News
News
Large Content and Behavior Models (LCBM) paper was accepted to ICLR (spotlight) and got a 10 score!
CABINET: Content Relevance-based Noise Reduction for Table Question Answering was accepted to ICLR (spotlight)!
Paper titled, "A Video Is Worth 4096 Tokens: Verbalize Story Videos To Understand Them In Zero Shot" was nominated for a best paper award at EMNLP-23.
Gave a talk titled "Optimizing Communication To Optimize Behavior: Towards Achieving Third Level of Shannon's Theory of Communication" at the National University of Singapore. Slides here: https://www.slideshare.net/YamanKumar3/optimizing-communication-to-optimize-behavior-lcbm
Paper titled, "A Video Is Worth 4096 Tokens: Verbalize Story Videos To Understand Them In Zero Shot" was accepted to EMNLP-23.
Won the prestigious Adobe Outstanding Young Engineer Award! Thanks Adobe :)
Paper titled "Automatic Essay Scoring Systems Are Both Overstable And Oversensitive: Explaining Why And Proposing Defenses" was accepted to the Dialogue and Discourse Journal.
Paper titled "Synthesizing Human Gaze Feedback for Improved NLP Performance" was accepted to EACL-23
Paper titled "H-AES: Towards Automated Essay Scoring for Hindi" accepted to EAAI-AAAI.
Paper titled "Persuasion Strategies in Advertisements: Dataset, Modeling, and Baselines" accepted to AAAI-23
Paper titled "What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structure" accepted in ICDM Foundation Models
Paper titled "LDKP: A Dataset for Identifying Keyphrases from Long Scientific Documents" accepted in CIKM DL4SR Workshop.
Paper titled "Span Classification with Structured Information for Disfluency Detection in Spoken Utterances" accepted in Interspeech.
Got the IIITD Dean Innovation, Research, and Development Award for the year 2021-22.
Interviewed by the IndiaAI team, the national Artificial Intelligence portal of India. Here's the link.
I got awarded the PhD Best First-Year Achiever Award at the State University of New York at Buffalo! Thanks, UB!!
I got awarded the prestigious CII-SERB Prime Minister Fellowship along with 38 other PhD scholars across the country! Thanks, CII and SERB!
I applied for this fellowship last year in 2020. However, due to a change in circumstances, I will not be claiming it.
Paper titled "MINIMAL: Mining Models for Data Free Universal Adversarial Triggers" was accepted to AAAI-2022! Congratulations, Swapnil Parekh, Somesh Singh, Rajiv Ratn Shah, Balaji Krishnamurthy, and Changyou Chen.
The paper "Automated Speech Scoring System Under The Lens: Evaluating and interpreting the linguistic cues for language proficiency" was accepted to IJAIED (the top journal in the education informatics space) and will appear in the journal soon. Congratulations to my co-authors Pakhi Bandev, Manraj Singh Grover, Payman Vafaee, Mika Hama, and Rajiv Ratn Shah!
Paper titled "Using Sampling to Estimate and Improve Performance of Automated Scoring Systems with Guarantees" was accepted at EAAI-AAAI-2022. Congratulations to my co-authors Sriram Krishna, Rajiv Shah, and Changyou Chen! Checkout the blogpost as well.
Paper titled "Evaluation Toolkit For Robustness Testing Of Automatic Essay Scoring Systems" was accepted at CODS-COMAD-2022. Congratulations to my co-authors Mehar Bhatia, Anubha Kabra, Junyi Jessy Li, and Rajiv Shah!
Serving as the PC member of AAAI-2022.
Awarded IIITD Dean Innovation, Research and Development Award-2021 for my work on "Visual Language Processing including Lipreading, and Speech Reconstruction". Thanks, IIITD!
Our work on lipreading, speech reconstruction, and visual language processing was reported in The Hindu. Related paper: Harnessing AI for Speech Reconstruction using Multi-view Silent Video Feed
Done with the first-year defence! Slides here.
Paper titled "Speaker-Conditioned Hierarchical Modeling for Automated Speech Scoring" was accepted to CIKM'21. Congratulations to my co-authors Avyakt Gupta, Shaurya Bagga, Balaji Krishnamurthy, Rajiv Shah, and Changyou Chen!
I will be mentoring high-school students on how to conduct research at the Summar STEM Institute (SSI) this summer. Excited to introduce research to these young minds!
My research project (at the MDSR Lab), CatchyContent was covered by Forrester, Fast Company, and other websites. It also won the prestigious best sneaks award at Adobe Sneaks 2021.
The patent Pose-invariant visual speech recognition using a single view input was filed at the USPTO.
The paper "LIFI: Towards Linguistically Informed Frame Interpolation" was accepted at ICASSP-2021. Congratulations to my co-authors Devansh Batra, Aradhya Neeraj Mathur, Roger Zimmermann, Rajiv Shah, and Changyou Chen! Do check out the work!
Slides for the tutorial delivered with Dr Rajiv Ratn Shah at ICVGIP-2020. The title of the tutorial is "Marriage of Computer Vision, Speech and Language".
Got the Google PhD fellowship 2020. Thanks, Google!
Gave a talk at Summer Symposium on AI research organized by SAIDL and APPCAIR. The title of the talk is "AI in Education and Education in AI: From AI assisting Education to Educating yourself in AI". Slides
I am organizing the grand challenge titled "Touchless Technologies" at IEEE BigMM in collaboration with Prof Guoying Zhao and Prof Li Liu, Henglin Shi from the University of Oulu, Prof Rajesh Kumar from Haverford College and Aradhya Mathur from IIIT-D. Check out the challenge and do participate!
Selected as one of the Heidelberg Laureate Young Researchers! Thanks, HLF!
Nominated for the Adobe Young Engineer Award 2020.
Team MobiVSR won the first prize at ACM India Chapters Technology Solution Contest. Thanks, ACM India!
Received InterSpeech Young Scientists Grant-2019. Thanks, InterSpeech!
My undergraduate thesis work AutoSAS with Dr Debanjan Mahata was covered by Tech at Bloomberg. Thanks, Bloomberg!
Won Best student abstract paper award at AAAI-19 for this paper. Thanks, AAAI!
Nominated for the Adobe Young Engineer Award 2019.
Won Best Poster Paper Runner Up award at ISM-18 for this paper. Thanks, ISM!