Vector Institute Brings 73 Papers to ICML2026
VectorInst · x · 2026-07-04
Ahead of ICML2026 in Seoul next week, the Vector Institute announced 73 accepted papers. The research spans multiple trending AI domains: analyzing "power-weakening" patterns in 1.5 million real AI conversations, training genomic foundation models to segment DNA like biology, and investigating whether vision-language models fail by "seeing the wrong image" or "reasoning incorrectly." Other focuses include reliable model reasoning, coherent long-video generation, and privacy protection.
More from Research
- VidMap uses RoMa coarse matching on all frames, fine-scale only for keyframes — ducha_aiki · 2026-09-11
- Bug Hunt Bench author: leaderboard noise is about 2-3 points — PawelHuryn · 2026-09-11
- PNAS paper shows a tiny billiard-ball system is a universal computer — undecidability lives in two dimensions — eigensteve · 2026-09-11
- New paper: Absolute pose estimation from affine cues and gravity direction — ducha_aiki · 2026-09-11
- LoMa Paper Ships REALLY HardPairs Dataset, Accepted at ECCV 2026 — ducha_aiki · 2026-09-11
- Johns Hopkins Launches Full-Stack Hands-on Robot Learning Class with SO-101 Arm Kits — _krishna_murthy · 2026-09-11