AI research velocity has grown exponentially in the last 10 years, but the tools and workflows around discovery and application of research have fallen behind.
@askalphaxiv
-
ByteDance Ouro: Scaling Latent Reasoning in Language Models
By
–
New paper from ByteDance Seed: Scaling Latent Reasoning via Looped LMs This paper proposes Ouro, which reuse the same layers to think in latent space instead of dumping long chain-of-thought text 2-3x param efficiency + increased performance via iterative latent computation
-
Kimi-K2: AI tool for research paper analysis and understanding
By
–
Introducing Kimi-K2 for understanding research papers 🚀
— alphaXiv (@askalphaxiv) 6 novembre 2025
Use Kimi-K2 to understand… the Kimi-K2 paper itself
Highlight any section to ask questions and "@" other papers for quick context, comparisons, and benchmark references pic.twitter.com/4a65tQBFaTIntroducing Kimi-K2 for understanding research papers Use Kimi-K2 to understand… the Kimi-K2 paper itself Highlight any section to ask questions and "@" other papers for quick context, comparisons, and benchmark references
-
Language Models are Injective and Invertible with SIPIT
By
–
Hottest paper on AlphaXiv Language Models are Injective and Hence Invertible Every prompt maps to a unique hidden state and can be exactly reconstructed with this paper’s algorithm SIPIT. This means the model’s internal activations are the full prompt in disguise!!
-
Recursive Language Models for Near-Infinite Context Agents
By
–
One of our best talks yet. Thanks @a1zhang for the amazing presentation + Q&A on Recursive Language Models! If you're interested in how we can get agents to handle near-infinite contexts, this one is a must. Watch the recording here!
-
Stanford Method Detects Copied Fine-Tuned AI Models
By
–
Someone stole your model & u can’t prove it? This Stanford paper just showed that you can find out if a model is a copy or finetuned based on your model with just its generated text So if someone yoinks DeepSeek-v3.2 and finetunes it, it’ll leave statistical traces!
-
Personalized arXiv feeds powered by AI recommendations
By
–
Introducing personalized arXiv feeds 🚀
— alphaXiv (@askalphaxiv) 30 octobre 2025
Rate 5 papers, get a feed tailored to your research that learns what you care about
Find the papers you need in seconds, not hours pic.twitter.com/3evDOcBKiOIntroducing personalized arXiv feeds Rate 5 papers, get a feed tailored to your research that learns what you care about Find the papers you need in seconds, not hours
-
Linearizer Collapses Diffusion Model Training to Single Step
By
–
Who Said Neural Networks Aren’t Linear?? In this paper, authors are able to collapse the training of diffusion models down to only 1 step by introducing Linearizer, which sandwiches a linear matrix A between two invertible neural networks!
-
Visualizing Llama 3.1 Tensor Operations Through GGML Debug Output
By
–
The three.js visualization parses the output of llama-cpp's ggml debug output (of unsloth llama 3.1) to directly obtain all the tensor calculations happening under the hood. Operations (MUL_MAT, ROPE, RESHAPE, ADD) are grouped into query, key, value, MLP, and residual stream
-
LlaMA Tensor Trace Tool for Model Analysis
By
–
Fly through LlaMA here! https://
alphaxiv.org/labs/tensor-tr
ace
…