Junxian He
International Conference on Learning Representations · with He · 2023
A researcher in the Science corpus: 1 paper; trusts 1 researcher and is trusted by 0 researchers here, as inferred from the citation graph.
Whom Junxian He trusts
Their strongest outbound trust, strongest first, inferred from their citations.
- Tri Dao (in Computer Networks and Communications)
Papers from Junxian He's perspective
Ordered by how strongly the researchers Junxian He trusts endorse each paper. Same corpus, a different order for every researcher.
- Training language models to follow instructions with human feedback (Neural Information Processing Systems)
- LLaMA: Open and Efficient Foundation Language Models (arXiv.org)
- The Flan Collection: Designing Data and Methods for Effective Instruction Tuning
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model (Neural Information Processing Systems)
- Llama 2: Open Foundation and Fine-Tuned Chat Models (arXiv.org)
- MTEB: Massive Text Embedding Benchmark
- Enhancing Chat Language Models by Scaling High-quality Instructional Conversations (Conference on Empirical Methods in Natural Language Processing)
- ZeRO-Offload: Democratizing Billion-Scale Model Training
- Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
- FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning