alphaXiv's banner
alphaXiv's profile picture

alphaXiv

@askalphaxiv • 53,622 subscribers

High fidelity research

Shorts

Introducing autoresearch for arXiv papers: replicate and experiment on any arXiv paper using an army of Claude/Codex agents For post-training, your agents can use Tinker to launch concurrent RL runs while you watch your experiment tree grow Try it out now on OpenResearch:

Introducing autoresearch for arXiv papers: replicate and experiment on any arXiv paper using an army of Claude/Codex agents For post-training, your agents can use Tinker to launch concurrent RL runs while you watch your experiment tree grow Try it out now on OpenResearch:

59,659 views

Transform a research idea into a paper end-to-end Turn Claude Code or Codex into research agents that can build an experiment tree + write LaTex to summarize everything they did and watch it all happen live in one workspace Try it out now with /write-paper on OpenResearch:

Transform a research idea into a paper end-to-end Turn Claude Code or Codex into research agents that can build an experiment tree + write LaTex to summarize everything they did and watch it all happen live in one workspace Try it out now with /write-paper on OpenResearch:

50,161 views

The problem with X dominating science communication is simple Unless you go viral, consequential work disappears We built a new-age research feed that surfaces preprints, blogs, and researchers to the right audience. Follow alex zhang Graham Neubig Samuel Schmidgall and more on alphaXiv!

The problem with X dominating science communication is simple Unless you go viral, consequential work disappears We built a new-age research feed that surfaces preprints, blogs, and researchers to the right audience. Follow alex zhang Graham Neubig Samuel Schmidgall and more on alphaXiv!

14,270 views

We used DeepSeek-V3 to classify every AI paper on arXiv by topic (agents, VLMs, etc) 🚀 Now you can instantly filter to see what's trending in each area 🚨

We used DeepSeek-V3 to classify every AI paper on arXiv by topic (agents, VLMs, etc) 🚀 Now you can instantly filter to see what's trending in each area 🚨

141,752 views

Introducing Discord for research Discord was built for gamers. What about researchers? We’ve built a platform where researchers can discover communities, engage in paper discussions, and connect with academics who share your interests - all in one dedicated space.

Introducing Discord for research Discord was built for gamers. What about researchers? We’ve built a platform where researchers can discover communities, engage in paper discussions, and connect with academics who share your interests - all in one dedicated space.

66,014 views

Tiny Recursive Models: A tiny 7M parameter model that recursively refines its answer beats LLMs 100x larger on hard puzzles like ARC-AGI We independently reproduced the paper, corroborated results, and released the weights + API access for those looking to benchmark it 🔍

Tiny Recursive Models: A tiny 7M parameter model that recursively refines its answer beats LLMs 100x larger on hard puzzles like ARC-AGI We independently reproduced the paper, corroborated results, and released the weights + API access for those looking to benchmark it 🔍

52,807 views

Paper discussion threads get easily lost on X Introducing the alphaXiv social tab 🚀 Track all notable external threads for any paper and filter for the most discussed papers on X!

Paper discussion threads get easily lost on X Introducing the alphaXiv social tab 🚀 Track all notable external threads for any paper and filter for the most discussed papers on X!

13,323 views

Introducing benchmark tracking across all of arXiv With thousands of models and benchmarks out there, it's impossible to track what's actually state-of-the-art We now index results from millions of papers to surface which models are SOTA according to open source research!

Introducing benchmark tracking across all of arXiv With thousands of models and benchmarks out there, it's impossible to track what's actually state-of-the-art We now index results from millions of papers to surface which models are SOTA according to open source research!

10,892 views

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

arXiv -> quickarXiv Papers are often written in convoluted language that is hard to understand Swap arXiv -> quickarXiv on any paper URL to get an instant blog with figures, insights, and explanations. Now extracted with Z.ai's GLM OCR 🚀 Also includes code + author tweet
0:27
askalphaxiv's profile picture

arXiv -> quickarXiv Papers are often written in convoluted language that is hard to understand Swap arXiv -> quickarXiv on any paper URL to get an instant blog with figures, insights, and explanations. Now extracted with Z.ai's GLM OCR 🚀 Also includes code + author tweet

alphaXiv

73,135 views • 6 days ago

If doomscrolling X is part of your research workflow, we built something for you. Introducing Paperscrolling 🚀 Get the most trending research with key ideas, figures, and audio explanations from alphaXiv Briefs
0:30
askalphaxiv's profile picture

If doomscrolling X is part of your research workflow, we built something for you. Introducing Paperscrolling 🚀 Get the most trending research with key ideas, figures, and audio explanations from alphaXiv Briefs

alphaXiv

125,965 views • 13 days ago

Introducing autoresearch for arXiv papers Change 'arxiv' to 'autoarxiv' in any paper URL An agent deploys to resolve setup issues on the codebase, run a minimal reproduction, and estimate full replication cost. Read more below
0:44
askalphaxiv's profile picture

