#misc
Attention Authors: Updated Practice for Review Articles and Position Papers in arXiv CS Category
https://blog.arxiv.org/2025/10/31/attention-authors-updated-practice-for-review-articles-and-position-papers-in-arxiv-cs-category/
Attention Authors: Updated Practice for Review Articles and Position Papers in arXiv CS Category
https://blog.arxiv.org/2025/10/31/attention-authors-updated-practice-for-review-articles-and-position-papers-in-arxiv-cs-category/
๐ฑ1
#ai
I ran into this quite interesting paper when exploring embeddings of time series.
In the past, the manifold hypothesis has always been working quite well for me regarding physical world data. You just take a model, compress it, do something in the latent space, decode it, damn it works so well. The latent space is so magical.
To me, the hyperparameters for the latent space has always been some kind of battle between the curse of dimensionality and the Whitney embedding theorem.
Then there comes the language models. The ancient word2vec was already amazing. It brings in the questioin of why embeddings works unbelievably well in language models and it bugs me a lot. If you think about it, regardless of the model, embedding has been working so well. This hints that language embeddings might be universal. There is the linear representation hypothesis, but it is weird as it is missing the global structure. This paper provides a bit more clarity. The authors used a lot of assumptions but the proposal is interesting in the sense that the cosine similarity we used is likely a tool that depends on the distance on the manifold of the continuous features in the backstage.
https://arxiv.org/abs/2505.18235v1
I ran into this quite interesting paper when exploring embeddings of time series.
In the past, the manifold hypothesis has always been working quite well for me regarding physical world data. You just take a model, compress it, do something in the latent space, decode it, damn it works so well. The latent space is so magical.
To me, the hyperparameters for the latent space has always been some kind of battle between the curse of dimensionality and the Whitney embedding theorem.
Then there comes the language models. The ancient word2vec was already amazing. It brings in the questioin of why embeddings works unbelievably well in language models and it bugs me a lot. If you think about it, regardless of the model, embedding has been working so well. This hints that language embeddings might be universal. There is the linear representation hypothesis, but it is weird as it is missing the global structure. This paper provides a bit more clarity. The authors used a lot of assumptions but the proposal is interesting in the sense that the cosine similarity we used is likely a tool that depends on the distance on the manifold of the continuous features in the backstage.
https://arxiv.org/abs/2505.18235v1
arXiv.org
The Origins of Representation Manifolds in Large Language Models
There is a large ongoing scientific effort in mechanistic interpretability to map embeddings and internal representations of AI systems into human-understandable concepts. A key element of this...
๐2
#ai
This is more than language models. Somehow many forecasting models also almost fall inside the realm. Somehow the root of this is the latent space. Time series models even classical ones, have enlarged latent space, which is more or less embedding patterns with higher dimensions.
However this paper is a bit fishy. I just can't trust the proof of theorem 2.2.
Language Models are Injective and Hence Invertible
https://arxiv.org/abs/2510.15511
This is more than language models. Somehow many forecasting models also almost fall inside the realm. Somehow the root of this is the latent space. Time series models even classical ones, have enlarged latent space, which is more or less embedding patterns with higher dimensions.
However this paper is a bit fishy. I just can't trust the proof of theorem 2.2.
Language Models are Injective and Hence Invertible
https://arxiv.org/abs/2510.15511
arXiv.org
Language Models are Injective and Hence Invertible
Transformer components such as non-linear activations and normalization are inherently non-injective, suggesting that different inputs could map to the same output and prevent exact recovery of...
๐1
#fun
Lol citing the onion in a research paper...
https://ajba.um.edu.my/index.php/JAT/article/download/11954/7915
Lol citing the onion in a research paper...
https://ajba.um.edu.my/index.php/JAT/article/download/11954/7915
๐1
#dl
Introducing more symmetries in attention
https://github.com/NVIDIA/torch-harmonics
https://neurips.cc/virtual/2025/loc/san-diego/poster/117783
Introducing more symmetries in attention
https://github.com/NVIDIA/torch-harmonics
https://neurips.cc/virtual/2025/loc/san-diego/poster/117783
GitHub
GitHub - NVIDIA/torch-harmonics: Differentiable signal processing on the sphere for PyTorch
Differentiable signal processing on the sphere for PyTorch - NVIDIA/torch-harmonics
๐1
#data
Last year a colleague introduced Marimo to me. It was surprisingly good after the first few days but then I was annoyed by the auto rerun on expensive computations.
