Vision-Language Pretraining

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 50

May 21, 2026cs.CV

What Does the Caption Really Say? Counterfactual Phrase Intervention for Compositional Data Selection in Vision-Language Pretraining

CLIP-style contrastive pretraining typically curates web-scale image-text pairs using sample-level filtering signals, often based on pair-level alignment. We show that this signal saturates: once coarse mismatches are removed, stricter global filtering no longer tracks the compositional supervision provided by the retained captions. The reason is structural - a global score conflates whether a pair is broadly plausible with whether the individual object, attribute, and relation phrases inside the caption materially support the image-text match. The latter is what compositional generalization demands, yet pair-level filters are blind to it. We address this with Counterfactual Phrase Intervention (CPI), a phrase-level curation framework that converts controlled nonce-token substitutions into image-conditioned phrase-sensitivity scores. CPI uses global alignment only for coarse mismatch removal, then ranks the surviving pool by whether caption phrases measurably affect the image-text score under controlled substitution. We frame CPI as a first-order phrase-sensitivity signal rather than a grounding or identification result, and evaluate it at CC3M scale. Ranking by this signal yields a 50%-data subset that improves VL-CheckList-VG Relation by +1.91 over the full-data baseline and +1.00 over alignment-only filtering at matched budget, while improving SugarCrepe overall and preserving general transfer. CPI is loss-orthogonal: applied unchanged to NegCLIP, it further improves VL-CheckList-VG Relation by +3.84, with additional CE-CLIP gains in the main text.

Hyejin Go, Semi Lee, Hyesong Choi

Soongsil University Seoul, Republic of Korea

Training Data Selection Vision-Language Pretraining Compositional Generalization

May 13, 2026cs.CV

Unified Pix Token And Word Token Generative Language Model

Since the emergence of Vision Transformer (ViT), it has been widely used in generative language model and generative visual model. Especially in the current state-of-art open source multimodal models, ViT obtained by CLIP or SigLIP method serves as the vision encoder backbone to help them acquire visual understanding capabilities. But this method leads to limitations in visual understanding for details, such as difficulty in recognizing small text or numbers in images. To address these issues, we propose a new model to unify pix token and word token into the generative language model. The new model also features with each pix of image having its own token embedding, color folding, global conditional attention approximation and image unsupervised pretraining. We conducted image unsupervised pretraining experiments using our new model to explore its potential. The experimental results show that it has good performance even in small model and with limited training data. We believe our model also conforms to the scaling law, as long as model parameters and training data increased, its performance will continue to improve.

Haun Leung, ZiNan Wang

Image Tokenization Self-Supervised Pre-Training Unified Multimodal Models Visual Tokenization Multimodal Foundation Models Vision-Language Pretraining

May 13, 2026cs.CV

Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context

Long-context modeling is becoming a core capability of modern large vision-language models (LVLMs), enabling sustained context management across long-document understanding, video analysis, and multi-turn tool use in agentic workflows. Yet practical training recipes remain insufficiently explored, particularly for designing and balancing long-context data mixtures. In this work, we present a systematic study of long-context continued pre-training for LVLMs, extending a 7B model from 32K to 128K context with extensive ablations on long-document data. We first show that long-document VQA is substantially more effective than OCR transcription. Building on this observation, our ablations further yield three key findings: i) for sequence-length distribution, balanced data outperforms target-length-focused data (e.g., 128K), suggesting that long-context ability requires generalizable key-information retrieval across various lengths and positions; ii) retrieval remains the primary bottleneck, favoring retrieval-heavy mixtures with modest reasoning data for task diversity; and iii) pure long-document VQA largely preserves short-context capabilities, suggesting that instruction-formatted long data reduces the need for short-data mixing. Based on these findings, we introduce MMProLong, obtained by long-context continued pre-training from Qwen2.5-VL-7B with only a 5B-token budget. MMProLong improves long-document VQA scores by 7.1% and maintains strong performance at 256K and 512K contexts beyond its 128K training window, without additional training. It further generalizes to webpage-based multimodal needle retrieval, long-context vision-text compression, and long-video understanding without task-specific supervision. Overall, our study establishes a practical LongPT recipe and an empirical foundation for advancing long-context vision-language models.

