Xiaodong Liu
- Papers
- 24
Cite
Notes
Only stored in your browser.
Authored papers
24SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks
arXiv 2026
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
preprint
FlowRL: Matching Reward Distributions for LLM Reasoning
arXiv 2025
DeepSeek-V3 Technical Report
arXiv 2024
DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
arXiv 2024
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
arXiv 2024
BayLing 2: A Multilingual Large Language Model with Efficient Language Alignment
arXiv 2024
Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities
arXiv 2024
Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning
arXiv 2024
DefSent+: Improving sentence embeddings of language models by projecting definition sentences into a quasi-isotropic or isotropic vector space of unlimited dictionary entries
arXiv 2024
Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering
arXiv 2024
Model Editing for LLMs4Code: How Far are We?
arXiv 2024
Augmenting Language Models with Long-Term Memory
augmenting-language-models-with-long-term
Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs
arXiv 2023
Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers
arXiv 2023
Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
arXiv 2022
AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning
arXiv 2022
Language Models as Inductive Reasoners
arXiv 2022
AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation
arXiv 2022
Taming Sparsely Activated Transformer with Stochastic Experts
taming-sparsely-activated-transformer-with-1
LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot Learners
list-lite-self-training-makes-efficient-few
Generation-Augmented Retrieval for Open-domain Question Answering
ACL 2021 5
On the Variance of the Adaptive Learning Rate and Beyond
ICLR 2020 1
SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization
smart-robust-and-efficient-fine-tuning-for-1
Affiliations
Frequent co-authors
10from 24 papers