conftrace_

looped transformer

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

in-context learning (2) multi-step gradient descent (1) data-fitting problem (1) sequence-to-sequence function (1) timestep encoding (1) latent thought (1) effective depth (1) modulus of continuity (1) large language model (1) scaling parameter (1)

Papers

Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent AISTATS 2025 On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding ICML 2025 Reasoning with Latent Thoughts: On the Power of Looped Transformers ICLR 2025 Looped Transformers are Better at Learning Learning Algorithms ICLR 2024