Mariya Toneva

发表

DURING DEEP NEURAL NETWORK LEARNING

Geoffrey J. Gordon, Alessandro Sordoni, Mariya Toneva, 2019 .

Towards a model for mid-level feature representation of scenes

Abhinav Gupta, Michael J. Tarr, Elissa Aminoff, 2014 .

Word Length Processing via Region-to-Region Connectivity

R. Kass, Tom. Mitchell, A. Ghuman, 2018 .

Supervised Mind Reading : Uncovering Text from Neural Data

Haohan Wang, Mariya Toneva, Vipul Singh, 2015 .

Combining computational controls with natural text reveals new aspects of meaning composition

Tom M. Mitchell, Tom. Mitchell, Leila Wehbe, 2020, bioRxiv.

Joint processing of linguistic properties in brains and language models

Mariya Toneva, S. Oota, Manish Gupta, 2022, ArXiv.

Language models and brain alignment: beyond word-level semantics and prediction

Mariya Toneva, Gabriele Merlin, 2022, ArXiv.

Different complement immune pathways mediate innate and learned aversion

M. Owen, T. Hughes, L. Wilkinson, 2019, bioRxiv.

Single-Trial MEG Data Can Be Denoised Through Cross-Subject Predictive Modeling

Leila Wehbe, Srinivas Ravishankar, Mariya Toneva, 2021, Frontiers in Computational Neuroscience.

Same Cause; Different Effects in the Brain

Christoph Dann, Leila Wehbe, Jennifer Williams, 2022, CLeaR.

The Physical Presence of a Robot Tutor Increases Cognitive Learning Gains

Brian Scassellati, Samuel Spaulding, Dan Leyzberg, 2012, CogSci.

Modeling Task Effects on Meaning Representation in the Brain via Zero-Shot MEG Prediction pdf

Tom M. Mitchell, Barnabas Poczos, Leila Wehbe, 2020, NeurIPS.

Does injecting linguistic structure into language models lead to better alignment with brain recordings? pdf

Anders Søgaard, Mostafa Abdou, Mariya Toneva, 2021, ArXiv.

Inducing brain-relevant bias in natural language processing models

Daniel Schwartz, Leila Wehbe, Mariya Toneva, 2019, NeurIPS.

Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain)

Leila Wehbe, Mariya Toneva, Leila Wehbe, 2019, NeurIPS.

The meaning that emerges from combining words is robustly localizable in space but not in time

Leila Wehbe, Mariya Toneva, Tom M. Mitchell, 2020 .

Training language models for deeper understanding improves brain alignment

Mariya Toneva, Khai Loong Aw, Mariya Toneva, 2022, ArXiv.

Training language models to summarize narratives improves brain alignment

Mariya Toneva, Khai Loong Aw, 2022, ICLR.

An Empirical Study of Example Forgetting during Deep Neural Network Learning pdf

Yoshua Bengio, Geoffrey J. Gordon, Adam Trischler, 2018, ICLR.

Large language models can segment narrative events similarly to humans

K. Norman, Sebastian Michelmann, Mariya Toneva, 2023, ArXiv.

An Exploration of Social Grouping in Robots: Effects of Behavioral Mimicry, Appearance, and Eye Gaze

Brian Scassellati, Ahsan I. Nawroj, Henny Admoni, 2014, CogSci.

Robot gaze does not reflexively cue human attention

Brian Scassellati, Henny Admoni, Joshua Tan, 2011, CogSci.

Applying artificial vision models to human scene understanding

Xinlei Chen, Abhinav Gupta, Michael J. Tarr, 2015, Front. Comput. Neurosci..

What Happens During Finetuning of Vision Transformers: An Invariance Based Investigation

Vedant Nanda, Mariya Toneva, Gabriele Merlin, 2023, CoLLAs.

Complement C 3 and C 3 aR differentially impact on learned fear and 1 innate anxiety 2 3

M. Owen, T. Hughes, L. Wilkinson, 2019 .