Bottleneck Tokens paired with a masked generative objective achieve state-of-the-art unified multimodal retrieval performance among 2B-scale models on the MMEB-V2 benchmark with 78 datasets.
Cafe: Unifying representation and generation with contrastive-autoregressive finetuning.arXiv preprint arXiv:2503.19900
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
PLUME uses latent-state autoregressive rollouts and a progressive training curriculum to deliver efficient reasoning for universal multimodal embeddings without generating explicit rationales.
Prune-then-Merge combines adaptive pruning of low-signal patches with hierarchical merging to achieve higher compression rates and better performance than prior single-stage methods in visual document retrieval.
CausalEmbed uses auto-regressive generation with iterative margin loss to produce multi-vector embeddings that reduce visual token counts 30-155x while retaining competitive performance on VDR benchmarks.
A prompt-and-layer tweak lets pretrained multimodal LLMs serve as competitive retrieval systems without any additional training, with reranking framed as multiple-choice questions to reduce label bias.
Using a structured rewrite instead of CoT as the generative interface improves MLLM-based multimodal embedding performance while cutting thinking tokens by about half.
citing papers explorer
-
Bottleneck Tokens for Unified Multimodal Retrieval
Bottleneck Tokens paired with a masked generative objective achieve state-of-the-art unified multimodal retrieval performance among 2B-scale models on the MMEB-V2 benchmark with 78 datasets.
-
PLUME: Latent Reasoning Based Universal Multimodal Embedding
PLUME uses latent-state autoregressive rollouts and a progressive training curriculum to deliver efficient reasoning for universal multimodal embeddings without generating explicit rationales.
-
Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework
Prune-then-Merge combines adaptive pruning of low-signal patches with hierarchical merging to achieve higher compression rates and better performance than prior single-stage methods in visual document retrieval.
-
CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding
CausalEmbed uses auto-regressive generation with iterative margin loss to produce multi-vector embeddings that reduce visual token counts 30-155x while retaining competitive performance on VDR benchmarks.
-
FreeRet: MLLMs as Training-Free Retrievers
A prompt-and-layer tweak lets pretrained multimodal LLMs serve as competitive retrieval systems without any additional training, with reranking framed as multiple-choice questions to reduce label bias.
-
Beyond Chain-of-Thought: Rewrite as a Universal Interface for Generative Multimodal Embeddings
Using a structured rewrite instead of CoT as the generative interface improves MLLM-based multimodal embedding performance while cutting thinking tokens by about half.