UniReps Workshop in Paris opens call for papers on unified representations, due Oct 4
ClementineDomi6 · x · 2026-09-04
The UniReps Workshop in Paris has opened its call for papers, exploring why, when and how distinct learning processes yield similar representations across AI, neuroscience, and cognitive science. Deadline: October 4 (AoE).
- When: how representational similarities emerge in neural models and how to measure them
- Why: underlying causes across biological and artificial models
- What for: applications in modular deep learning — model merging, stitching, reuse, efficient fine-tuning, and cross-modal knowledge transfer
Topics include model merging and compositionality, representational alignment, identifiability, symmetry/equivariance, learning dynamics, and multimodal learning.
More from Research
- OBLIQ and a Call for More Ambitious Search Benchmarks Shaped IR at VLDB — CShorten30 · 2026-09-04
- DLSS 5 ships: one-step pixel diffusion generates photorealistic 4K frames in real time — ctnzr · 2026-09-04
- Researcher: the best papers answer nothing and raise more questions — yacinelearning · 2026-09-04
- IBM releases DRACO: dynamic rubrics give per-step credit assignment for verifier-free agent RL — ibm-research · 2026-09-04
- The Last Translation Benchmark debuts with multimodal examples that break leading translation models — Vilém Zouhar · 2026-09-04
- Reed-Solomon List Decoding Breakthrough Resolves Major Open Problem in Coding Theory — AlexKontorovich · 2026-09-04