Introducing autoresearch for arXiv papers Change 'arxiv' to 'autoarxiv' in any paper URL An agent deploys to resolve setup issues on the codebase, run a minimal reproduction, and estimate full replication cost. Read more below

alphaXiv

486,045 views • 2 months ago

Introducing GLM 5.2 for autoresearch GLM 5.2 is the first open weights model we've tried on our autoresearch pipeline that's proven capable for real research tasks. With Fable 5's restrictions on research, having an open weights alternative is a huge win for open source Watch it carry out fully async vs colocated sync RL training on Harbor code contests across two 8xH100 nodes on top of SkyRL. Resolves setup issues, tracks runs to completion, and produces a full comparison of throughput and reward stability
0:48
askalphaxiv's profile picture

Introducing GLM 5.2 for autoresearch GLM 5.2 is the first open weights model we've tried on our autoresearch pipeline that's proven capable for real research tasks. With Fable 5's restrictions on research, having an open weights alternative is a huge win for open source Watch it carry out fully async vs colocated sync RL training on Harbor code contests across two 8xH100 nodes on top of SkyRL. Resolves setup issues, tracks runs to completion, and produces a full comparison of throughput and reward stability

alphaXiv

271,663 views • 2 months ago

Introducing GLM-5.3 Flash for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references, powered by Z.ai
0:34
askalphaxiv's profile picture

Introducing GLM-5.3 Flash for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references, powered by Z.ai

alphaXiv

17,430 views • 6 days ago

Introducing MCP for arXiv Let your research agents stand on the shoulders of giants Fast multi-turn retrieval, keyword search, and embedding search tools across millions of arXiv papers 🚀
0:39
askalphaxiv's profile picture

Introducing MCP for arXiv Let your research agents stand on the shoulders of giants Fast multi-turn retrieval, keyword search, and embedding search tools across millions of arXiv papers 🚀

alphaXiv

276,888 views • 5 months ago

Introducing autoresearch with GPT 5.6 We had GPT 5.6 Sol reproduce the key findings from “Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in LLM Finetuning” Compared to GPT-5.5 and even Fable 5, GPT-5.6 stayed more focused on a few, critical experiments and spent less time on peripheral details. It also asked fewer “clarification” questions and independently resolved ambiguities instead of pushing them back to us OpenAI pushing the boundaries of the automated research loop with models that don’t have handcuffs
0:23
askalphaxiv's profile picture

Introducing autoresearch with GPT 5.6 We had GPT 5.6 Sol reproduce the key findings from “Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in LLM Finetuning” Compared to GPT-5.5 and even Fable 5, GPT-5.6 stayed more focused on a few, critical experiments and spent less time on peripheral details. It also asked fewer “clarification” questions and independently resolved ambiguities instead of pushing them back to us OpenAI pushing the boundaries of the automated research loop with models that don’t have handcuffs

alphaXiv

88,164 views • 1 month ago

GPT 5.6 Sol can one-shot convert an arXiv paper into an interactive Marimo notebook! Great for papers best understood hands on (lots of fun examples in interpretability, inference engineering, agent harnesses, benchmarking, and more) Play around with the notebook, inspect the code, or try the same workflow with your own agents below
0:26
askalphaxiv's profile picture

GPT 5.6 Sol can one-shot convert an arXiv paper into an interactive Marimo notebook! Great for papers best understood hands on (lots of fun examples in interpretability, inference engineering, agent harnesses, benchmarking, and more) Play around with the notebook, inspect the code, or try the same workflow with your own agents below

alphaXiv

85,280 views • 1 month ago

Introducing LinkedIn for researchers 🚀 LinkedIn optimizes for engagement bait. What about actual research? We aggregated papers, affiliations, experiences, and coauthors to create the most comprehensive profile for every AI researcher You can now ask questions like “Who’s working on automated math discovery at DeepMind?” or "Which researchers are working on world models in San Francisco?" Claim your profile below👇
0:53
askalphaxiv's profile picture

Introducing LinkedIn for researchers 🚀 LinkedIn optimizes for engagement bait. What about actual research? We aggregated papers, affiliations, experiences, and coauthors to create the most comprehensive profile for every AI researcher You can now ask questions like “Who’s working on automated math discovery at DeepMind?” or "Which researchers are working on world models in San Francisco?" Claim your profile below👇

alphaXiv

36,126 views • 19 days ago

If you're using Claude Code for research: stop making it read directly from PDFs We've introduced a SKILL.md that fetches structured, AI-friendly paper overviews from alphaXiv 👀
0:22
askalphaxiv's profile picture

If you're using Claude Code for research: stop making it read directly from PDFs We've introduced a SKILL.md that fetches structured, AI-friendly paper overviews from alphaXiv 👀

alphaXiv

246,817 views • 5 months ago

Looking for a fun weekend read? Introducing the Illustrated ICML 🌎 We indexed all 6000+ ICML papers and built a visual way to explore the whole landscape Search your favorite topics, open a cluster, and dive right in Inspired by Jay Alammar
0:34
askalphaxiv's profile picture

Looking for a fun weekend read? Introducing the Illustrated ICML 🌎 We indexed all 6000+ ICML papers and built a visual way to explore the whole landscape Search your favorite topics, open a cluster, and dive right in Inspired by Jay Alammar

alphaXiv

89,957 views • 2 months ago

We used DeepSeek OCR to extract every dataset from tables/charts across 500k+ AI arXiv papers for $1000 🚀 See which benchmarks are trending and discover datasets you didn't know existed Doing the same task with Mistral OCR would've cost $7500 👀
0:30
askalphaxiv's profile picture

We used DeepSeek OCR to extract every dataset from tables/charts across 500k+ AI arXiv papers for $1000 🚀 See which benchmarks are trending and discover datasets you didn't know existed Doing the same task with Mistral OCR would've cost $7500 👀

alphaXiv

288,761 views • 10 months ago

Introducing autoresearch for GitHub repos Change 'Github' to 'ARGithub' in any repo URL Research artifacts extend beyond papers. Autoresearch is especially useful for experimenting on existing codebases that move fast and outpace their own publications. With one URL change you can now deploy an agent to orient itself on the codebase, resolve setup issues, and iterate on experiments.
0:48
askalphaxiv's profile picture

Introducing autoresearch for GitHub repos Change 'Github' to 'ARGithub' in any repo URL Research artifacts extend beyond papers. Autoresearch is especially useful for experimenting on existing codebases that move fast and outpace their own publications. With one URL change you can now deploy an agent to orient itself on the codebase, resolve setup issues, and iterate on experiments.

alphaXiv

73,230 views • 2 months ago

Introducing Deep Research for arXiv Ask questions like 'What are the latest breakthroughs in RL fine-tuning?' and get comprehensive lit reviews with trending papers automatically included Turn hours of literature searches into seconds with AI-powered research context ⚡
0:50
askalphaxiv's profile picture

Introducing Deep Research for arXiv Ask questions like 'What are the latest breakthroughs in RL fine-tuning?' and get comprehensive lit reviews with trending papers automatically included Turn hours of literature searches into seconds with AI-powered research context ⚡

alphaXiv

373,010 views • 1 year ago

Introducing paper replications for arXiv Research codebases are notoriously hard to set up We deploy autoresearch agents to ingest popular arXiv repos, resolve setup issues, and get the core claim running. You can now sort papers by ease of implementation 🚀
0:27
askalphaxiv's profile picture

Introducing paper replications for arXiv Research codebases are notoriously hard to set up We deploy autoresearch agents to ingest popular arXiv repos, resolve setup issues, and get the core claim running. You can now sort papers by ease of implementation 🚀

alphaXiv

60,378 views • 2 months ago

Introducing the Global Researcher Map 🌎 We mapped every AI researcher into a visual landscape you can explore Search your favorite authors, topics, or institutions, and see who’s behind the work
0:33
askalphaxiv's profile picture

Introducing the Global Researcher Map 🌎 We mapped every AI researcher into a visual landscape you can explore Search your favorite authors, topics, or institutions, and see who’s behind the work

alphaXiv

44,421 views • 1 month ago

Ever suspected a paper you’re reading is AI slop? You can now turn on AI detection mode on alphaXiv to visualize what is written by an AI and what is not. Now available for every research paper indexed on arXiv. Integrated with the latest detection model from 🚀
0:20
askalphaxiv's profile picture

Ever suspected a paper you’re reading is AI slop? You can now turn on AI detection mode on alphaXiv to visualize what is written by an AI and what is not. Now available for every research paper indexed on arXiv. Integrated with the latest detection model from 🚀

alphaXiv

97,745 views • 4 months ago

Introducing OpenResearch: run parallel research agents with any model Bring your own compute and your code + data stays with you A virtual lab on your machine
0:56
askalphaxiv's profile picture

Introducing OpenResearch: run parallel research agents with any model Bring your own compute and your code + data stays with you A virtual lab on your machine

alphaXiv

32,864 views • 1 month ago

Introducing quickarXiv Papers are often written in convoluted language that is hard to understand. We're fixing that. Swap arxiv → quickarxiv on any paper URL to get an instant blog with figures, insights, and explanations. Now extracted with DeepSeek OCR 🚀
0:31
askalphaxiv's profile picture

Introducing quickarXiv Papers are often written in convoluted language that is hard to understand. We're fixing that. Swap arxiv → quickarxiv on any paper URL to get an instant blog with figures, insights, and explanations. Now extracted with DeepSeek OCR 🚀

alphaXiv

138,043 views • 9 months ago

If doomscrolling X is part of your research workflow, we built something for you. Introducing Paperscrolling 🚀 Get the most trending research with key ideas, figures, and audio explanations from alphaXiv Briefs
0:29
askalphaxiv's profile picture

If doomscrolling X is part of your research workflow, we built something for you. Introducing Paperscrolling 🚀 Get the most trending research with key ideas, figures, and audio explanations from alphaXiv Briefs

alphaXiv

83,961 views • 5 months ago