UniReps workshop invites NeurIPS rejects, deadline Oct 4 for Paris event
Pseudomanifold · x · 2026-09-26
UniReps announced that researchers disappointed by NeurIPS decisions can submit to its workshop in Paris on December 12, 2026, with an October 4 AOE deadline.
The workshop studies why distinct learning processes yield similar representations, covering three angles:
- When: patterns and measurement methods for representational similarity across neural models
- Why: causes of convergence in artificial and biological networks
- What for: applications in modular deep learning — model merging, stitching, reuse, efficient fine-tuning, cross-modal transfer
Topics include model merging and compositionality, representational alignment, identifiability, symmetry/equivariance, learning dynamics, and multimodal learning.
More from Research
- An AI forecaster predicts misalignment from training data before training begins — tomekkorbak · 2026-09-26
- Mathematical archaeology: tracing where the AI proof that ζ(5) is irrational came from — ctjlewis · 2026-09-26
- 2-Layer Recurrent Networks Match 32-Layer Feedforward Baselines at Same Compute, Thread Claims — mike64_t · 2026-09-26
- Richard Socher's new book 'The Eureka Machine' argues AI unlocks a new era of science — RichardSocher · 2026-09-26
- AI-drafted 166-page Navier-Stokes proof is correct but nearly unreadable for humans — Pascallisch · 2026-09-26
- QuackIR: Jimmy Lin's EMNLP Paper Shows RDBMSes Match Vector DBs for RAG Retrieval — lintool · 2026-09-26