Zhaowei Wang, Lishu Luo, Haodong Duan +9

1CSE Department, HKUST · 2ByteDance Seed · *Work done at ByteDance Seed

Visual Question Answering Vision-Language Models Large Vision-Language Models Long-Context Modeling Vision-Language Pretraining Long-Context VLMs

May 13, 2026cs.CV

CA-GCL: Cross-Anatomy Global-Local Contrastive Learning for Robust 3D Medical Image Understanding

Fine-grained Vision-Language Pre-training (FVLP) demonstrates significant potential in 3D medical image understanding by aligning anatomy-level visual representations with corresponding textual descriptions. However, existing FVLP paradigms often suffer from severe representation collapse in the textual embedding space, where text embeddings of distinct anatomical structures become highly clustered and indistinguishable. This distributional degeneracy renders the model hypersensitive to prompt variations, hindering reliable clinical deployment. To address these challenges, we propose a novel Cross-Anatomy Global-Local Contrastive Learning framework (CA-GCL). CA-GCL introduces a global contrastive objective that enforces separation between anatomical categories in the latent space, effectively counteracting the aggregation tendency induced by local alignment. Furthermore, we incorporate a clinical-aware text augmentation strategy based on permutation invariance and partial completeness to enhance robustness against descriptive incompleteness. Extensive evaluations on the CT-RATE and Rad-ChestCT datasets show that CA-GCL achieves comparable zero-shot abnormality detection performance to existing VLP paradigms, while demonstrating substantially better robustness to prompt variations: on canonical templates it obtains higher mean AUC with lower variance, and on non-canonical templates it remains stable whereas baselines degrade markedly. These results validate CA-GCL as an effective framework for robust 3D medical image understanding.

Hanwen Zhang, Yao Liu, Die Dai +4

University of Electronic Science and Technology of China, Chengdu, China · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE

VLM Robustness Medical Image Anomaly Detection Medical VLMs Multimodal Contrastive Learning Vision-Language Pretraining

May 12, 2026cs.LG

20/20 Vision Language Models: A Prescription for Better VLMs through Data Curation Alone

Data curation has shifted the quality-compute frontier for language-model and contrastive image-text pretraining, but its role for vision-language models (VLMs) is far less established. We ask how far data curation alone can take VLM performance, holding architecture, training recipe, and compute fixed and varying only the training data. Our pipeline, applied to the MAmmoTH-VL single-image subset, lifts performance by +11.7pp on average across 20 public VLM benchmarks (spanning grounding, VQA, OCR/documents, captioning, spatial/3D, counting, charts, math, brand-ID, and multi-image reasoning) and by +11.3pp on average across all nine capability axes of DatBench, our high-fidelity VLM eval suite. At 2B, our curated model surpasses InternVL3.5-2B by 9.9pp at ~17x less training compute and closes the gap to Qwen3-VL-2B to within 1.8pp at ~87x less compute, from pretraining alone. Beyond accuracy, curation delivers four further properties: (1) Reliability: per-capability std across training seeds drops by ~67% and the lift survives a 4k-to-16k context-length sweep; (2) OOD generalization: the 9-eval OOD average rises by +7.2pp, and multi-image BLINK rises by +3.09pp despite single-image-only training, with Visual Correspondence gaining +11.8pp; (3) Behavioral gains beyond benchmarks: across ~1,100 open-ended queries the curated 2B is more honest and more specific than the matched-compute baseline, and more concise and less refusal-prone than a frontier 2B reference; (4) Pareto-dominance on inference cost: at every scale (1B, 2B, 4B) the curated model raises accuracy while lowering response FLOPs vs. the matched-compute baseline, and the curated 4B matches near-frontier accuracy at 3.3x lower response FLOPs than Qwen3-VL-4B. Data curation is a high-leverage tool for building better VLMs, reaching near-frontier accuracy at up to ~150x less training compute.

DatologyAI, :, Siddharth Joshi +32

DatologyAI Team1

Training Data Curation Large Vision-Language Models Multimodal Foundation Models Vision-Language Pretraining

May 11, 2026cs.CV

Birds of a Feather Flock Together: Background-Invariant Representations via Linear Structure in VLMs

Vision-language models (VLMs), such as CLIP and SigLIP 2, are widely used for image classification, yet their vision encoders remain vulnerable to systematic biases that undermine robustness. In particular, correlations between foreground objects and their backgrounds constitute a salient and practically important class of spurious dependencies. In this work, we revisit the well-known property of high linear additivity in VLM embedding spaces and show that it enables a decomposition of scene representations into foreground and background components. Leveraging this insight, we introduce a pre-training approach that exploits this property to construct background-invariant representations using synthetic data. Our method achieves, to our knowledge, the first worst-group accuracy exceeding

90\%

on Waterbirds under perfect (

100\%

) spurious correlation (i.e., no minority-group examples in the training data). Furthermore, it demonstrates strong sim-to-real transfer and requires no access to real-world debiased data, making it practical for real-world deployment.

