Michal Lukasik

61 papers A* 11A 2B 4Journal 29Unranked 12

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge. CoRR Yasi Zhang, Tianyu Chen, Mingyuan Zhou, Oscar Leong, Ying Nian Wu, Michal Lukasik
2025	A*	`conf`	Better autoregressive regression with LLMs via regression-aware fine-tuning. ICLR Michal Lukasik, Zhao Meng, Harikrishna Narasimhan, Yin-Wen Chang, Aditya Krishna Menon, Felix Yu, Sanjiv Kumar
2025	A*	`conf`	Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation. ICML Michal Lukasik, Lin Chen, Harikrishna Narasimhan, Aditya Krishna Menon, Wittawat Jitkrittum, Felix X. Yu, Sashank J. Reddi, Gang Fu, MohammadHossein Bateni, Sanjiv Kumar
2025	J	`jnl`	Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation. CoRR Michal Lukasik, Lin Chen, Harikrishna Narasimhan, Aditya Krishna Menon, Wittawat Jitkrittum, Felix X. Yu, Sashank J. Reddi, Gang Fu, MohammadHossein Bateni, Sanjiv Kumar
2025	—	`conf`	TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-Judge. ACL (1) Cheng-Han Chiang, Hung-yi Lee, Michal Lukasik
2025	J	`jnl`	TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-Judge. CoRR Cheng-Han Chiang, Hung-yi Lee, Michal Lukasik
2024	J	`jnl`	Metric-aware LLM inference. CoRR Michal Lukasik, Harikrishna Narasimhan, Aditya Krishna Menon, Felix X. Yu, Sanjiv Kumar
2024	A*	`conf`	On Bias-Variance Alignment in Deep Models. ICLR Lin Chen, Michal Lukasik, Wittawat Jitkrittum, Chong You, Sanjiv Kumar
2024	—	`conf`	Regression Aware Inference with LLMs. EMNLP (Findings) Michal Lukasik, Harikrishna Narasimhan, Aditya Krishna Menon, Felix X. Yu, Sanjiv Kumar
2024	A*	`conf`	Two-stage LLM Fine-tuning with Less Specialization and More Generalization. ICLR Yihan Wang, Si Si, Daliang Li, Michal Lukasik, Felix X. Yu, Cho-Jui Hsieh, Inderjit S. Dhillon, Sanjiv Kumar
2024	J	`jnl`	What do larger image classifiers memorise? Trans. Mach. Learn. Res. Michal Lukasik, Vaishnavh Nagarajan, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar
2023	J	`jnl`	It's an Alignment, Not a Trade-off: Revisiting Bias and Variance in Deep Models. CoRR Lin Chen, Michal Lukasik, Wittawat Jitkrittum, Chong You, Sanjiv Kumar
2023	—	`conf`	Large Language Models with Controllable Working Memory. ACL (Findings) Daliang Li, Ankit Singh Rawat, Manzil Zaheer, Xin Wang, Michal Lukasik, Andreas Veit, Felix X. Yu, Sanjiv Kumar
2023	A*	`conf`	ResMem: Learn what you can and memorize the rest. NeurIPS Zitong Yang, Michal Lukasik, Vaishnavh Nagarajan, Zonglin Li, Ankit Singh Rawat, Manzil Zaheer, Aditya Krishna Menon, Sanjiv Kumar
2023	J	`jnl`	ResMem: Learn what you can and memorize the rest. CoRR Zitong Yang, Michal Lukasik, Vaishnavh Nagarajan, Zonglin Li, Ankit Singh Rawat, Manzil Zaheer, Aditya Krishna Menon, Sanjiv Kumar
2023	A	`conf`	Robust distillation for worst-class performance: on the interplay between teacher and student objectives. UAI Serena Wang, Harikrishna Narasimhan, Yichen Zhou, Sara Hooker, Michal Lukasik, Aditya Krishna Menon
2023	J	`jnl`	What do larger image classifiers memorise? CoRR Michal Lukasik, Vaishnavh Nagarajan, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar
2022	B	`conf`	Hawkes Process Classification through Discriminative Modeling of Text. IJCNN Rohan Tondulkar, Manisha Dubey, P. K. Srijith, Michal Lukasik
2022	J	`jnl`	Large Language Models with Controllable Working Memory. CoRR Daliang Li, Ankit Singh Rawat, Manzil Zaheer, Xin Wang, Michal Lukasik, Andreas Veit, Felix X. Yu, Sanjiv Kumar
2022	J	`jnl`	Preserving In-Context Learning ability in Large Language Model Fine-tuning. CoRR Yihan Wang, Si Si, Daliang Li, Michal Lukasik, Felix X. Yu, Cho-Jui Hsieh, Inderjit S. Dhillon, Sanjiv Kumar
2022	J	`jnl`	Robust Distillation for Worst-class Performance. CoRR Serena Lutong Wang, Harikrishna Narasimhan, Yichen Zhou, Sara Hooker, Michal Lukasik, Aditya Krishna Menon
2022	J	`jnl`	Teacher's pet: understanding and mitigating biases in distillation. Trans. Mach. Learn. Res. Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar
2022	J	`jnl`	XR Hackathon Going Online: Lessons Learned from a Case Study with Goethe-Institut. CoRR Wieslaw Kopec, Kinga Skorupska, Anna Jaskulska, Michal Lukasik, Barbara Karpowicz, Julia Paluch, Kinga Kwiatkowska, Daniel Jablonski, Rafal Maslyk
2021	J	`jnl`	Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation. CoRR Srinadh Bhojanapalli, Ayan Chakrabarti, Himanshu Jain, Sanjiv Kumar, Michal Lukasik, Andreas Veit
2021	J	`jnl`	HD-cos Networks: Efficient Neural Architectures for Secure Multi-Party Computation. CoRR Wittawat Jitkrittum, Michal Lukasik, Ananda Theertha Suresh, Felix X. Yu, Gang Wang
2021	J	`jnl`	Leveraging redundancy in attention with Reuse Transformers. CoRR Srinadh Bhojanapalli, Ayan Chakrabarti, Andreas Veit, Michal Lukasik, Himanshu Jain, Frederick Liu, Yin-Wen Chang, Sanjiv Kumar
2021	J	`jnl`	Teacher's pet: understanding and mitigating biases in distillation. CoRR Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar
2021	—	`conf`	XR Hackathon Going Online: Lessons Learned from a Case Study with Goethe-Institute. MIDI Wieslaw Kopec, Kinga Skorupska, Anna Jaskulska, Michal Lukasik, Barbara Karpowicz, Julia Paluch, Kinga Kwiatkowska, Daniel Jablonski, Rafal Maslyk
2020	A*	`conf`	Does label smoothing mitigate label noise? ICML Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar
2020	J	`jnl`	Does label smoothing mitigate label noise? CoRR Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar
2020	J	`jnl`	Hawkes Process Classification through Discriminative Modeling of Text. CoRR Rohan Tondulkar, Manisha Dubey, P. K. Srijith, Michal Lukasik
2020	A*	`conf`	Scaling Graph Neural Networks with Approximate PageRank. KDD Aleksandar Bojchevski, Johannes Klicpera, Bryan Perozzi, Amol Kapoor, Martin Blais, Benedek Rózemberczki, Michal Lukasik, Stephan Günnemann
2020	J	`jnl`	Scaling Graph Neural Networks with Approximate PageRank. CoRR Aleksandar Bojchevski, Johannes Klicpera, Bryan Perozzi, Amol Kapoor, Martin Blais, Benedek Rózemberczki, Michal Lukasik, Stephan Günnemann
2020	—	`conf`	Semantic Label Smoothing for Sequence to Sequence Problems. EMNLP (1) Michal Lukasik, Himanshu Jain, Aditya Krishna Menon, Seungyeon Kim, Srinadh Bhojanapalli, Felix X. Yu, Sanjiv Kumar
2020	J	`jnl`	Semantic Label Smoothing for Sequence to Sequence Problems. CoRR Michal Lukasik, Himanshu Jain, Aditya Krishna Menon, Seungyeon Kim, Srinadh Bhojanapalli, Felix X. Yu, Sanjiv Kumar
2020	—	`conf`	Text Segmentation by Cross Segment Attention. EMNLP (1) Michal Lukasik, Boris Dadachev, Kishore Papineni, Gonçalo Simões
2020	J	`jnl`	Text Segmentation by Cross Segment Attention. CoRR Michal Lukasik, Boris Dadachev, Gonçalo Simões, Kishore Papineni
2019	J	`jnl`	Gaussian Processes for Rumour Stance Classification in Social Media. ACM Trans. Inf. Syst. Michal Lukasik, Kalina Bontcheva, Trevor Cohn, Arkaitz Zubiaga, Maria Liakata, Rob Procter
2018	A	`conf`	A Bayesian Point Process Model for User Return Time Prediction in Recommendation Systems. UMAP Sherin Thomas, P. K. Srijith, Michal Lukasik
2018	A*	`conf`	Content Explorer: Recommending Novel Entities for a Document Writer. EMNLP Michal Lukasik, Richard Zens
2018	J	`jnl`	Discourse-aware rumour stance classification in social media using sequential classifiers. Inf. Process. Manag. Arkaitz Zubiaga, Elena Kochkina, Maria Liakata, Rob Procter, Michal Lukasik, Kalina Bontcheva, Trevor Cohn, Isabelle Augenstein
