![Yiorgos (Georgios) Chochlakis <br/> (Γιώργος Χοχλάκης ['jorɣos xo'xlakis])](https://gchochla.github.io/images/profile_new_2.png)
| Education | |
|---|---|
 | University of Southern California, Los Angeles, CA, U.S.A. Ph.D. in Computer Science August 2021 -- Present Advisor: Prof. Shri Narayanan |
| University of Southern California, Los Angeles, CA, U.S.A. M.Sc. in Computer Science August 2021 -- Present Current GPA: 4.0 / 4.0 Coursework: CSCI-670 (Advanced Analysis of Algorithms), PSYC-626 (Computational Social Sciences), ... CSCI-699 (Grounding Natural Language), CSCI-534 (Affective Computing), ... EE-546 (Math of High-Dimensional Data), CSCI-535 (Multimodal Prob Learning of Communication), ... CSCI-654 (Crafting a Research Agenda), CSCI-699 (Science of LLMs), ... CSCI-699 (History of Language and Computations) |
 | National Technical University of Athens, Athens, Greece Joint B.Sc. & M.Eng. in Electrical & Computer Engineering September 2015 -- October 2020 (5yrs) Major: Computer Science Cumulative GPA: 9.56 / 10 Thesis: Using Artificial Neural Networks for Zero-shot Learning Advisor: Prof. Alexandros Potamianos Selected Coursework: Neural Networks and Intelligent Systems, Pattern Recognition, Computer Vision, ... Advanced Computer Architecture, Advanced Algorithms, Distributed Systems, Information Theory, ... Advanced Topics in Databases, Operating Systems Laboratory, Robotics I: Analysis-Control-Laboratory |
| Work Experience | |
|---|---|
 | Amazon Web Services, Bellevue, WA, U.S.A. Applied Science intern May 2024 -- August 2024 (3mos) Duties: Developed methods for robustness in audio-textual classification. |
| Amazon Web Services, Santa Clara, CA, U.S.A. Applied Science intern May 2023 -- August 2023 (3mos) Duties: Developed methods for robustness in audio-visual representation learning (paper) |
 | Behavioral Signal Technologies, Los Angeles, CA, U.S.A. Machine Learning engineer December 2020 -- July 2021 (6mos) Duties: Speech Diarization in phone calls, Feature engineering and modeling of speakers in phone calls |
 | SCiO P.C., Athens, Greece Machine Learning intern July 2019 -- August 2019 (2mos) Duties: Feature Engineering and Predictive Modeling for rice production in India Body of Work: code Supervisor: Dr. Pythagoras Karampiperis |
| Research Experience | |
|---|---|
| University of Southern California, Los Angeles, CA, U.S.A. Graduate Research Assistant at the Signal Analysis and Interpretation Lab May 2021 -- Present Duties: Multilingual & Multimodal Affective Analysis on Social Media ... Resurrected the reading group of the lab with 15-20 active members ... Actively mentoring undergraduate and graduate students ... IEEE K-12 Outreach programs: Presented in Spring 22 to approx. 90 students, *Team Lead* in Fall 22 for approx. 90 students ... Google ExploreCSR: Student mentor in Spring 23 Advisor: Prof. Shri Narayanan |
| National Technical University of Athens, Athens, Greece Undergraduate Research assistant at the Speech and Language Processing group March 2020 -- November 2020 (9mos) Duties: Sample-efficient Learning research Body of Work: paper (preprint) with code Advisor: Prof. Alexandros Potamianos |
 | Demokritos National Center for Scientific Research, Athens, Greece Research intern at the Institute of Informatics & Telecommunications October 2019 -- June 2020 (9mos) Duties: Remote Sensing applications of Computer Vision and Deep Learning Body of Work: paper with code Advisor: Dr. Eleni Charou |
| Honors & Awards | |
|---|---|
 | CapitalOne 2025 Fellowship |
 | Gerondelis Foundation 2023 -- 2024 Scholarship |
 | NeurIPS 2022 Top reviewer |
| National Technical University of Athens, Athens, Greece 2019 -- 2020 Highest GPA in school of ECE, Thomaidis Foundation Grant |
| National Technical University of Athens, Athens, Greece 2020 Publication Award, Thomaidis Foundation Grant |
| Publications |
|---|
Large Language Models Do Multi-Label Classification DifferentlyMarcus Ma*, Georgios Chochlakis*, Niyantha Maruthu Pandiyan, Jesse Thomason, and Shrikanth Narayanan. "Large Language Models Do Multi-Label Classification Differently." arXiv preprint arXiv:2505.17510 |