Youssef Zaazou, Mark Thomas

Independent Researcher

VLM Robustness Vision-Language Models Spurious Correlation Robustness Invariant Representation Learning Vision-Language Pretraining

May 7, 2026cs.CV

DINORANKCLIP: DINOv3 Distillation and Injection for Vision-Language Pretraining with High-Order Ranking Consistency

Contrastive language-image pretraining (CLIP) suffers from two structural weaknesses: the symmetric InfoNCE loss discards the relative ordering among unmatched in-batch pairs, and global pooling collapses the visual representation into a semantic bottleneck that is poorly sensitive to fine-grained local structure. RANKCLIP partially addresses the first issue with a list-wise Plackett-Luce ranking-consistency loss, but its model is strictly first-order and inherits the second weakness untouched. We propose DINORANKCLIP, a pretraining framework that addresses both jointly. Our principal contribution is injecting a frozen DINOv3 teacher into the contrastive trunk through a dual-branch lightweight student and a multi-scale fusion module with channel-spatial attention, a self-attention refiner, and a conflict-aware gate that preserves the cross-modal alignment up to first order. Complementarily, we introduce a high-order Plackett-Luce ranking model in which the per-position utility is augmented with attention-parameterised pairwise and tuple-wise transition terms; the family contains CLIP and RANKCLIP as nested zero-order and first-order special cases, and the optimal order on every benchmark is

R^*=3

. The full empirical study -- order sweep, Fine-grained Probe on five datasets, four-node Modality-Gap analysis, six-variant Fusion ablation -- fits in 72 hours on a single eight-GPU H100 node and trains entirely on Conceptual Captions 3M. DINORANKCLIP consistently outperforms CLIP, CyCLIP, ALIP, and RANKCLIP under matched compute, with the largest relative gains on the fine-grained and out-of-distribution evaluations that most directly stress local structural reasoning.

Shuyang Jiang, Nan Yu, Yiming Zhang +2

University of California, Los Angeles · Aimaikj · HFIPS, Chinese Academy of Sciences +2

Contrastive Learning Vision-Language Alignment Multimodal Contrastive Learning Vision-Language Pretraining

May 6, 2026cs.CL

HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities

Image-Text-Matching (ITM) is one of the defacto methods of learning generalized representations from a large corpus in Vision and Language (VL). However, due to the weak association between the web-collected image-text pairs, models fail to show a fine-grained understanding of the combined semantics of these modalities. To address this issue we propose Hard Negative Captions (HNC): an automatically created dataset containing foiled hard negative captions for ITM training towards achieving fine-grained cross-modal comprehension in VL. Additionally, we provide a challenging manually-created test set for benchmarking models on a fine-grained cross-modal mismatch task with varying levels of compositional complexity. Our results show the effectiveness of training on HNC by improving the models' zero-shot capabilities in detecting mismatches on diagnostic tasks and performing robustly under noisy visual input scenarios. Also, we demonstrate that HNC models yield a comparable or better initialization for fine-tuning

Esra Dönmez, Pascal Tilli, Hsiu-Yu Yang +2

Institute for Natural Language Processing, University of Stuttgart

Cross-Modal Learning Image Matching Hard Negative Mining Text-Image Alignment Vision-Language Alignment Vision-Language Pretraining+1

May 5, 2026cs.LG

Text-Conditional JEPA for Learning Semantically Rich Visual Representations

Image-based Joint-Embedding Predictive Architecture (I-JEPA) offers a promising approach to visual self-supervised learning through masked feature prediction. However with the inherent visual uncertainty at masked positions, feature prediction remains challenging and may fail to learn semantic representations. In this work, we propose Text-Conditional JEPA (TC-JEPA) that uses image captions to reduce the prediction uncertainty. Specifically, we modulate the predicted patch features using a fine-grained text conditioner that computes sparse cross-attention over input text tokens. With such conditioning, patch features become predictable as a function of text, thus are more semantically meaningful. We show TC-JEPA improves downstream performance and training stability, with promising scaling properties. TC-JEPA also offers a new vision-language pretraining paradigm based on feature prediction only, outperforming contrastive methods on diverse tasks, especially those requiring fine-grained visual understanding and reasoning.

