Pith. sign in

REVIEW 10 cited by

Jina CLIP: Your CLIP Model Is Also Your Text Retriever

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.20204 v2 pith:VPRIFEC4 submitted 2024-05-30 cs.CL cs.AIcs.CVcs.IR

Jina CLIP: Your CLIP Model Is Also Your Text Retriever

classification cs.CL cs.AIcs.CVcs.IR
keywords modelscliptasksretrievalcontrastiveinformationmodelmultimodal
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Contrastive Language-Image Pretraining (CLIP) is widely used to train models to align images and texts in a common embedding space by mapping them to fixed-sized vectors. These models are key to multimodal information retrieval and related tasks. However, CLIP models generally underperform in text-only tasks compared to specialized text models. This creates inefficiencies for information retrieval systems that keep separate embeddings and models for text-only and multimodal tasks. We propose a novel, multi-task contrastive training method to address this issue, which we use to train the jina-clip-v1 model to achieve the state-of-the-art performance on both text-image and text-text retrieval tasks.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers

    cs.CL 2026-05 unverdicted novelty 7.0

    Jina-embeddings-v5-omni creates multimodal embeddings for text, image, audio, and video by freezing the text and media encoders and training only 0.35% of the weights via a VLM-style connector.

  2. TCD-Arena: Assessing Robustness of Time Series Causal Discovery Methods Against Assumption Violations

    cs.LG 2026-05 unverdicted novelty 7.0

    TCD-Arena is a new customizable testing framework that runs millions of experiments to map how 33 different assumption violations affect time series causal discovery methods and shows ensembles can boost overall robustness.

  3. MARVEL: Multimodal Adaptive Reasoning-intensiVe Expand-rerank and retrievaL

    cs.IR 2026-04 unverdicted novelty 7.0

    MARVEL reaches 37.9 nDCG@10 on the MM-BRIGHT benchmark by combining LLM query expansion, a reasoning-enhanced dense retriever, and GPT-4o CoT reranking, beating prior multimodal encoders by 10.3 points.

  4. jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers

    cs.CL 2026-05 unverdicted novelty 6.0

    GELATO extends frozen text embedding models with locked image and audio encoders, training minimal connectors to produce a single semantic embedding space for text, image, audio, and video while keeping original text ...

  5. jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers

    cs.CL 2026-05 unverdicted novelty 6.0

    GELATO extends frozen Jina Embeddings v5 text models with locked non-text encoders, training only connectors to produce competitive multimodal embeddings while preserving exact text performance.

  6. One Perturbation, Two Failure Modes: Probing VLM Safety via Embedding-Guided Typographic Perturbations

    cs.CV 2026-04 unverdicted novelty 6.0

    Multimodal embedding distance predicts typographic attack success rate across VLMs, and optimizing it under bounded perturbations on surrogates exposes two co-occurring failure modes of lost readability and reduced sa...

  7. Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality

    cs.CV 2026-06 unverdicted novelty 5.0

    MACCO applies cross-modal masked reconstruction of compositional concepts with inter- and intra-modal auxiliary objectives to improve visio-linguistic compositionality in VLMs.

  8. Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models

    cs.CV 2026-04 unverdicted novelty 5.0

    Text-image embedding distance negatively correlates with typographic attack success rates (r = -0.71 to -0.93) on VLMs, with font size and image degradations strongly modulating effectiveness.

  9. BRIDGE: Multimodal-to-Text Retrieval via Reinforcement-Learned Query Alignment

    cs.IR 2026-04 unverdicted novelty 5.0

    BRIDGE reaches 29.7 nDCG@10 on MM-BRIGHT by RL-aligning multimodal queries to text and using a reasoning retriever, beating multimodal encoders and, when combined with Nomic-Vision, exceeding the best text-only retrie...

  10. ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP

    cs.CV 2026-06 unverdicted novelty 4.0

    ReasonCLIP-58M applies continual pretraining with visually grounded reasoning captions on 58M examples to improve CLIP-style models on commonsense and compositional reasoning tasks.