Proving and improving the Platonic Representation Hypothesis with JEPAs(arxiv.org)

156 points by Anon84 1 day ago | 78 comments

arXiv paper by Balestriero and LeCun proving a Platonic Representation Theorem for JEPAs and showing good views align modalities more efficiently than next-token prediction.

The alien space of science: Coherent but cognitively unavailable directions(arxiv.org)

195 points by martincsweiss 11 days ago | 80 comments

arXiv abstract page for a NeurIPS 2026 paper proposing a method to sample scientifically coherent research directions that existing researcher communities are unlikely to propose.

Monoidal computer I: Basic computability by string diagrams (2012)(arxiv.org)

3 points by measurablefunc 10 days ago | 0 comments

arXiv abstract page for Dusko Pavlovic's 2012 paper proposing a model of computation based on monoidal categories and string diagrams.

Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence (2025)(arxiv.org)

140 points by robin_reala 2 months ago | 77 comments

A taxonomy of omnicidal futures involving artificial intelligence (2025)(arxiv.org)

67 points by amelius 3 months ago | 56 comments

Attention Is Not What You Need (2025)(arxiv.org)

177 points by westurner 7 days ago | 62 comments

arXiv paper proposing an attention-free sequence model using Grassmann flows and Plucker coordinates, compared against Transformers on Wikitext-2 and SNLI.

RWKV: Reinventing RNNs for the Transformer Era(arxiv.org)

318 points by ianbutler 3 years ago | 164 comments

arXiv paper introducing RWKV, a model architecture combining Transformer-style parallel training with efficient RNN inference via linear attention.

Generative Agents: Interactive Simulacra of Human Behavior(arxiv.org)

326 points by mmq 3 years ago | 178 comments

arXiv paper introducing generative agents, LLM-powered software agents that simulate believable human behavior in an interactive sandbox environment.

Browser extensions are underrated: the promise of hackable software (2019)(geoffreylitt.com)

552 points by mufty 2 years ago | 275 comments

A 2019 blog post by Geoffrey Litt arguing that browser extensions are underrated as a way for users to customize and modify the software they use.

Heretic: Automatic censorship removal for language models(github.com)

705 points by melded 11 months ago | 339 comments

GitHub repository for Heretic, an AGPL-licensed tool for fully automatic censorship removal (abliteration) in transformer language models.

ArXiv now offers papers in HTML format(blog.arxiv.org)

1130 points by programd 2 years ago | 296 comments

arXiv blog post announcing that research papers are now available in HTML format to improve accessibility for users with disabilities.

Reducibility Among Combinatorial Problems (1972) [pdf](cgi.di.uoa.gr)

6 points by liamswayne 6 days ago | 0 comments

PDF of Richard Karp's 1972 paper "Reducibility Among Combinatorial Problems," which showed 21 classic combinatorial problems to be NP-complete.