Visual Entailment

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

3 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 33 papers with code (56 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• UNITER: UNiversal Image-TExt Representation Learning
  25 Sep 2019 7 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 2 pointer-only (licence)
  Different from previous work that applies joint random masking to both modalities, we use conditional masking on pre-training tasks (i.
• CoCa: Contrastive Captioners are Image-Text Foundation Models
  4 May 2022 6 repositories listed Syntology ran 9 of 17 samples · 8 unverified
  We apply a contrastive loss between unimodal image and text embeddings, in addition to a captioning loss on the multimodal decoder outputs which predicts text tokens autoregressively.
• Visual Spatial Reasoning
  30 Apr 2022 4 repositories listed Syntology ran 5 of 10 samples · 5 unverified
  Spatial relations are a basic part of human cognition.
• OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
  7 Feb 2022 4 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization.
• Distilled Dual-Encoder Model for Vision-Language Understanding
  16 Dec 2021 4 repositories listed
  We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering.
• How Much Can CLIP Benefit Vision-and-Language Tasks?
  13 Jul 2021 4 repositories listed Syntology ran 6 of 10 samples · 4 unverified · 9 pointer-only (licence)
  Most existing Vision-and-Language (V&L) models rely on pre-trained visual encoders, using a relatively small set of manually-annotated data (as compared to web-crawled data), to perceive the visual world.
• Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning
  15 Dec 2023 3 repositories listed
  This work inaugurates a new domain in factual error correction for chart captions, presenting a novel evaluation mechanism, and demonstrating an effective approach to ensuring the factuality of generated chart captions.
• Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning
  7 Apr 2021 3 repositories listed
  As region-based visual features usually represent parts of an image, it is challenging for existing vision-language models to fully understand the semantics from paired natural languages.
• Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based Segmentation
  11 Jun 2024 2 repositories listed
  Grounded Multimodal Named Entity Recognition (GMNER) task aims to identify named entities, entity types and their corresponding visual regions.
• LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition
  15 Feb 2024 2 repositories listed
  Grounded Multimodal Named Entity Recognition (GMNER) is a nascent multimodal task that aims to identify named entities, entity types and their corresponding visual regions.
• Large-Scale Adversarial Training for Vision-and-Language Representation Learning
  11 Jun 2020 2 repositories listed Syntology ran 10 of 20 samples · 10 unverified · 6 pointer-only (licence)
  We present VILLA, the first known effort on large-scale adversarial training for vision-and-language (V+L) representation learning.
• Defeasible Visual Entailment: Benchmark, Evaluator, and Reward-Driven Optimization
  19 Dec 2024 1 repository listed
  Additionally, we introduce a reward-driven update optimization method to further enhance the quality of updates generated by multimodal models.
• Understanding Figurative Meaning through Explainable Visual Entailment
  2 May 2024 1 repository listed
  To close this gap, we propose a new task framing the figurative meaning understanding problem as an explainable visual entailment task, where the model has to predict whether the image (premise) entails a caption…
• MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion
  14 Mar 2024 1 repository listed
  Despite the demonstrated parameter efficiency of prompt-based multimodal fusion methods, their limited adaptivity and expressiveness often result in suboptimal performance compared to other tuning approaches.
• VEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing
  5 Mar 2024 1 repository listed
  Visual entailment (VE) is a multimodal reasoning task consisting of image-sentence pairs whereby a promise is defined by an image, and a hypothesis is described by a sentence.
• p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models
  17 Dec 2023 1 repository listed
  In this paper, we present a novel modeling framework that recasts adapter tuning after attention as a graph message passing process on attention graphs, where the projected query and value features and attention matrix…
• Good Questions Help Zero-Shot Image Reasoning
  4 Dec 2023 1 repository listed
  QVix enables a wider exploration of visual scenes, improving the LVLMs' reasoning accuracy and depth in tasks such as visual question answering and visual entailment.
• Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages
  29 Jun 2023 1 repository listed Syntology ran 0 of 4 samples · 4 unverified
  Our evaluation across three distinct tasks (image-text retrieval, visual entailment, and natural language visual reasoning) demonstrates that this approach outperforms the state-of-the-art multilingual vision-language…
• I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors
  24 May 2023 1 repository listed
  We propose to solve the task through the collaboration between Large Language Models (LLMs) and Diffusion Models: Instruct GPT-3 (davinci-002) with Chain-of-Thought prompting generates text that represents a visual…
• Benchmarking Robustness of Multimodal Image-Text Models under Distribution Shift
  15 Dec 2022 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  Multimodal image-text models have shown remarkable performance in the past few years.
• Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations
  8 Dec 2022 1 repository listed Syntology ran 1 of 8 samples · 7 unverified
  Natural language explanations promise to offer intuitively understandable explanations of a neural network's decision process in complex vision-language tasks, as pursued in recent VL-NLE models.
• I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision
  17 Nov 2022 1 repository listed Syntology ran 1 of 6 samples · 5 unverified
  We produce models using only text training data on four representative tasks: image captioning, visual entailment, visual question answering and visual news captioning, and evaluate them on standard benchmarks using…
• MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model
  11 Oct 2022 1 repository listed
  Multimodal semantic understanding often has to deal with uncertainty, which means the obtained messages tend to refer to multiple targets.
• Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment
  29 Aug 2022 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  Vision and Language Pretraining has become the prevalent approach for tackling multimodal downstream tasks.
• Prompt Tuning for Generative Multimodal Pretrained Models
  4 Aug 2022 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Prompt tuning has become a new paradigm for model tuning and it has demonstrated success in natural language pretraining and even vision pretraining.
• Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations
  23 Jul 2022 1 repository listed
  CSI), a relation inferrer, and a Lexical Constraint-aware Generator (arr.
• MixGen: A New Multi-Modal Data Augmentation
  16 Jun 2022 1 repository listed Syntology ran 0 of 2 samples · 2 unverified
  Data augmentation is a necessity to enhance data efficiency in deep learning.
• Fine-Grained Visual Entailment
  29 Mar 2022 1 repository listed
  In this paper, we propose an extension of this task, where the goal is to predict the logical relationship of fine-grained knowledge elements within a piece of text to an image.
• NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks
  9 Mar 2022 1 repository listed
  Current NLE models explain the decision-making process of a vision or vision-language model (a.
• Check It Again:Progressive Visual Question Answering via Visual Entailment
  1 Aug 2021 1 repository listed
  Besides, they only explore the interaction between image and question, ignoring the semantics of candidate answers.

Syntology lines on 13 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.