Humans Hallucinate Too: Language Models Identify and Correct Subjective Annotation Errors With Label-in-a-Haystack PromptsChochlakis, Georgios, Peter Wu, Arjun Bedi, Marcus Ma, Kristina Lerman, and Shrikanth Narayanan. "Humans Hallucinate Too: Language Models Identify and Correct Subjective Annotation Errors With Label-in-a-Haystack Prompts." arXiv preprint arXiv:2505.17222 |
Aggregation Artifacts in Subjective Tasks Collapse Large Language Models PosteriorsChochlakis, Georgios, Alexandros Potamianos, Kristina Lerman, and Shrikanth Narayanan. "Aggregation Artifacts in Subjective Tasks Collapse Large Language Models Posteriors." In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL). |
Larger Language Models Dont Care How You Think: Why Chain-of-Thought Prompting Fails in Subjective TasksChochlakis, Georgios, Niyantha Maruthu Pandiyan, Kristina Lerman, and Shrikanth Narayanan. "Larger Language Models Dont Care How You Think: Why Chain-of-Thought Prompting Fails in Subjective Tasks." In ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1-5. IEEE, 2025. |
The Strong Pull of Prior Knowledge in Large Language Models and Its Impact on Emotion RecognitionChochlakis, Georgios, Alexandros Potamianos, Kristina Lerman and Shrikanth Narayanan. “The Strong Pull of Prior Knowledge in Large Language Models and Its Impact on Emotion Recognition.” In 2024 12th International Conference on Affective Computing and Intelligent Interaction (ACII). |
Tackling missing modalities in audio-visual representation learning using masked autoencodersChochlakis, Georgios, Chandrashekhar Lavania, Prashant Mathur and Kyu Han. “Tackling missing modalities in audio-visual representation learning using masked autoencoders. Interspeech 2024. |
Socio-Linguistic Characteristics of Coordinated Inauthentic AccountsBurghardt, Keith, Ashwin Rao, Siyi Guo, Zihao He, Georgios Chochlakis, Baruah Sabyasachee, Andrew Rojecki, Shri Narayanan, and Kristina Lerman. "Socio-Linguistic Characteristics of Coordinated Inauthentic Accounts." arXiv preprint arXiv:2305.11867 (2023). |
Using Emotion Embeddings to Transfer Knowledge Between Emotions, Languages, and Annotation FormatsChochlakis, Georgios, Gireesh Mahajan, Sabyasachee Baruah, Keith Burghardt, Kristina Lerman, and Shrikanth Narayanan. "Using Emotion Embeddings to Transfer Knowledge between Emotions, Languages, and Annotation Formats." In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1-5. IEEE, 2023. |
Leveraging Label Correlations in a Multi-label Setting: A Case Study in EmotionChochlakis, Georgios, Gireesh Mahajan, Sabyasachee Baruah, Keith Burghardt, Kristina Lerman, and Shrikanth Narayanan. "Leveraging label correlations in a multi-label setting: A case study in emotion." In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1-5. IEEE, 2023. |
VAuLT: Augmenting the Vision-and-Language Transformer for Sentiment Classification on Social MediaChochlakis, G.; Srinivasan, T.; Thomason, J.; and Narayanan, S. 2022. VAuLT: Augmenting the Vision-and-Language Transformer for Sentiment Classification on Social Media. arXiv preprint arXiv:2208.09021. |
CLiMB: A Continual Learning Benchmark for Vision-and-Language TasksSrinivasan, T., Chang, T. Y., Alva, L. L. P., Chochlakis, G., Rostami, M., & Thomason, J. (2022). CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks. Thirty-sixth Conference on Neural Information Processing Systems. |
End-to-end Generative Zero-shot Learning via Few-shot LearningChochlakis G., Georgiou E., Potamianos A. End-to-end Generative Zero-shot Learning via Few-shot Learning. arXiv preprint arXiv:2102.04379, 2021. |
Generating Elevation Surface from a single RGB remotely sensed image using Deep Learning*Panagiotou E, *Chochlakis G, Grammatikopoulos L, Charou E. Generating Elevation Surface from a Single RGB Remotely Sensed Image Using Deep Learning. Remote Sensing. 2020; 12(12):2002. |
🇬🇷 Greek (Native), 🇬🇧 🇺🇸 English (Fluent), 🇫🇷 French (Paris-Sorbonne C1), 🇪🇸 Spanish (Elementary)
Sports ⚽ 🏀 👟
Books 📖 -> popular science🥼 AI🤖 history📜 philosophy💭 crime🔫
Video Games 🐭⚡ ⚽ 🏀 …