Stanford UG Courses Index

Last edited: April 4, 2026

Stanford UG Y1, Aut

Stanford UG Y1, Win

Stanford UG Y1, Spr

Stanford UG Y2, Aut

Stanford UG Y2, Win

Stanford UG Y2, Spr

Stanford UG Y3, Aut

Stanford UG Y3, Win

Stanford UG Y3, Spr

Geology Index

Stanford UG Talks

Date	Topic	Presenter	Link
<2023-09-20 Wed>	UG Research Program	Brian Thomas	Stanford UG Research Program
<2023-09-28 Thu>	Bld an Ecosystem, Not Monolith	Colin Raffel	Build a System
<2023-10-05 Thu>	Training Helpful CHatbots	Nazeen Rajani	Training Helpful Chatbots
<2023-10-26 Thu>	AI Intepretability for Bio	Gasper Begus	AI Intepretability
<2023-11-02 Thu>	PT Transformers on Long Seqs	Mike Lewis	Pretraining Long Transformers
<2023-11-07 Tue>	Transformers!	A. Vaswani	Transformers
<2023-11-09 Thu>	Towards Interactive Agents	Jessy Lin	Interactive Agent
<2023-11-16 Thu>	Dissociating Language and Thought	Anna Ivanova	Dissociating Language and Thought
<2024-01-11 Thu>	Language Agents	Karthik Narasimhan	Language Agents with Karthik
<2024-02-01 Thu>			Pretraining Data
<2024-02-08 Thu>	value alignment	Been Kim	LM Alignment
<2024-02-15 Thu>	model editing	Peter Hase	Knowledge Editing
<2024-07-18 Thu>			Knowledge Localization
<2024-11-11 Mon>	Presentations	Sydney Katz	Presentations
<2025-01-06 Mon>	Video Generation with Learned Prior	Meenakshi Sarkar	Priors
<2025-01-06 Mon>	Theoretical Drone Control		Sliding Mode UAV Control
<2025-01-09 Thu>	VLM to Agents	Tao Yu	VLM to Agents
<2025-01-13 Mon>	Social RL	Natasha Jaques	Social Reinforcement Learning
<2025-02-10 Mon>	Model Predictive Control + Prompting	Gabriel Maher	LLM MPC
<2025-03-03 Mon>			Planning for Learning
<2025-03-06 Thu>	Theorem Proving		Self-Play Conjection Generalization
<2025-04-10 Thu>	Safety for Trucks	Safety for Autonomous Trucking
<2025-08-04 Mon>	Collaborate Multiagent DM	Collaborative Multiagent DM
<2025-09-22 Mon>	AI Safety Talks	AI Safety Annual Meeting
<2025-10-02 Thu>	Pretraining under infinite compute		Limited Samples and Infinite Compute
<2025-10-06 Mon>	Mel Krusniak	Decisions.jl
<2025-10-11 Sat>	SISL Flash Talks	SISL Talks
<2025-10-16 Thu>	Predicting Scaling Performance
<2025-12-08 Mon>	mixed-autonomy traffic with LLMS	mixed-autonomy traffic with LLMs
<2026-01-05 Mon>	AI Incidents Policy	AI Incidents Policy
<2026-01-12 Mon>	Reliable RL	Reliable RL
<2026-01-15 Thu>	Words to Concepts	Words to Concepts
		Zen’s Defense
<2026-03-30 Mon>	multi-agent LLM	Multi-Agent LLMs

Contacts

Talk Contacts

EMNLP2025 Index

Last edited: December 12, 2025

Talks

Posters

Takes

although parsing maybe dead for natural language, structure helps parse scientific information (i.e. drugs, molecules, proteins, etc.)
two idea: 1) how to formalize approach mathematically 2) what can LMs do that humans can’t do?
information-rich statefulness + constraints for pruning space is the unlock for ability to build on previous results; i.e. “critical thinking”

Tasks to Do

EMNLP2025 Fan: medium is not the message: I wonder if we can remove keyboard based signals from BM25 using this method
EMNLP2025 Xu: tree of prompting: a bunch of multi-hop retrieval datasets to benchmark for RAG-DOLL
EMNLP2025 Bai: understanding and leveraging expert specialization of context faithfulness: a good set of retrieval benchmarks

Tasks Can Do

EMNLP2025 Keynote: Heng Ji: “protein LLM requires early exit to capture dynamical Beauvoir”; what if we Mixture of Depth a protein LM?
EMNLP2025 Hutson: measuring informative of open and questions: formalize this as a rho– POMDP , or use actual value of information measures with Belman backup
EMNLP2025 Karamanolakis: interactive machine teaching: use MCTS UCB to pick the next set of constitutions to optimize for
EMNLP2025 Yu: Long-Context LM Fail in Basic Retrieval: I wonder how thoughtbubbles do on the dataset
EMNLP2025 Bai: understanding and leveraging expert specialization of context faithfulness: could be interesting using the same freeze/clamping technique for cultural work
EMNLP2025 Vasu: literature grounded hypothesis generation: maybe could use its same hypothesis generation pipeline for RAG
EMNLP2025Li: enhancing RAG RESPONSE evaluator: maybe could be useful to use to evaluate edge rewards for RAGDOLL

Houjun's Academic Home Page

Last edited: December 12, 2025

👋 Howdy, I'm Houjun Liu!

I’m a third-year coterminal MSCS and BSCS student in the Computer Science Department at Stanford University, grateful to be advised by Prof. Mykel Kochenderfer. In the course of my research, I have also had the fortunate opportunity to work with Stanford NLP under Prof. Chris Manning, CMU TalkBank under Prof. Brian MacWhinney, and Prof. Xin Liu at UC Davis Engineering. I am affiliated with the Stanford NLP Group and Stanford Intelligent Systems Lab.