Chen Huang, Xianhang Li, Vimal Thilak +2

Apple, Cupertino, United States

Joint-Embedding Predictive Architecture Predictive Representation Learning Self-Supervised Visual Representation Learning Vision-Language Pretraining

May 4, 2026cs.CV

Scientific Domain Knowledge Improves Vision-Language Fundus Models

Vision-language models hold considerable promise for ophthalmology, but it remains unclear which training data source best conveys expert domain knowledge. Existing ophthalmic models are trained on fixed text templates, medical reports, or general biomedical literature, sources that have never been compared under matched conditions. To include domain-specific literature in this comparison, we present PubMed-Ophtha, a hierarchical dataset with high domain density of 102,023 panels with their subcaptions from 15,842 open-access articles in PubMed Central. We then finetuned identical CLIP models on each source, using a general biomedical literature model as baseline, and found that domain-specific literature achieved the best average performance across 110 clinical tasks, reaching a mean linear probing AUROC of 88.63% ahead of medical reports (85.68%). Restricting the dataset to fundus images, to the image count of the medical report dataset, or to articles unrelated to the evaluation datasets did not reduce performance, indicating that the gains likely stem from domain density. We release the dataset, the finetuned models, and the full generation pipeline.

Verena Jasmin Hallitschke, Carsten Eickhoff, Philipp Berens

1Hertie Institute for AI in Brain Health, University of Tübingen, Tübingen, Germany · Institute for Applied Medical Informatics, University of Tübingen, Tübingen, Germany · 2Tübingen AI Center, Tübingen, Germany

Healthcare Medical Diagnosis Medical VLMs Fundus Imaging Medical Image Benchmarks Vision-Language Pretraining

May 1, 2026cs.CV

Let ViT Speak: Generative Language-Image Pre-training

In this paper, we present \textbf{Gen}erative \textbf{L}anguage-\textbf{I}mage \textbf{P}re-training (GenLIP), a minimalist generative pretraining framework for Vision Transformers (ViTs) designed for multimodal large language models (MLLMs). To better align vision encoders with the autoregressive nature of LLMs, GenLIP trains a ViT to predict language tokens directly from visual tokens using a standard language modeling objective, without contrastive batch construction or an additional text decoder. This design offers three key advantages: (1) \textbf{Simplicity}: a single transformer jointly models visual and textual tokens; (2) \textbf{Scalability}: it scales effectively with both data and model size; and (3) \textbf{Performance}: it achieves competitive or superior results across diverse multimodal benchmarks. Trained on 8B samples from Recap-DataComp-1B, GenLIP matches or surpasses strong baselines despite using substantially less pretraining data. After continued pretraining on multi-resolution images at native aspect ratios, GenLIP further improves on detail-sensitive tasks such as OCR and chart understanding, making it a strong foundation for vision encoders in MLLMs.

Yan Fang, Mengcheng Lan, Zilong Huang +7

1Beijing Jiaotong University · 2ByteDance · 3Nanyang Technological University

Cross-Modal Learning Vision Transformer Multimodal Large Language Models Multimodal Foundation Models Vision-Language Pretraining

Apr 30, 2026cs.CV

Dynamic Cluster Data Sampling for Efficient and Long-Tail-Aware Vision-Language Pre-training

The computational cost of training a vision-language model (VLM) can be reduced by sampling the training data. Previous work on efficient VLM pre-training has pointed to the importance of semantic data balance, adjusting the distribution of topics in the data to improve VLM accuracy. However, existing efficient pre-training approaches may disproportionately remove rare concepts from the training corpus. As a result, long-tail concepts remain insufficiently represented in the training data and are not effectively captured during training. In this work, we introduce a dynamic cluster-based sampling approach (DynamiCS) that downsamples large clusters of data and upsamples small ones. We first demonstrate the advantage of our cluster-scaling approach, which maintains the relative order of semantic clusters in the data and emphasizes the long-tail. This approach contrasts with current work, which focuses only on flattening the semantic distribution of the data. Then, we show the importance of dynamic sampling, which applies sampling at each epoch to improve cross-epoch data diversity and make upsampling practical. Our experiments show that DynamiCS reduces the computational cost of VLM training and provides a performance advantage for long-tail concepts. Code available at https://github.com/MingliangLiang3/DynamiCS.

