Trending

Active discussions, ranked by recent helpful reactions and replies.

Reproductionon Denoising Diffusion Probabilistic Models

Reproduction note: training seems sensitive to seed

Computer VisionML Systems
4 26 days ago

by tbecker

Questionon Attention Is All You Need

Why does the attention mechanism scale by sqrt(d_k)?

NLPTheory
3 26 days ago

by amir_r

Research Ideaon Foundation Models for Electronic Health Records

Could this method work for clinical event sequences?

EHRMedicine
2 16 days ago

by priyanair

Critiqueon Learning Transferable Visual Models From Natural Language Supervision

Do zero-shot numbers overstate real-world robustness?

Computer Vision
2 06 days ago

by lenaf

Explanationon Attention Is All You Need

How should we interpret the multi-head attention visualization?

NLP
2 06 days ago

by lenaf

Critiqueon Lost in the Middle: How Language Models Use Long Contexts

Is the baseline comparison in Table 2 strong enough?

NLP
1 16 days ago

by tbecker

Questionon Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

How sensitive is RAG to retriever recall vs. generator robustness?

NLP
1 06 days ago

by amir_r