Search Results - "Łukasik, Michał"

Computational Approach to Dendritic Spine Taxonomy and Shape Transition Analysis by Bokota, Grzegorz, Magnowska, Marta, Kuśmierczyk, Tomasz, Łukasik, Michał, Roszkowska, Matylda, Plewczynski, Dariusz

“…The common approach in morphological analysis of dendritic spines of mammalian neuronal cells is to categorize spines into subpopulations based on whether they…”
Get full text

XR Hackathon Going Online: Lessons Learned from a Case Study with Goethe-Institut by Kopeć, Wiesław, Skorupska, Kinga, Jaskulska, Anna, Łukasik, Michał, Karpowicz, Barbara, Paluch, Julia, Kwiatkowska, Kinga, Jabłoński, Daniel, Masłyk, Rafał

“…In this article we report a case study of a Language and Culture-oriented transdisciplinary XR hackathon organized with Goethe-Institut. The hackathon was…”
Get full text

Discourse-aware rumour stance classification in social media using sequential classifiers by Zubiaga, Arkaitz, Kochkina, Elena, Liakata, Maria, Procter, Rob, Lukasik, Michal, Bontcheva, Kalina, Cohn, Trevor, Augenstein, Isabelle

“…Rumour stance classification, defined as classifying the stance of specific social media posts into one of supporting, denying, querying or commenting on an…”
Get full text

Evaluation of Features for Author Name Disambiguation Using Linear Support Vector Machines by Dendek, P. J., Bolikowski, L., Lukasik, M.

“…Author name disambiguation allows to distinguish between two or more authors sharing the same name. In a previous paper, we have proposed a name disambiguation…”
Get full text

Probabilistic modeling of rumour stance and popularity in social media by Lukasik, Michal

Get full text

It's an Alignment, Not a Trade-off: Revisiting Bias and Variance in Deep Models by Chen, Lin, Lukasik, Michal, Jitkrittum, Wittawat, You, Chong, Kumar, Sanjiv

“…Classical wisdom in machine learning holds that the generalization error can be decomposed into bias and variance, and these two terms exhibit a…”
Get full text

Regression-aware Inference with LLMs by Lukasik, Michal, Narasimhan, Harikrishna, Menon, Aditya Krishna, Yu, Felix, Kumar, Sanjiv

“…EMNLP Findings 2024 Large language models (LLMs) have shown strong results on a range of applications, including regression and scoring tasks. Typically, one…”
Get full text

What do larger image classifiers memorise? by Lukasik, Michal, Nagarajan, Vaishnavh, Rawat, Ankit Singh, Menon, Aditya Krishna, Kumar, Sanjiv

“…The success of modern neural networks has prompted study of the connection between memorisation and generalisation: overparameterised models generalise well,…”
Get full text

Teacher's pet: understanding and mitigating biases in distillation by Lukasik, Michal, Bhojanapalli, Srinadh, Menon, Aditya Krishna, Kumar, Sanjiv

“…Knowledge distillation is widely used as a means of improving the performance of a relatively simple student model using the predictions from a complex teacher…”
Get full text

Hawkes Process Classification through Discriminative Modeling of Text by Tondulkar, Rohan, Dubey, Manisha, Srijith, P.K., Lukasik, Michal

“…Social media such as Twitter has provided a platform for users to gather and share information and stay updated with the news. However, restriction on the…”
Get full text

Hawkes Process Classification through Discriminative Modeling of Text by Tondulkar, Rohan, Dubey, Manisha, Srijith, P. K, Lukasik, Michal

“…Social media has provided a platform for users to gather and share information and stay updated with the news. Such networks also provide a platform to users…”
Get full text

Robust Distillation for Worst-class Performance by Wang, Serena, Narasimhan, Harikrishna, Zhou, Yichen, Hooker, Sara, Lukasik, Michal, Menon, Aditya Krishna

“…Knowledge distillation has proven to be an effective technique in improving the performance a student model using predictions from a teacher model. However,…”
Get full text

ResMem: Learn what you can and memorize the rest by Yang, Zitong, Lukasik, Michal, Nagarajan, Vaishnavh, Li, Zonglin, Rawat, Ankit Singh, Zaheer, Manzil, Menon, Aditya Krishna, Kumar, Sanjiv

“…The impressive generalization performance of modern neural networks is attributed in part to their ability to implicitly memorize complex training patterns…”
Get full text

Text Segmentation by Cross Segment Attention by Lukasik, Michal, Dadachev, Boris, Simões, Gonçalo, Papineni, Kishore

“…Document and discourse segmentation are two fundamental NLP tasks pertaining to breaking up text into constituents, which are commonly used to help downstream…”
Get full text

Large Language Models with Controllable Working Memory by Li, Daliang, Rawat, Ankit Singh, Zaheer, Manzil, Wang, Xin, Lukasik, Michal, Veit, Andreas, Yu, Felix, Kumar, Sanjiv

“…Large language models (LLMs) have led to a series of breakthroughs in natural language processing (NLP), owing to their excellent understanding and generation…”
Get full text

Two-stage LLM Fine-tuning with Less Specialization and More Generalization by Wang, Yihan, Si, Si, Li, Daliang, Lukasik, Michal, Yu, Felix, Hsieh, Cho-Jui, Dhillon, Inderjit S, Kumar, Sanjiv

“…Pretrained large language models (LLMs) are general purpose problem solvers applicable to a diverse set of tasks with prompts. They can be further improved…”
Get full text

Does label smoothing mitigate label noise? by Lukasik, Michal, Bhojanapalli, Srinadh, Menon, Aditya Krishna, Kumar, Sanjiv

“…Label smoothing is commonly used in training deep learning models, wherein one-hot training labels are mixed with uniform label vectors. Empirically, smoothing…”
Get full text

HD-cos Networks: Efficient Neural Architectures for Secure Multi-Party Computation by Jitkrittum, Wittawat, Lukasik, Michal, Suresh, Ananda Theertha, Yu, Felix, Wang, Gang

“…Multi-party computation (MPC) is a branch of cryptography where multiple non-colluding parties execute a well designed protocol to securely compute a function…”
Get full text

Longitudinal Modeling of Social Media with Hawkes Process Based on Users and Networks by Srijith, P. K., Lukasik, Michal, Bontcheva, Kalina, Cohn, Trevor

“…Online social media provide a platform for rapid network propagation of information at an unprecedented scale. In this paper, we study the evolution of…”
Get full text

Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation by Bhojanapalli, Srinadh, Chakrabarti, Ayan, Jain, Himanshu, Kumar, Sanjiv, Lukasik, Michal, Veit, Andreas

“…State-of-the-art transformer models use pairwise dot-product based self-attention, which comes at a computational cost quadratic in the input sequence length…”
Get full text