Journal Clubs

📅 Meeting Details

• Frequency: Bi-weekly sessions
• Format: Virtual
• Duration: 60 minutes with Q&A
• Language: English
• Time: Monday 3 PM Beijing, 4 PM JST/KST
• Access link: Please check out journal club channel on our slack.

Past Sessions - 2026

2025-03-16

TBA

2026-03-09

Agent models

• Agentic AI – Physicist Collaboration in Experimental Particle Physics: A Proof-of-Concept Measurement with LEP Open Data (arXiv:2603.05735)
• The Denario project: Deep knowledge AI agents for scientific discovery (arXiv:2510.26887)
• MadAgents (arXiv:2601.21015)
• CoLLM: AI engineering toolbox for end-to-end deep learning in collider analyses (arXiv:2602.06496)

Fine-tuning and Low Rank Adaptations (LoRA)

• LoRA: Low-Rank Adaptation of Large Language Models (arXiv:2106.09685)
• QLoRA: Efficient Finetuning of Quantized LLMs (arXiv:2305.14314)
• Hands-on Large Language Models

2026-02-23

Causal chats

• Bayesian Cosmic Void Finding with Graph Flows (arXiv:2602.14630)
• Revealing the Dark Threads of the Cosmic Web (arXiv:2003.04393)
• AstroAI Asian Network

2026-01-05

QnA on AI for Physics and Physics for AI

Past Sessions - 2025

2025-12-08

Physics, Language Models, and Data

• QCD in Language Models: What do they really know about QCD? (arXiv:2512.02072)
• Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Models (arXiv:2501.05382)

2025-11-24

Lorentz-equivariant Neural Networks

• focused Lorentz Local Canonicalization: How to Make Any Network Lorentz-Equivariant (arXiv:2505.20280)

Fundamental Limit of Jet Tagging Performance

• SURFing to the Fundamental Limit of Jet Tagging (arXiv:2511.15779)

Flow-matching with non-uniform dimension data

• Branching Flows: Discrete, Continuous, and Manifold Flow Matching with Splits and Deletions (arXiv:2511.09465)

2025-10-27

Quantum-Informed Neural Networks

• QINNs: Quantum-Informed Neural Networks (arXiv:2510.17984)

Neural Networks and Renormalization Groups

• focused Dynamic neuron approach to deep neural networks: Decoupling neurons for renormalization group analysis (arXiv:2410.00396)
• The Principles of Deep Learning Theory (arXiv:2106.10165)

Unfolding Detector Effects in Collider Physics

• Generative Unfolding of Jets and Their Substructure (arXiv:2510.19906)

2025-09-29

Classification Performance vs. Robustness in Jet Tagging

• focused The Pareto Frontier of Resilient Jet Tagging (arXiv:2509.19431)

Foundation models for high-energy physics

• Foundation models for high-energy physics (arXiv:2509.21434)

2025-09-15

Double Descent and Overparameterization in Particle Physics Data

• focused Double Descent and Overparameterization in Particle Physics Data (arXiv:2509.01397)
• Double Descent
• Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets (arXiv:2201.02177)

Other Papers

• Higgs Signal Strength Estimation with Machine Learning under Systematic Uncertainties (arXiv:2509.00672)

2025-09-01

Inductive Bias in Foundation Models and World Models (Continued)

• focused What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models (arXiv:2507.06952)

Optical Generative Models

• Optical generative models (arXiv:2410.17970)

Foundation models for Collider Physics - OmniLearn

• Solving Key Challenges in Collider Physics with Foundation Models (arXiv:2404.16091)

2025-08-27 (Wed)

Inductive Bias in Foundation Models and World Models

• focused What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models (arXiv:2507.06952)

2025-08-11

Symbolic Regressions

• focused Angular Coefficients from Interpretable Machine Learning with Symbolic Regression (arXiv:2508.00989)
• Deep symbolic regression for physics guided by units constraints: toward the automated discovery of physical laws (arXiv:2303.03192)
• Class Symbolic Regression: Gotta Fit ‘Em All (arXiv:2312.01816)

2025-07-14

Learning at Criticality

• focused Learning-at-Criticality in Large Language Models for Quantum Field Theory and Beyond (arXiv:2506.03703)

2025-06-30

New Architecture Design for More Human-like NN & Dynamic Sparsity

• focused Continuous Thought Machines (arXiv:2505.05522)
• IAFormer: Interaction-Aware Transformer network for collider data analysis (arXiv:2505.03258)

2025-06-16

Neural Network Compositionality & Mechanistic Interpretability

• focused Break It Down: Evidence for Structural Compositionality in Neural Networks (arXiv:2301.10884)

Other Papers

• Interpreting the structure of multi-object representations in vision encoders (arXiv:2406.09067)
• Tracing Thoughts in Language Models (anthropic)
• Mapping the Mind of Language Models (anthropic)
• Domain Separation Networks (arXiv:1608.06019)

2025-06-02

Neural Thermodynamic Laws for Large Language Model Training

• Exploring how thermodynamic principles can be applied to understand and optimize large language model training processes.
• focused Neural Thermodynamic Laws for LLM Training (arXiv:2505.10559)

Spectral Bias of Neural Networks

• On the Spectral Bias of Neural Networks (arXiv:1806.08734)
• Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains (2006.10739)