Welcome to Siriuslala’s Blog! 👋

It is the responsibility of intellectuals to speak the truth and expose lies.

-- Noam Chomsky

Hi, I'm Yueyan Li, just call me Sirius! I am a reseacher on machine learning, deep learning and anything cool with that. My interest focuses on interpretability and its applications, cognitive science and linguistics. The blog is a place where I share my thoughts, ideas and some cool stuff I found. Hope you'll enjoy it!

- Publications can be found here.

- Details about my basic information can be found in the About page.

If you have any questions or suggestions about my blogs or simply want for a communication, feel free to comment below my blogs or contact me via my work email or my personal email.

A Collection of My Publications

* Equal contribution ✉ Corresponding author Technical Report Seedance 2.0: Advancing Video Generation for World Complexity Team Seedance Arxiv, 2026 PDF ICLR 2026 Reading Images Like Texts: Sequential Image Understanding in Vision-Language Models Yueyan Li*, Chenggong Zhao, Zeyuan Zhang, Caixia Yuan✉, Xiaojie Wang International Conference on Learning Representations (ICLR), 2026 PDF Code arxiv Sparse Model Diffing via Dynamic Circuits Yueyan Li*, Wenhao Gao, Caixia Yuan✉, Xiaojie Wang ArXiv, 2026 PDF Code Technical Report AutoGLM: Autonomous Foundation Agents for GUIs Team AutoGLM Arxiv, 2024 PDF Code EMNLP 2024 ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline Yifan Xu*, Xiao Liu, Xinghan Liu, Zhenyu Hou, Yueyan Li, Xiaohan Zhang, Zihan Wang, Aohan Zeng, Zhengxiao Du, Zhao Wenyi, Jie Tang, Yuxiao Dong✉ Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024 PDF Code Technical Report ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools Team GLM Arxiv, 2024 PDF Code ICML 2026 EntroKV: An Entropy-aware Memory Manager for KV cache Compression Wenhao Gao*, Haoran Cao, Yueyan Li, Caixia Yuan, Xiaojie Wang✉ ICML, 2026 Code

Thinking and Reasoning

A curated overview of LLM reasoning, post-training, reinforcement learning, and related resources.

LLM Agents

A running collection of notes, papers, and benchmarks around LLM agents, agentic RL, GUI agents, and deep research systems.

Interpretability (& other areas) for Multimodal Models

A curated reading list on multimodal interpretability, information flow, diffusion models, and related research threads.

一些语言学的梗和有意思的知识

This post is written in Chinese. If you don’t know Chinese, you can learn it lol. (Sorry for this because simply translating the post into English may not be enough for you to understand). 语言学乐子皮钦语 (pidgin) 大家对那些 1.言语中不时夹杂着英文单词 2.装/凡尔赛的人表现出一种厌恶。例如，下面是某恋综里的一段留子对话的名场面： ...

Possible Research Areas in Mechanistic Interpretability

An overview of mechanistic interpretability directions, including circuit discovery, SAEs, steering vectors, and model diffing.

Exploring Emotional Features in GPT2-Small

🎶Code in this post can be found at the jupyter notebook in my “saeExploration” repo. Find features that reflect positive emotions To find the features related to a specific emotion, I write five sentences containing the key words for each emotion. For example, for happy emotions I have: 1 2 3 4 5 prompt_happy = ["I'll be on a vacation tomorrow and I'm so happy.", "My mombrings home a new puppy and I'm so happy.", "I'm so glad I got the job I wanted.", "I feel so happy when I'm with my friends.", "I'm so happy I got the promotion I wanted.",] I choose to look for features that reflect happiness and sadness. Apart from that, I also wonder if the feature that reflects excitedness has something to do with the one that reflects happiness (they are alike from the semantic level at least.) ...

A Brief Introduction to Mechanistic Interpretability Research

⚠️ Warnings This post was written when I first delved into this area, and it hasn’t been updated for a long time. Thus there might be a lot of errors. I’m still interested in interpretability and its applications. I’ll write something new and interesting later ~ 💡 This post is accompanied with another post, which contains specific content in this area. ...