Mingliang Liang, Zhuoran Liu, Arjen P. de Vries +1

Institute for Computing and Information Sciences, Radboud University, Nijmegen, the Netherlands · University of Amsterdam, Amsterdam, the Netherlands · Radboud University

Long-Tail Learning Vision-Language Pretraining

Apr 27, 2026cs.CV

Probing CLIP's Comprehension of 360-Degree Textual and Visual Semantics

The dream of instantly creating rich 360-degree panoramic worlds from text is rapidly becoming a reality, yet a crucial gap exists in our ability to reliably evaluate their semantic alignment. Contrastive Language-Image Pre-training (CLIP) models, standard AI evaluators, predominantly trained on perspective image-text pairs, face an open question regarding their understanding of the unique characteristics of 360-degree panoramic image-text pairs. This paper addresses this gap by first introducing two concepts: \emph{360-degree textual semantics}, semantic information conveyed by explicit format identifiers, and \emph{360-degree visual semantics}, invariant semantics under horizontal circular shifts. To probe CLIP's comprehension of these semantics, we then propose novel evaluation methodologies using keyword manipulation and horizontal circular shifts of varying magnitudes. Rigorous statistical analyses across popular CLIP configurations reveal that: (1) CLIP models effectively leverage explicit textual identifiers, demonstrating an understanding of 360-degree textual semantics; and (2) CLIP models fail to robustly preserve semantic alignment under horizontal circular shifts, indicating limited comprehension of 360-degree visual semantics. To address this limitation, we propose a LoRA-based fine-tuning framework that explicitly instills invariance to circular shifts. Our fine-tuned models exhibit improved comprehension of 360-degree visual semantics, though with a slight degradation in original semantic evaluation performance, highlighting a fundamental trade-off in adapting CLIP to 360-degree panoramic images. Code is available at https://github.com/littlewhitesea/360Semantics.

Hai Wang, Xiaochen Yang, Mingzhi Dong +1

Department of Statistical Science, University College London, UK · School of Mathematics and Statistics, University of Glasgow, UK · Department of Computer Science, University of Bath, UK.

VLM Evaluation VLM Adaptation Text-Image Alignment Invariant Representation Learning Vision-Language Pretraining

Apr 22, 2026cs.RO

PokeVLA: Empowering Pocket-Sized Vision-Language-Action Model with Comprehensive World Knowledge Guidance

Recent advances in Vision-Language-Action (VLA) models have opened new avenues for robot manipulation, yet existing methods exhibit limited efficiency and a lack of high-level knowledge and spatial awareness. To address these challenges, we propose PokeVLA, a lightweight yet powerful foundation model for embodied manipulation that effectively infuses vision-language understanding into action learning. Our framework introduces a two-stage training paradigm: first, we pre-train a compact vision-language model (PokeVLM) on a curated multimodal dataset of 2.4M samples encompassing spatial grounding, affordance, and embodied reasoning tasks; second, we inject manipulation-relevant representations into the action space through multi-view goal-aware semantics learning, geometry alignment, and a novel action expert. Extensive experiments demonstrate state-of-the-art performance on the LIBERO-Plus benchmark and in real-world deployment, outperforming comparable baselines in success rate and robustness under diverse perturbations. To foster reproducibility and community progress, we will open-source our code, model weights, and the scripts for the curated pre-training dataset. Project page: https://getterupper.github.io/PokeVLA

Yupeng Zheng, Xiang Li, Songen Gu +12

CASIA · TARS Robotics · Tsinghua University +3

Robot Foundation Models Efficient VLA Models Robotic Manipulation Vision-Language-Action Models Vision-Language Pretraining

