TTE-Flash trains latent think tokens with CoT generation loss and embedding tokens with contrastive loss to deliver high-performance multimodal representations without generating explicit reasoning at inference time.
TMLR , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
VPiT enables pretrained LLMs to perform both visual understanding and generation by predicting discrete text tokens and continuous visual tokens, with understanding data proving more effective than generation-specific data.
citing papers explorer
-
TTE-Flash: Accelerating Reasoning-based Multimodal Representations via Think-Then-Embed Tokens
TTE-Flash trains latent think tokens with CoT generation loss and embedding tokens with contrastive loss to deliver high-performance multimodal representations without generating explicit reasoning at inference time.
-
MetaMorph: Multimodal Understanding and Generation via Instruction Tuning
VPiT enables pretrained LLMs to perform both visual understanding and generation by predicting discrete text tokens and continuous visual tokens, with understanding data proving more effective than generation-specific data.