Skip to content
conftrace_

denoising objective

8 papers

Explore in graph

Co-occurring keywords · papers mentioning both

self-supervised learning (3) sequence-to-sequence model (2) state space model (2) representation learning (2) zero-shot text style transfer (1) encoder-decoder model (1) parallel data (1) semantic textual similarity (1) cross-lingual natural language inference (1) model controllability (1)

Papers

Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors (Extended Abstract) IJCAI 2025 On the Feature Learning in Diffusion Models ICLR 2025 Reconstructive Visual Instruction Tuning ICLR 2025 DenoSent: A Denoising Objective for Self-Supervised Sentence Representation Learning AAAI 2024 Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors ICLR 2024 Uncovering Hidden Consequences of Pre-training Objectives in Sequence-to-Sequence Models ACL 2023 PARADISE: Exploiting Parallel Data for Multilingual Sequence-to-Sequence Pretraining NAACL 2022 Educating Text Autoencoders: Latent Representation Guidance via Denoising ICML 2020