Past Talks Archive
A record of previous LangLunches presentations.
| Date | Speaker | Topic |
|---|---|---|
| May 5, 2026 | Anisha Saha | MUStReason: A Benchmark for Diagnosing Pragmatic Reasoning in Video-LMs for Multimodal Sarcasm Detection |
| April 21st, 2026 | Entang Wang | How Few-Shot Examples Add Up: A Causal Decomposition of Function Vectors in In-Context Learning. |
| July 16, 2025 | Benedict Krieger | On the limits of LLM surprisal as a functional explanation of the N400 and P600 |
| July 16, 2025 | Yash Sarrof | Theory of Transformers |
| July 1, 2025 | Mayank Jobanaputra | Understanding Logic Proofs in the Age of LLMs: A Benchmark and Analysis |
| July 1, 2025 | Yuekun Yao | language models can learn implicit multi-hop reasoning, but only if they have lots of training data |
| June 18, 2025 | Arianna Bienati | An 'intuitive' notion of complexity? Fluctuation complexity in the making |
| June 18, 2025 | Xin Tong | Informal title: Dot by Dot - Neuroscientific approach to studying Human Perception |
| June 3, 2025 | Maja Stegenwallner | Design of the MultiplEYE multilingual eye-tracking study on natural reading |
| June 3, 2025 | Soyoung Oh | Idiom Processing in LLMs |
| May 21, 2025 | Damiana Porcellato | A semantic map of negation in Indo-European |
| May 21, 2025 | Aravind Krishnan | Not all data are unlearned equally |
| May 6, 2025 | Alex Duchnowski | EHOP: A Dataset of Everday NP-Hard Optimization Problems |
| May 6, 2025 | Sarubi Thillainathan | Controllable Text Adaptation Using In-context Learning with Linguistic Features |
| April 23, 2025 | Zena AL Khalili | Evaluating Intermediate Programs of Code-assisted LLMs for Mathematics |
| April 23, 2025 | Sasha Bakalova | Contextualize-then-Aggregate: Circuits for In-Context Learning in Gemma-2 2B |