

Characterizing LLM Abstention Behavior in Science QA with Context Perturbations Autoría: Wen, Bingbing, Howe, Bill, Wang, Lucy Lu

Towards Zero-Shot Annotation of the Built Environment with Vision-Language Models (Vision Paper) Autoría: Han, Bin, Yang, Yiwei, Caspi, Anat, Howe, Bill

Dataset Scale and Societal Consistency Mediate Facial Impression Bias in Vision-Language AI Autoría: Wolfe, Robert, Dangol, Aayushi, Hiniker, Alexis, Howe, Bill

Representation Bias of Adolescents in AI: A Bilingual, Bicultural Study Autoría: Wolfe, Robert, Dangol, Aayushi, Howe, Bill, Hiniker, Alexis

Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery Autoría: Clark, Nicholas, Shen, Hua, Howe, Bill, Mitra, Tanushree

Fragments to Facts: Partial-Information Fragment Inference from LLMs Autoría: Rosenblatt, Lucas, Han, Bin, Wolfe, Robert, Howe, Bill

Can Large Language Models Integrate Spatial Data? Empirical Insights into Reasoning Strengths and Computational Weaknesses Autoría: Han, Bin, Wolfe, Robert, Caspi, Anat, Howe, Bill

PathwayBench: Assessing Routability of Pedestrian Pathway Networks Inferred from Multi-City Imagery Autoría: Zhang, Yuxiang, Howe, Bill, Mehta, Sachin, Bolten, Nicholas-J, Caspi, Anat

Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMs Autoría: Xu, Chenjun, Wen, Bingbing, Han, Bin, Wolfe, Robert, Wang, Lucy Lu, Howe, Bill

STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes Autoría: Xu, Chenjun, Zhou, Zhennan, Su, Zhan, Howe, Bill, Wang, Lucy Lu, Wen, Bingbing

Know Your Limits: A Survey of Abstention in Large Language Models Autoría: Wen, Bingbing, Yao, Jihan, Feng, Shangbin, Xu, Chenjun, Tsvetkov, Yulia, Howe, Bill, Wang, Lucy Lu

MixAtlas: Uncertainty-aware Data Mixture Optimization for Multimodal LLM Midtraining Autoría: Wen, Bingbing, Salekin, Sirajul, Kang, Feiyang, Howe, Bill, Wang, Lucy Lu, Movellan, Javier, Bilkhu, Manjot

Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations? Autoría: Yang, Yiwei, Lee, Chung Peng, Feng, Shangbin, Zhao, Dora, Wen, Bingbing, Liu, Anthony Z., Tsvetkov, Yulia, Howe, Bill

Laboratory-Scale AI: Open-Weight Models are Competitive with ChatGPT Even in Low-Resource Settings Autoría: Wolfe, Robert, Slaughter, Isaac, Han, Bin, Wen, Bingbing, Yang, Yiwei, Rosenblatt, Lucas, Herman, Bernease, Brown, Eva, Qu, Zening, Weber, Nic, Howe, Bill

Understanding Privacy Norms Around LLM-Based Chatbots: A Contextual Integrity Perspective Autoría: Tran, Sarah, Lu, Hongfan, Slaughter, Isaac, Herman, Bernease, Dangol, Aayushi, Fu, Yue, Chen, Lufei, Gebreyohannes, Biniyam, Howe, Bill, Hiniker, Alexis, Weber, Nicholas, Wolfe, Robert

Résultats de la recherche - Howe, Bill

SARN: Structurally-Aware Recurrent Network for Spatio-Temporal Disaggregation Autoría: Han, Bin, Howe, Bill

ML-EAT: A Multilevel Embedding Association Test for Interpretable and Transparent Social Science Autoría: Wolfe, Robert, Hiniker, Alexis, Howe, Bill

Reliable, Routable, and Reproducible: Collection of Pedestrian Pathways at Statewide Scale Autoría: Zhang, Yuxiang, Howe, Bill, Caspi, Anat

Are Data Experts Buying into Differentially Private Synthetic Data? Gathering Community Perspectives Autoría: Rosenblatt, Lucas, Howe, Bill, Stoyanovich, Julia

Characterizing LLM Abstention Behavior in Science QA with Context Perturbations Autoría: Wen, Bingbing, Howe, Bill, Wang, Lucy Lu

Towards Zero-Shot Annotation of the Built Environment with Vision-Language Models (Vision Paper) Autoría: Han, Bin, Yang, Yiwei, Caspi, Anat, Howe, Bill

Dataset Scale and Societal Consistency Mediate Facial Impression Bias in Vision-Language AI Autoría: Wolfe, Robert, Dangol, Aayushi, Hiniker, Alexis, Howe, Bill

Representation Bias of Adolescents in AI: A Bilingual, Bicultural Study Autoría: Wolfe, Robert, Dangol, Aayushi, Howe, Bill, Hiniker, Alexis

Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery Autoría: Clark, Nicholas, Shen, Hua, Howe, Bill, Mitra, Tanushree

Fragments to Facts: Partial-Information Fragment Inference from LLMs Autoría: Rosenblatt, Lucas, Han, Bin, Wolfe, Robert, Howe, Bill

Can Large Language Models Integrate Spatial Data? Empirical Insights into Reasoning Strengths and Computational Weaknesses Autoría: Han, Bin, Wolfe, Robert, Caspi, Anat, Howe, Bill

PathwayBench: Assessing Routability of Pedestrian Pathway Networks Inferred from Multi-City Imagery Autoría: Zhang, Yuxiang, Howe, Bill, Mehta, Sachin, Bolten, Nicholas-J, Caspi, Anat

Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMs Autoría: Xu, Chenjun, Wen, Bingbing, Han, Bin, Wolfe, Robert, Wang, Lucy Lu, Howe, Bill

STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes Autoría: Xu, Chenjun, Zhou, Zhennan, Su, Zhan, Howe, Bill, Wang, Lucy Lu, Wen, Bingbing

Know Your Limits: A Survey of Abstention in Large Language Models Autoría: Wen, Bingbing, Yao, Jihan, Feng, Shangbin, Xu, Chenjun, Tsvetkov, Yulia, Howe, Bill, Wang, Lucy Lu

MixAtlas: Uncertainty-aware Data Mixture Optimization for Multimodal LLM Midtraining Autoría: Wen, Bingbing, Salekin, Sirajul, Kang, Feiyang, Howe, Bill, Wang, Lucy Lu, Movellan, Javier, Bilkhu, Manjot

Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations? Autoría: Yang, Yiwei, Lee, Chung Peng, Feng, Shangbin, Zhao, Dora, Wen, Bingbing, Liu, Anthony Z., Tsvetkov, Yulia, Howe, Bill

Laboratory-Scale AI: Open-Weight Models are Competitive with ChatGPT Even in Low-Resource Settings Autoría: Wolfe, Robert, Slaughter, Isaac, Han, Bin, Wen, Bingbing, Yang, Yiwei, Rosenblatt, Lucas, Herman, Bernease, Brown, Eva, Qu, Zening, Weber, Nic, Howe, Bill

Understanding Privacy Norms Around LLM-Based Chatbots: A Contextual Integrity Perspective Autoría: Tran, Sarah, Lu, Hongfan, Slaughter, Isaac, Herman, Bernease, Dangol, Aayushi, Fu, Yue, Chen, Lufei, Gebreyohannes, Biniyam, Howe, Bill, Hiniker, Alexis, Weber, Nicholas, Wolfe, Robert

Outils de recherche: