Profiles2020-2025
Michal Lukasik
Department of Computer Science UCLA
10Papers
1Last author
19Unique co-authors
5First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers10
- Better autoregressive regression with LLMs via regression-aware fine-tuningAuthor 1 of 5ICLR 2025
- Bipartite Ranking From Multiple Labels: On Loss Versus Label AggregationAuthor 1 of 10ICML 2025
- TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-JudgeAuthor 3 of 3ACL 2025
- Two-stage LLM Fine-tuning with Less Specialization and More GeneralizationAuthor 4 of 8ICLR 2024 · 45 citations
- On Bias-Variance Alignment in Deep ModelsAuthor 2 of 5ICLR 2024 · 8 citations
- Regression Aware Inference with LLMsAuthor 1 of 5EMNLP Findings 2024 · 3 citations
- Large Language Models with Controllable Working MemoryAuthor 5 of 11ACL Findings 2023 · 46 citations
- ResMem: Learn what you can and memorize the restAuthor 2 of 8NeurIPS 2023 · 14 citations
- Does label smoothing mitigate label noise?Author 1 of 4ICML 2020 · 411 citations
- Text Segmentation by Cross Segment AttentionAuthor 1 of 5EMNLP 2020 · 1 citation