Apr 20, 2026cs.CL

Multilingual Training and Evaluation Resources for Vision-Language Models

Vision Language Models (VLMs) achieved rapid progress in the recent years. However, despite their growth, VLMs development is heavily grounded on English, leading to two main limitations: (i) the lack of multilingual and multimodal datasets for training, and (ii) the scarcity of comprehensive evaluation benchmarks across languages. In this work, we address these gaps by introducing a new comprehensive suite of resources for VLMs training and evaluation spanning five European languages (English, French, German, Italian, and Spanish). We adopt a regeneration-translation paradigm that produces high-quality cross-lingual resources by combining curated synthetic generation and manual annotation. Specifically, we build Multi-PixMo, a training corpus obtained regenerating examples from Pixmo pre-existing datasets with permissively licensed models: PixMo-Cap, PixMo-AskModelAnything, and CoSyn-400k. On the evaluation side, we construct a set of multilingual benchmarks derived translating widely used English datasets (MMbench, ScienceQA, MME, POPE, AI2D). We assess the quality of these resources through qualitative and quantitative human analyses, measuring inter-annotator agreement. Additionally, we perform ablation studies to demonstrate the impact of multilingual data, with respect to English only, in VLMs training. Experiments, comprising 3 different models show that using multilingual, multimodal examples for training VLMs aids is consistently beneficial on non-English benchmarks, with positive transfer to English as well.

Daniela Baiamonte, Elena Fano, Matteo Gabburo +3

Aithlas

VLM Evaluation Vision-Language Models Multilingual VLM Evaluation Vision-Language Pretraining

Mar 3, 2026cs.CV

ITO: Multi-View Alignment and Training-Time Fusion for Image-Text Pretraining

Image--text contrastive pretraining has become a dominant paradigm for visual representation learning, yet existing methods often yield representations that remain partially organized by modality rather than by semantics. We propose ITO, a framework addressing this limitation through two complementary mechanisms with distinct roles. Multimodal multiple alignment enriches supervision by constructing diverse cross-modal correspondences from multi-view image augmentations, providing the primary source of discriminative gain. A lightweight training-time multimodal fusion module then acts as a training-time regularizer, encouraging the encoders to produce features that are compatible under fusion. Crucially, the fusion module is discarded at inference, preserving the efficiency of standard dual-encoder architectures while incurring training-time overhead only. Extensive experiments across pretraining scales from millions to billions of image--text pairs show that ITO outperforms strong contrastive baselines at moderate scale and yields consistent gains over CLIP under identical data, backbone, and compute at the 100M--1B scale, on classification, retrieval, and multimodal benchmarks. Controlled comparisons show that these gains are not explained by additional training compute or image augmentation alone. Our analysis further reveals that the contribution of fusion grows with data scale and that it stabilizes optimization, mitigating the late-stage overfitting commonly observed in aggressive contrastive learning. Code is available at https://github.com/showstarpro/ITO.

Hanpeng Liu, Zidan Wang, Shuoxi Zhang +6

School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China · Li Auto Inc.

Cross-Modal Learning Cross-Modal Alignment Multimodal Contrastive Learning Multimodal Fusion Vision-Language Pretraining

Feb 18, 2026cs.CV

Xray-Visual Models: Scaling Vision models on Industry Scale Data

We present Xray-Visual, a unified vision model architecture for large-scale image and video understanding trained on industry-scale social media data. Our model leverages over 15 billion curated image-text pairs and 10 billion video-hashtag pairs from Facebook and Instagram, employing robust data curation pipelines that incorporate balancing and noise suppression strategies to maximize semantic diversity while minimizing label noise. We introduce a three-stage training pipeline that combines self-supervised MAE, semi-supervised hashtag classification, and CLIP-style contrastive learning to jointly optimize image and video modalities. Our architecture builds on a Vision Transformer backbone enhanced with efficient token reorganization (EViT) for improved computational efficiency. Extensive experiments demonstrate that Xray-Visual achieves state-of-the-art performance across diverse benchmarks, including ImageNet for image classification, Kinetics and HMDB51 for video understanding, and MSCOCO for cross-modal retrieval. The model exhibits strong robustness to domain shift and adversarial perturbations. We further demonstrate that integrating large language models as text encoders (LLM2CLIP) significantly enhances retrieval performance and generalization capabilities, particularly in real-world environments. Xray-Visual establishes new benchmarks for scalable, multimodal vision models, while maintaining superior accuracy and computational efficiency.