Then I bailed out.
This morning I read a blog on this topic and realized there's a switch...
Time to jump in again.
https://docs.marimo.io/guides/configuration/runtime_configuration/#disable-autorun-on-cell-change-lazy-execution
Last year a colleague introduced Marimo to me. It was surprisingly good after the first few days but then I was annoyed by the auto rerun on expensive computations.
Then I bailed out.
This morning I read a blog on this topic and realized there's a switch...
Time to jump in again.
https://docs.marimo.io/guides/configuration/runtime_configuration/#disable-autorun-on-cell-change-lazy-execution
๐1
#ai
Interesting... Going from finite Eucleadian space to Hilbert space
https://openreview.net/forum?id=1b7whO4SfY
Interesting... Going from finite Eucleadian space to Hilbert space
https://openreview.net/forum?id=1b7whO4SfY
openreview.net
Gated Attention for Large Language Models: Non-linearity, Sparsity,...
Gating mechanisms have been widely utilized, from early models like LSTMs and Highway Networks to recent state space models, linear attention, and also softmax attention.
Yet, existing literature...
Yet, existing literature...
๐ฅ1
#ai
What GitHub imagined about everyone creating their own app is almost here. Github Spark is not that good, vercel ship 0 is also buggy. Cloude is doing a fairly good job here.
The other day I needed a special checklist and instead of writing the code myself, I asked Gemini to do it and it was surprisingly good.
---
Build interactive diagram tools | Claude | Claude
https://www.claude.com/resources/use-cases/build-interactive-diagram-tools
What GitHub imagined about everyone creating their own app is almost here. Github Spark is not that good, vercel ship 0 is also buggy. Cloude is doing a fairly good job here.
The other day I needed a special checklist and instead of writing the code myself, I asked Gemini to do it and it was surprisingly good.
---
Build interactive diagram tools | Claude | Claude
https://www.claude.com/resources/use-cases/build-interactive-diagram-tools
Claude Academy
Build interactive diagram tools ยท Claude Academy
From body systems to molecular structures, turn a detailed prompt into a working reference app with the depth and design you specify.
๐1
#misc
Quote from the following article:
> Scientists want AI partnership but can't yet trust it for core research
Introducing Anthropic Interviewer \ Anthropic https://www.anthropic.com/news/anthropic-interviewer
Quote from the following article:
> Scientists want AI partnership but can't yet trust it for core research
Introducing Anthropic Interviewer \ Anthropic https://www.anthropic.com/news/anthropic-interviewer
Anthropic
Introducing Anthropic Interviewer: What 1,250 professionals told us about working with AI
What 1,250 professionals told us about working with AI
๐1
#engineering
Clear and concise intro.
Making Sense of Memory in AI Agents โ Leonie Monigatti
https://www.leoniemonigatti.com/blog/memory-in-ai-agents.html
Clear and concise intro.
Making Sense of Memory in AI Agents โ Leonie Monigatti
https://www.leoniemonigatti.com/blog/memory-in-ai-agents.html
Leonie Monigatti
Making Sense of Memory in AI Agents โ Leonie Monigatti
Learn how to make stateless LLM agents remember conversations, manage context, and implement memory banks.
๐1
#misc
There's always something more exciting to explore in our life. If not, we create new games with new rules. This is what we humans are really good at.
Kosmyna, Nataliya, Eugene Hauptmann, Ye Tong Yuan, Jessica Situ, Xian-Hao Liao, Ashly Vivian Beresnitzky, Iris Braunstein, and Pattie Maes. 2025. โYour Brain on ChatGPT: Accumulation of Cognitive Debt When Using an AI Assistant for Essay Writing Task.โ arXiv [Cs.AI]. arXiv. http://arxiv.org/abs/2506.08872.
There's always something more exciting to explore in our life. If not, we create new games with new rules. This is what we humans are really good at.
