Ansar Aynetdinov

4 papers · 2024–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12) 🐣 Hot Topic Early Bird 🏆 Keyword Champion (2)

Venues

EMNLP (2) ACL (1) NAACL (1)

Top co-authors

Alan Akbik (4) Patrick Haller (1) Elena Merdjanovska (1)

Research topics

Natural Language Processing (4) Artificial Intelligence (2) Machine Learning (2) Core AI (2) Generation (2) Learning Types · Machine Learning (2) Deep Learning (1) Learning Paradigms (1) Learning Types · Deep Learning (1) Optimization & Theory (1) Resources & Methods (1) Understanding (1)

Keywords

pretraining objective (2) small language model (2) multi-token prediction (2) curriculum learning (2) instruction tuning (1) label noise (1) language model (1) next-token prediction (1) annotation error (1) demographic bia (1) self-speculative decoding (1) explicit bia (1) noise-robust learning (1) zero-shot learning (1) instruction-tuned large language model (1) sample efficiency (1) sequence labeling (1) named entity recognition (1)

Papers

Babies Learn to Look Ahead: Multi-Token Prediction in Small LMs EMNLP 2025 Pre-Training Curriculum for Multi-Token Prediction in Language Models ACL 2025 NoiseBench: Benchmarking the Impact of Real Label Noise on Named Entity Recognition EMNLP 2024 OpinionGPT: Modelling Explicit Biases in Instruction-Tuned LLMs NAACL 2024