McGill NLP Group

McGill NLP Group on Hugging Face Daily Papers: 7 papers, 1 in the top 3 of their day, 0 paper of the day.

1. Forecasting Downstream Performance of LLMs With Proxy Metrics 14 upvotes, #22 of 2026-05-22
2. Structured Distillation of Web Agent Capabilities Enables Generalization 20 upvotes, #18 of 2026-04-10
3. LLM2Vec-Gen: Generative Embeddings from Large Language Models 40 upvotes, #4 of 2026-03-12
4. Humans and LLMs Diverge on Probabilistic Inferences 11 upvotes, #13 of 2026-03-04
5. LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs 18 upvotes, #17 of 2026-02-11
6. Value Drifts: Tracing Value Alignment During LLM Post-Training 12 upvotes, #12 of 2025-11-03
7. LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders 61 upvotes, #2 of 2024-04-10

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.