"A Complete Guide to Spherical Equivariant Graph Transformers" This paper explains how to make neural networks that understand 3D geometry the way physics does, so models for molecules and proteins give the same and correct answers no matter how you rotate the structure.
@askalphaxiv
-
Gemini 3 Flash Enables Research Paper Analysis and Comparison
By
–
Introducing Gemini 3 Flash for understanding research papers 🚀
— alphaXiv (@askalphaxiv) 17 décembre 2025
Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references pic.twitter.com/u3pZc78mn5Introducing Gemini 3 Flash for understanding research papers Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references
-
Small Model Outperforms DeepSeek-r1 With Recursive Reasoning
By
–
Recursive reasoning beats multi-billion-parameter models You can now easily train your own 7M param model from scratch and outperform DeepSeek-r1 on ARC-AGI 1 We provide a simple speedrun script that handles setup, training, and eval in one go.
-
Open-source AI paper implementation with pretrained weights released
By
–
Checkout our adaptation of @jm_alexia
's work here: https://
github.com/alphaXiv/paper
-implementations
… We also provide pretrained weights for Sudoku, Maze, and ARC-AGI for easy evaluation! -
Google’s Scaling Laws for Multi-Agent AI Systems
By
–
Google’s "scaling law" for building agentic systems This paper shows when adding more AI agents helps.. and when it backfires They empirically measured coordination costs, error propagation, and task structure, grounding multi-agent design from heuristics into predictive rules
-
Error-Free Linear Attention Surpasses Hybrid Attention Methods
By
–
With the recent hybrid attention releases from MiniMax, Qwen, Kimi, and NVIDIA, this paper introduces Error-Free Linear Attention that could top them all This new technique has a stable linear-time attention that's better than any linear attention variants and also DeltaNet!
-
NeurIPS Panel on AI for Science Gains Major Media Coverage
By
–
Thrilled to see takeaways from our NeurIPS panel discussion mentioned in NBC! Community interest in AI for Science has skyrocketed Check out the full story below @jeffclune @_perloj
-
Dynamic erf improves normalization-free Transformers architecture
By
–
Common conception, shattered again. Normalization isn’t fundamental to Transformers, and this approach keeps getting better This paper introduces Dynamic erf (Derf), which further improves normalization-free Transformers With strong empirical results while generalizing better
-
ArXiv paper abstract on machine learning or scientific research
By
–
https://
alphaxiv.org/abs/2511.21140 -
Correcting LLM-as-a-Judge Bias Statistical Calibration Method
By
–
How to Properly do LLM-as-a-Judge Raw LLM-as-a-Judge scores are inherently biased due to how LLMs would often make mistakes This paper proposes a simple statistical method to correct the scores and calculate valid confidence intervals via a human-verified calibration set