SOTAVerified

Disentanglement

This is an approach to solve a diverse set of tasks in a data efficient manner by disentangling (or isolating ) the underlying structure of the main problem into disjoint parts of its representations. This disentanglement can be done by focussing on the "transformation" properties of the world(main problem)

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1091–1100 of 1854 papers

TitleStatusHype
When Is Unsupervised Disentanglement Possible?—0
When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners—0
Why disentanglement-based speaker anonymization systems fail at preserving emotions?—0
WordCon: Word-level Typography Control in Scene Text Rendering—0
WordRobe: Text-Guided Generation of Textured 3D Garments—0
XHate-999: Analyzing and Detecting Abusive Language Across Domains and Languages—0
XMP-Font: Self-Supervised Cross-Modality Pre-training for Few-Shot Font Generation—0
X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention—0
Y-GAN: Learning Dual Data Representations for Efficient Anomaly Detection—0
You Talking to Me? A Corpus and Algorithm for Conversation Disentanglement—0
Show:102550
← PrevPage 110 of 186Next →

No leaderboard results yet.