2017	J	`jnl`	Discourse-Aware Rumour Stance Classification in Social Media Using Sequential Classifiers. CoRR Arkaitz Zubiaga, Elena Kochkina, Maria Liakata, Rob Procter, Michal Lukasik, Kalina Bontcheva, Trevor Cohn, Isabelle Augenstein
2017	B	`conf`	Longitudinal Modeling of Social Media with Hawkes Process Based on Users and Networks. ASONAM P. K. Srijith, Michal Lukasik, Kalina Bontcheva, Trevor Cohn
2017	—	`—`	Probabilistic modeling of rumour stance and popularity in social media. Michal Lukasik
2016	J	`jnl`	Computational Approach to Dendritic Spine Taxonomy and Shape Transition Analysis. Frontiers Comput. Neurosci. Grzegorz Bokota, Marta Magnowska, Tomasz Kusmierczyk, Michal Lukasik, Matylda Roszkowska, Dariusz Plewczynski
2016	A*	`conf`	Convolution Kernels for Discriminative Learning from Streaming Text. AAAI Michal Lukasik, Trevor Cohn
2016	—	`conf`	Hawkes Processes for Continuous Time Sequence Classification: an Application to Rumour Stance Classification in Twitter. ACL (2) Michal Lukasik, P. K. Srijith, Duy Vu, Kalina Bontcheva, Arkaitz Zubiaga, Trevor Cohn
2016	—	`conf`	Metrics for Evaluation of Word-level Machine Translation Quality Estimation. ACL (2) Varvara Logacheva, Michal Lukasik, Lucia Specia
2016	B	`conf`	Stance Classification in Rumours as a Sequential Task Exploiting the Tree Structure of Social Media Conversations. COLING Arkaitz Zubiaga, Elena Kochkina, Maria Liakata, Rob Procter, Michal Lukasik
2016	J	`jnl`	Stance classification in Rumours as a Sequential Task Exploiting the Tree Structure of Social Media Conversations. CoRR Arkaitz Zubiaga, Elena Kochkina, Maria Liakata, Rob Procter, Michal Lukasik
2016	J	`jnl`	Using Gaussian Processes for Rumour Stance Classification in Social Media. CoRR Michal Lukasik, Kalina Bontcheva, Trevor Cohn, Arkaitz Zubiaga, Maria Liakata, Rob Procter
2015	A*	`conf`	Classifying Tweet Level Judgements of Rumours in Social Media. EMNLP Michal Lukasik, Trevor Cohn, Kalina Bontcheva
2015	J	`jnl`	Estimating collective judgement of rumours in social media. CoRR Michal Lukasik, Trevor Cohn, Kalina Bontcheva
2015	A*	`conf`	Modeling Tweet Arrival Times using Log-Gaussian Cox Processes. EMNLP Michal Lukasik, P. K. Srijith, Trevor Cohn, Kalina Bontcheva
2015	—	`conf`	Point Process Modelling of Rumour Dynamics in Social Media. ACL (2) Michal Lukasik, Trevor Cohn, Kalina Bontcheva
2013	—	`ch.`	Comparing Hierarchical Mathematical Document Clustering against the Mathematics Subject Classification Tree. Intelligent Tools for Building a Scientific Information Platform Tomasz Kusmierczyk, Michal Lukasik, Lukasz Bolikowski, Hung Son Nguyen
2013	—	`conf`	Generic Framework for Simulation of Cognitive Systems: A Case Study of Color Category Boundaries. ICMMI Dariusz Plewczynski, Michal Lukasik, Konrad Kurdej, Julian Zubek, Franciszek Rakowski, Joanna Raczaszek-Leonardi
2013	—	`ch.`	Hierarchical, Multi-label Classification of Scholarly Publications: Modifications of ML-KNN Algorithm. Intelligent Tools for Building a Scientific Information Platform Michal Lukasik, Tomasz Kusmierczyk, Lukasz Bolikowski, Hung Son Nguyen
2013	—	`conf`	Multiobjective Differential Evolution: A Comparative Study on Benchmark Problems. ICMMI Indrajit Saha, Ujjwal Maulik, Michal Lukasik, Dariusz Plewczynski
2013	—	`conf`	Threshold ML-KNN: Statistical Evaluation on Multiple Benchmarks. IIS Michal Lukasik, Marcin Sydow
2012	B	`conf`	Evaluation of Features for Author Name Disambiguation Using Linear Support Vector Machines. Document Analysis Systems Piotr Jan Dendek, Lukasz Bolikowski, Michal Lukasik