Kosmyna, Nataliya, Eugene Hauptmann, Ye Tong Yuan, Jessica Situ, Xian-Hao Liao, Ashly Vivian Beresnitzky, Iris Braunstein, and Pattie Maes. 2025. โYour Brain on ChatGPT: Accumulation of Cognitive Debt When Using an AI Assistant for Essay Writing Task.โ arXiv [Cs.AI]. arXiv. http://arxiv.org/abs/2506.08872.
๐1
#visualization
Broken Chart: discover 9 visualization alternatives โ Dr Dominic Royรฉ
https://dominicroye.github.io/blog/2025-12-14-broken-charts/
Broken Chart: discover 9 visualization alternatives โ Dr Dominic Royรฉ
https://dominicroye.github.io/blog/2025-12-14-broken-charts/
๐1
#ai
It's just conflicting thoughts patched together.
AI Is Changing How We Learn at Work
https://hbr.org/2025/12/ai-is-changing-how-we-learn-at-work
It's just conflicting thoughts patched together.
AI Is Changing How We Learn at Work
https://hbr.org/2025/12/ai-is-changing-how-we-learn-at-work
Harvard Business Review
AI Is Changing How We Learn at Work
As artificial intelligence rapidly transforms the workplace, it is also reshaping how people learn, develop expertise, and form their professional identities. Although gen AI promises to accelerate learning and boost productivity, it risks undermining theโฆ
๐1
#ai
Well, "one engineer one month one million lines of code" -> "who the hell knows what's in there" -> "you need some AI coder architect".
https://www.linkedin.com/posts/galenh_principal-software-engineer-coreai-microsoft-activity-7407863239289729024-WTzf
Well, "one engineer one month one million lines of code" -> "who the hell knows what's in there" -> "you need some AI coder architect".
https://www.linkedin.com/posts/galenh_principal-software-engineer-coreai-microsoft-activity-7407863239289729024-WTzf
๐คฏ1๐คฃ1
#ai
Miao, Tingjia, Jiawen Dai, Jingkun Liu, Jinxin Tan, Muhua Zhang, Wenkai Jin, Yuwen Du, et al. 2025. โPhysMaster: Building an Autonomous AI Physicist for Theoretical and Computational Physics Research.โ arXiv [Cs.AI]. arXiv. https://doi.org/10.48550/arXiv.2512.19799.
Miao, Tingjia, Jiawen Dai, Jingkun Liu, Jinxin Tan, Muhua Zhang, Wenkai Jin, Yuwen Du, et al. 2025. โPhysMaster: Building an Autonomous AI Physicist for Theoretical and Computational Physics Research.โ arXiv [Cs.AI]. arXiv. https://doi.org/10.48550/arXiv.2512.19799.
arXiv.org
PhysMaster: Building an Autonomous AI Physicist for Theoretical...
Advances in LLMs have produced agents with knowledge and operational capabilities comparable to human scientists, suggesting potential to assist, accelerate, and automate research. However,...
๐1
#ai
โๅ้ขๅฎถๆจกๅโ
Zhang, Alex L., Tim Kraska, and Omar Khattab. 2025. โRecursive Language Models.โ arXiv [Cs.AI]. arXiv. https://doi.org/10.48550/arXiv.2512.24601.
โๅ้ขๅฎถๆจกๅโ
Zhang, Alex L., Tim Kraska, and Omar Khattab. 2025. โRecursive Language Models.โ arXiv [Cs.AI]. arXiv. https://doi.org/10.48550/arXiv.2512.24601.
arXiv.org
Recursive Language Models
We study allowing large language models (LLMs) to process arbitrarily long prompts through the lens of inference-time scaling. We propose Recursive Language Models (RLMs), a general inference...
๐1
#misc
No comment, but you (tailwind) won't win. /s
https://github.com/tailwindlabs/tailwindcss.com/pull/2388
No comment, but you (tailwind) won't win. /s
https://github.com/tailwindlabs/tailwindcss.com/pull/2388
GitHub
feat: add llms.txt endpoint for LLM-optimized documentation by quantizor ยท Pull Request #2388 ยท tailwindlabs/tailwindcss.com
Add /llms.txt endpoint that serves a concatenated, text-only version of all Tailwind CSS documentation pages optimized for Large Language Model consumption.
Extract text from MDX files, removing J...
Extract text from MDX files, removing J...
๐ค1