Lin Gui

Thanks to #ICLR2026 for giving me the chance to expand my horizons. Just got assigned some papers way outside my domain…

Thanks for the suggestion. BTW, do remember to estimate the reviewer's time zone. Don’t time your reply to land exactly 12 hours after their comment. No one likes openreview notifications at midnight.

@iclr_conf In my batch, it seems like the judgement of AI geneated reviews is purely based on the decisions from pangram. Do you think it is reliable evidence to desk reject so many submissions? At least in my batch, 2 out of 7 reviews flagged by pangram are not from AI

We want to update the community on our response to concerns about low-quality and LLM-generated papers and reviews, and steps we are taking & will be taking blog.iclr.cc/2025/11/19/icl… We will follow up with another blog later on desk rejections and reviewer-related decisions!

@alec_helbling May I include this in my teaching slides? Very comprehensive!

Data often lie on a low-dimensional manifold embedded in a high-dimensional space. But these manifolds are often highly non-linear, making linear dimensionality reduction methods like PCA insufficient. This has motivated the development of non-linear dimensionality reduction.

Remember the world is bigger than your ICLR reviews

@xuandongzhao Who is Summary?

Welcome to the funniest chapter of conference cycles

@gan_chuang @miiche_yang Congratulations! May I invite him to share this work with our group? We have many students who are working on the topic of latent reasoning.

Congratulations to my student @miiche_yang for winning the Best Paper Award at the ICCV KnowledgeMR Workshop for his work on Machine Mental Imagery! Code: github.com/UMass-Embodied…

New work from our KCL NLP group @kclnlp in collaboration with the Centre for AI @ASTRAZENECAUK ! We introduce Latent Refinement Decoding (LRD), a two-stage parallel generation framework that achieves up to 10.6× faster decoding while improving accuracy across coding and reasoning tasks. LRD addresses key limitations of diffusion-inspired approaches by maintaining distributional mixtures and iterative feedback for more globally consistent generation. 🧠 A strong and versatile alternative to standard autoregressive decoding! Paper: huggingface.co/papers/2510.11… #AI #NLP #LLMs #GenerativeAI #Research

🚀 The KCL NLP Group is heading to #ACL2025 We’re excited to present our latest work on LLM reasoning, interpretability, personalization, and many other topics. 📍 Catch us in Vienna — stop by, say hi, and let’s talk!

@CSProfKGD @mabdelhack Our coauthor, who is Chinese but completed her education in the UK since high school and has no prior research experience in China, is still awaiting the outcome of her visa application.

@mabdelhack It appears Canada visa issues. All authors from Chinese institutes.

Three #ICML2025 talks in and none of the authors showed due to visa issues 🤨

Steer LLM reasoning using a single continuous token, without relying on SFT or RL. Check out our #ICML2025 poster E-2024 from the KCL NLP group: Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration. Paper: arxiv.org/abs/2505.24688 GitHub: github.com/alickzhu/Soft-…