Deep learning is the predominant machine learning paradigm in natural language processing (NLP). This approach not only gave huge performance improvements across a large variety of natural language processing tasks. For a detailed list of this years topics, the below.
Lecturer: Dietrich Klakow
Location: t.d.b
Time: block course in September 2025 however preparations start earlier. Here the specific time line
Closing topic doodle: early May
Kick-Off: mid May
One page outline: mid June
Draft presentation: mid July
Practice talks and final talks will be in September. Time/date will be decided during the kick-off.
Application for participation: registration system. (this is for CoLI, for CS, DSAI, Bioinformatics please use the CS seminar system). Before applying check please check the list of topics and your availability in September. Apply latest by Sunday April 21st. Number is participants is limited to 12. Notification of acceptance on April 22nd. Bioinformatics: you have to have passed NNTI and need to pick a bioinformatics topic from the list below.
HISPOS registration deadline: tbd
Grading :
- 5% one page talk outline
- 10% draft presentation
- 10% practice talk
- 35% final talk
- 5% contributions to discussion during final talk of fellow participants
- 35% report
List of Topics (tentative):
- Does representation matter? exploring intermediate layers in large language models
- Confidence regulation neurons in language models
- Discrete flow matching
- Simple and effective masked diffusion language models
- Are language models actually useful for time series forecasting?
- Chain of lora: Efficient fine-tuning of language models via residual learning
- Scientific large language models: A survey on biological & chemical domains,
- Leveraging biomolecule and natural language through multi-modal learning: A survey
- A review of large language models and autonomous agents in chemistry
- Designing proteins with language models
- Controllable protein design with language models
- Prollama: A protein large language model for multi-task protein language processing