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

classification cs.CLcs.AIcs.CVcs.IR
keywords modelscliptasksretrievalcontrastiveinformationmodelmultimodal
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

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). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

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

  1. AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoning

    cs.CV 2025-08 reject novelty 6.0 of 10

    A new audio-visual reasoning benchmark and a two-part metric (factual consistency, core inference) claim to expose a gap between answer accuracy and reasoning quality in AV-LLMs.

  2. CONCAP: Seeing Beyond English with Concepts Retrieval-Augmented Captioning

    cs.CL 2025-07 conditional novelty 6.0 of 10

    CONCAP combines retrieved captions with retrieved concepts to improve multilingual image captioning, reaching 34.2 average CIDEr on XM3600 against 31.8 for Pangea and 25.9 for mBLIP while training on 566K pairs.

  3. jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval

    cs.AI 2025-06 conditional novelty 6.0 of 10

    jina-embeddings-v4 is a multimodal embedding model built on Qwen2.5-VL with LoRA adapters and dual single/multi-vector outputs, and it introduces the Jina-VDR benchmark for visually rich retrieval.

  4. MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval

    cs.AI 2025-06 conditional novelty 6.0 of 10

    MM-R5, a 7B multimodal re-ranker trained with SFT and GRPO, achieves state-of-the-art page-level recall on MMDocIR by generating per-page reasoning chains.

  5. Progressive Multimodal Reasoning via Active Retrieval

    cs.CL 2024-12 conditional novelty 6.0 of 10

    AR-MCTS retrieves per-step multimodal knowledge during tree search and trains a process reward model, improving MLLM reasoning accuracy on three benchmarks by a few points.

  6. FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training

    cs.CV 2024-11 conditional novelty 6.0 of 10

    Frozen LLM text encoders, combined with multi-prompt hidden-state extraction and cached embeddings, make CLIP-style pre-training data-efficient, long-context aware, and multilingual.

  7. Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning

    cs.CL 2025-06 conditional novelty 5.0 of 10

    State-of-the-art text embeddings lag far behind on tasks requiring pragmatic inference, stance detection, and social meaning, relative to their strong performance on surface semantic benchmarks.

  8. Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation

    cs.CV 2025-05 conditional novelty 5.0 of 10

    DCLIP fine-tunes a CLIP student's image encoder to match a YOLO-region, bidirectional cross-attention teacher, improving retrieval while retaining most zero-shot accuracy.

  9. jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images

    cs.CL 2024-12 conditional novelty 5.0 of 10

    jina-clip-v2, an 865M-parameter multilingual dual-encoder, outperforms prior CLIP-style models on text-only and crossmodal retrieval, and on visually rich document retrieval, while supporting flexible embedding dimensions.

  10. Human Action CLIPs: Detecting AI-generated Human Motion

    cs.CV 2024-11 conditional novelty 5.0 of 10

    CLIP-based semantic embeddings, with a fine-tuned variant, detect AI-generated human-motion video with high accuracy (up to 99.2% video-level) and generalize to unseen generators.

Pith tools