ICLR 2025 BlogPosts Submissions

Building Blocks of Differentially Private Training
Mahmoud Hegazy, Aymeric Dieuleveut
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
An Illustrated Guide to Automatic Sparse Differentiation
Adrian Hill, Guillaume Dalle, Alexis Montoison
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
Reexamining the Aleatoric and Epistemic Uncertainty Dichotomy
Michael Kirchhof, Gjergji Kasneci, Enkelejda Kasneci
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
Restating the Proof of Linear Convergence for Linear GNNs
Huayi Tang, Yuhe Guo, Yong Liu, Zhewei Wei
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
Positional Embeddings in Transformer Models: Evolution from Text to Vision Domains
Abhinav Kumar, Adesh Gupta, Shivank Garg, Mansi Gupta
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
How to visualize training dynamics in neural networks
Michael Y. Hu, Shreyans Jain, Sangam Chaulagain, Naomi Saphra
- Published: 23 Jan 2025, Last Modified: 01 Apr 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
Repurposing in AI: A Distinct Approach or an Extension of Creative Problem Solving?
Aissatou Diallo, Antonis Bikakis, Luke Dickens, Anthony Hunter, Rob Miller
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
Fine-Tuning Token-Based Large Multimodal Models: What Works, What Doesn’t and What's Next
Zhulin Hu, Yan Ma, Jiadi Su, Ethan Chern, Pengfei Liu
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
Can LLM Simulations Truly Reflect Humanity? A Deep Dive
Qian Wang, Zhenheng Tang, Bingsheng He
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
Open-Source vs Close-Source: The Context Utilization Challenge
Litu Ou
- Published: 26 Feb 2025, Last Modified: 30 Mar 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
Multi-modal Learning: A Look Back and the Road Ahead
Divyam Madaan, Sumit Chopra, Kyunghyun Cho
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
Understanding Model Calibration - A gentle introduction and visual exploration of calibration and the expected calibration error (ECE)
Maja Pavlovic
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
Lost in Prediction: Why Social Media Narratives Don't Help Macroeconomic Forecasting?
Almog Gueta, Roi Reichart, Amir Feder, Ariel Goldstein, Zorik Gekhman
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
Do not write that jailbreak paper
Javier Rando
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
The Illustrated AlphaFold
Elana Simon, Jake Silberg
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
Do vision models perceive objects like toddlers ?
Arthur Aubret, Jochen Triesch
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
On LLM Knowledge Distillation - A Comparison between Forward KL and Reverse KL
Yihan Cao, Yanbin Kang
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
Flow With What You Know
Scott H. Hawley
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
Steering LLMs' Behavior with Concept Activation Vectors
Ruixuan Huang, Shuai Wang
- Published: 26 Feb 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
Why RoPE Struggles to Maintain Long-Term Decay in Long Sequences?
Wei Shen, Chao Yin, Yuliang Liu, Zikai Xiao, Xiaonan He, WangYan
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
Towards more rigorous evaluations of language models
Desi R. Ivanova, Ilija Ilievski, Momchil P. Konstantinov
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
How do we interpret the outputs of a neural network trained on classification?
Yudi Xie
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
A primer on analytical learning dynamics of nonlinear neural networks
Rodrigo Antonio Carrasco-Davis, Erin Grant
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone
Mechanistic Interpretability Meets Vision Language Models: Insights and Limitations
Yiming Liu, Yuhui Zhang, Serena Yeung-Levy
- Published: 23 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Blogpost Track
- Readers: Everyone