Shizhe Diao
arXiv.org · with Belcák · 2025
A researcher in the Science corpus: 2 papers; trusts 1 researcher and is trusted by 0 researchers here, as inferred from the citation graph.
Whom Shizhe Diao trusts
Their strongest outbound trust, strongest first, inferred from their citations.
- Daniel T. Gillespie (in Statistical and Nonlinear Physics)
Papers from Shizhe Diao's perspective
Ordered by how strongly the researchers Shizhe Diao trusts endorse each paper. Same corpus, a different order for every researcher.
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
- LoRA: Low-Rank Adaptation of Large Language Models (International Conference on Learning Representations)
- Least-to-Most Prompting Enables Complex Reasoning in Large Language Models
- Structured Denoising Diffusion Models in Discrete State-Spaces
- Improving language models by retrieving from trillions of tokens
- Toolformer: Language Models Can Teach Themselves to Use Tools (Neural Information Processing Systems)
- Attention is All you Need (Neural Information Processing Systems)
- Approximate accelerated stochastic simulation of chemically reacting systems
- A Continuous Time Framework for Discrete Denoising Models (Neural Information Processing Systems)
- Instruction-Following Evaluation for Large Language Models
Their papers
- Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding (2025) — 345 citations
- Small Language Models are the Future of Agentic AI (2025) — 310 citations