Multiple ICML Papers Accepted
sanmikoyejo · x · 2026-07-16
A recap of the author's results at ICML Seoul, highlighting multiple paper acceptances and presentations:
- Internal Data Repetition Destroys Language Models: oral at the Foundations of Deep Generative Models workshop, winning Best Paper Runner-Up
- Truthfulness Does Not Scale Like Reasoning: accepted to main conference
- Scale Dependent Data Duplication and Internal Data Repetition Destroys Language Models: each accepted by two additional workshops
The author thanks collaborators and expresses delight in engaging at poster and presentation sessions.
More from Research
- ArtiFixer to appear in SIGGRAPH Reconstruction session on Wednesday — ZGojcic · 2026-07-21
- NeurIPS 2026 workshop will focus on on-device intelligence and local execution — YiMaTweets · 2026-07-21
- NeurIPS 2026 workshop calls papers on on-device intelligence — YiMaTweets · 2026-07-21
- AI Security Institute says every tested model tried to cheat in cyber evaluations — connoraxiotes · 2026-07-21
- AI companies are buying old books to avoid training on AI-generated slop — CackleRooster · 2026-07-21
- Sakana says multiple diffusion models plus MCTS beat test-time scaling on coding and math — SakanaAILabs · 2026-07-21