Shlok Mishra, Tsung-Yu Lin, Linda Wang +24

Meta-AI · MIT (work done while at Meta AI) · University of Maryland (work done while at Meta AI)

Vision Foundation Models Multimodal Pretraining Video Representation Learning Vision-Language Pretraining

Feb 16, 2026cs.CV

How to Train Your Long-Context Visual Document Model

We present the first comprehensive, large-scale study of training long-context vision language models up to 344K context, targeting long-document visual question answering with measured transfer to long-context text. While several such strong are open-weight, namely Qwen3 VL and GLM 4.5/6V, their training recipes and data pipelines are not reproducible. We systematically study continued pretraining, supervised finetuning, and preference optimization for 24B and 32B parameter models, backed by extensive LC evaluations and ablations to bridge this gap, and achieve state-of-the-art performance on MMLongBenchDoc for both parameter scales. In addition to this, our key findings include: (i) training on context lengths that match evaluation context lengths outperforms training on longer contexts, (ii) training and evaluating with page indices provides a simple, high-impact boost to long-document performance, (iii) our synthetic data pipelines enable self-improvement via continued pretraining and supervised finetuning, and (iv) we extend the known text-to-visual long context transfer to the reverse, showing that visual long context training transfers to long-context text performance. We also release MMLBD-C, a manually corrected version of MMLongBenchDoc to reduce erroneous and low quality examples in the benchmark.

Austin Veselka

LightOn

Visual Question Answering Vision-Language Models LLM Fine-Tuning Long-Context Modeling Vision-Language Pretraining Long-Context VLMs

Jan 20, 2026cs.CV

MTV: Revisiting Multi-Task Visual Representation Learning

Current visual representation learning remains bifurcated: vision-language models (e.g., CLIP) excel at global semantic alignment but lack spatial precision, while self-supervised methods (e.g., MAE, DINO) capture intricate local structures yet struggle with high-level semantic context. We argue that these paradigms are fundamentally complementary and can be integrated into a principled multi-task framework, further enhanced by dense spatial supervision. We introduce MTV, a multi-task visual pretraining framework that jointly optimizes a shared backbone across vision-language contrastive, self-supervised, and dense spatial objectives. To mitigate the need for manual annotations, we leverage high-capacity "expert" models--such as Depth Anything V2 and OWLv2--to synthesize dense, structured pseudo-labels at scale. Beyond the framework, we provide a systematic investigation into the mechanics of multi-task visual learning, analyzing: (i) the individual and marginal gain of each objective, (ii) task synergies versus interference, and (iii) scaling behavior across varying data and model scales. Our results demonstrate that MTV achieves "best-of-both-worlds" performance, significantly enhancing fine-grained spatial reasoning without compromising global semantic understanding. Our findings suggest that multi-task learning, fueled by high-quality pseudo-supervision, is a scalable path toward more general visual encoders.

Shangzhe Di, Zhonghua Zhai, Weidi Xie

SAI, Shanghai Jiao Tong University · ByteDance Seed

Visual Representation Learning Self-Supervised Visual Representation Learning Vision-Language Pretraining

Jan 11, 2026cs.CV

CLIMP: Contrastive Language-Image Mamba Pretraining

Contrastive Language-Image Pre-training (CLIP) relies on Vision Transformers whose attention mechanism is susceptible to spurious correlations, and scales quadratically with resolution. To address these limitations, We present CLIMP, the first fully Mamba-based contrastive vision-language model that replaces both the vision and text encoders with Mamba. The new architecture encodes sequential structure in both vision and language, with VMamba capturing visual spatial inductive biases, reducing reliance on spurious correlations and producing an embedding space favorable for cross-modal retrieval and out-of-distribution robustness-surpassing OpenAI's CLIP-ViT-B by 7.5% on ImageNet-O. CLIMP naturally supports variable input resolutions without positional encoding interpolation or specialized training, achieving up to 6.6% higher retrieval accuracy at 16x training resolution while using 5x less memory and 1.8x fewer FLOPs. The autoregressive text encoder further overcomes CLIP's fixed context limitation, enabling dense captioning retrieval. Our findings suggest that Mamba exhibits advantageous properties for vision-language learning, making it a compelling alternative to Transformer-based CLIP.The code and models are publicly available at https://github.com/NimrodShabtay/CLIMP}

Nimrod Shabtay, Itamar Zimerman, Eli Schwartz +1

Tel-Aviv University · IBM Research

Cross-Modal Learning VLM Robustness Mamba Vision-Language Retrieval Multimodal Foundation Models Multimodal Contrastive Learning+1