I am Xiao Liu, a fourth-year PhD student in Tsinghua University since 2021, expected to graduate on June 2026.
-
🔭 Interested in Machine Learning, Natural Language Processing, and Foundation Models.
-
🌱 Find my up-to-date publication list in Google Scholar! Some of my proud works as lead authors:
Large Language Model (LLM) Training and Prompt Learning
- P-tuning and P-tuning v2 (ACL'22): pioneer works on prompt tuning
- GLM-130B (ICLR'23): an open bilingual (Enligsh & Chinese) pre-trained model with 130 billion parameters based on GLM (ACL'22); better than GPT-3 175B on LAMBADA and MMLU.
- ChatGLM-6B & ChatGLM2-6B & ChatGLM3-6B & GLM-4: a family of open bilingual dialogue language models, over 14,000,000 global downloads. Receiving
,
,
, and
GitHub Stars!
- WebGLM (KDD'23): an efficient web-enhanced question answering system based on GLM-10B, outperforming WebGPT-13B and approaching WebGPT-175B performance in human evaluation.
Foundational Agents For Real-world Challenging Missions
- AgentBench (ICLR'24): the first systematic multi-dimensional benchmark to evaluate LLMs as Agents in 8 distinct environments deriving from real-world practical missions.
- AutoWebGLM (KDD'24): a strong web navigating agent constructed upon ChatGLM-3-6B, outperforming prompted GPT-4 on Mind2Web, WebArena, and our constructed new dataset AutoWebBench.
- VisualAgentBench (ICLR'25): a comprehensive framework to train and test Large Multimodal Models (LMMs) to serve as visual foundation agents.
- WebRL (ICLR'25): self-evolving online curriculum RL transform open LLMs to outperform GPT-4-Turbo on Web Agent tasks by 160%.
- AndroidLab (ACL'25): training and systematic benchmarking android autonomous agents.
- AutoGLM: autonomous foundation agents for GUIs, the first Phone Use and Web Browser Use agent family.
Alignment and Scalable Oversights over LLMs and Diffusers
- ImageReward (NeurIPS'23): the first general-purpose text-to-image human preference reward model (RM) for RLHF, outperforming CLIP/BLIP/Aesthetic by 30% in terms of human preference prediction.
- BPO (Black-box Prompt Optimization, ACL'24): a novel direction to align LLMs via preference-aware prompt optimization. Improving ChatGPT, Claude, LLaMA on human preference's win rates by 20%+ without training them.
- AlignBench (ACL'24): the first comprehensive benchmark on evaluating LLMs' Chinese alignment, deriving from ChatGLM's online real scenarios. Adopted by top Chinese LLMs (ChatGLM, Qwen, DeepSeek, Yi, Baichuan, Abab, and etc.)
- SPaR (ICLR'25): Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models
Self-supervised Learning and Reasoning
- Self-supervised Learning: Generative or Contrastive (TKDE'21): one of the most cited survey on self-supervised learning
- SelfKG (WWW'22): self-supervised alignment can be comparable to supervised ones, Best Paper Nominee in WWW 2022.
- kgTransformer (KDD'22): pre-training knowledge graph transformers with mixture-of-experts (MoE) for complex logical reasoning
-
🤔 Dedicated to building next-generation of AI systems via both Large Pre-trained Model and Symbolic Agent Reasoning.
-
💬 Feel free to drop me an email for:
- Any form of collaboration
- Any issue about my works or code
- Interesting ideas to discuss or just chatting