Copertina

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xie, Jiahao, Tonioni, Alessio, Rauschmayr, Nathalie, Tombari, Federico, Schiele, Bernt
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

R-CoV: Region-Aware Chain-of-Verification for Alleviating Object Hallucinations in LVLMs
di: Xie, Jiahao, et al.
Pubblicazione: (2026)

Test-Time Visual In-Context Tuning
di: Xie, Jiahao, et al.
Pubblicazione: (2025)

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs
di: Kuzucu, Selim, et al.
Pubblicazione: (2025)

PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding
di: Kuzucu, Selim, et al.
Pubblicazione: (2026)

RefAM: Attention Magnets for Zero-Shot Referral Segmentation
di: Kukleva, Anna, et al.
Pubblicazione: (2025)

ClipTTT: CLIP-Guided Test-Time Training Helps LVLMs See Better
di: Nath, Mriganka, et al.
Pubblicazione: (2026)

LIME: Localized Image Editing via Attention Regularization in Diffusion Models
di: Simsar, Enis, et al.
Pubblicazione: (2023)

Extracting Training Data from Document-Based VQA Models
di: Pinto, Francesco, et al.
Pubblicazione: (2024)

UIP2P: Unsupervised Instruction-based Image Editing via Edit Reversibility Constraint
di: Simsar, Enis, et al.
Pubblicazione: (2024)

Text-Conditioned Resampler For Long Form Video Understanding
di: Korbar, Bruno, et al.
Pubblicazione: (2023)

Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos
di: Plizzari, Chiara, et al.
Pubblicazione: (2025)

AIM: Amending Inherent Interpretability via Self-Supervised Masking
di: Alshami, Eyad, et al.
Pubblicazione: (2025)

Reading Between the Lines: Abstaining from VLM-Generated OCR Errors via Latent Representation Probes
di: Yao, Jihan, et al.
Pubblicazione: (2025)

Active Data Curation Effectively Distills Large-Scale Multimodal Models
di: Udandarao, Vishaal, et al.
Pubblicazione: (2024)

VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow
di: Gorgun, Ada, et al.
Pubblicazione: (2025)

Toward a Diffusion-Based Generalist for Dense Vision Tasks
di: Fan, Yue, et al.
Pubblicazione: (2024)

How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations
di: Gairola, Siddhartha, et al.
Pubblicazione: (2025)

SSL-SLR: Self-Supervised Representation Learning for Sign Language Recognition
di: Madjoukeng, Ariel Basso, et al.
Pubblicazione: (2025)

Adversarial Training against Location-Optimized Adversarial Patches
di: Rao, Sukrut, et al.
Pubblicazione: (2020)

BRAVE: Broadening the visual encoding of vision-language models
di: Kar, Oğuzhan Fatih, et al.
Pubblicazione: (2024)

MTA-CLIP: Language-Guided Semantic Segmentation with Mask-Text Alignment
di: Das, Anurag, et al.
Pubblicazione: (2024)

Scribbles for All: Benchmarking Scribble Supervised Segmentation Across Datasets
di: Boettcher, Wolfgang, et al.
Pubblicazione: (2024)

Do Instance Priors Help Weakly Supervised Semantic Segmentation?
di: Das, Anurag, et al.
Pubblicazione: (2026)

SimNP: Learning Self-Similarity Priors Between Neural Points
di: Wewer, Christopher, et al.
Pubblicazione: (2023)

Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement
di: Khan, Zaid, et al.
Pubblicazione: (2024)

OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning
di: Ahmed, Noor, et al.
Pubblicazione: (2024)

DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring
di: Dong, Jiangxin, et al.
Pubblicazione: (2021)

Rewis3d: Reconstruction Improves Weakly-Supervised Semantic Segmentation
di: Ernst, Jonas, et al.
Pubblicazione: (2026)

AnyUp: Universal Feature Upsampling
di: Wimmer, Thomas, et al.
Pubblicazione: (2025)

InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenes
di: Shahbazi, Mohamad, et al.
Pubblicazione: (2024)

MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Querying
di: Shi, Shaoshuai, et al.
Pubblicazione: (2023)

Training-free Online Video Step Grounding
di: Zanella, Luca, et al.
Pubblicazione: (2025)

Learning to Prompt with Text Only Supervision for Vision-Language Models
di: Khattak, Muhammad Uzair, et al.
Pubblicazione: (2024)

Optimising for Interpretability: Convolutional Dynamic Alignment Networks
di: Böhle, Moritz, et al.
Pubblicazione: (2021)

Towards Better Understanding Attribution Methods
di: Rao, Sukrut, et al.
Pubblicazione: (2022)

B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers
di: Böhle, Moritz, et al.
Pubblicazione: (2023)

FullFlow: Upgrading Text-to-Image Flow Matching Models for Bidirectional Vision--Language Generation
di: Bill, Eric Tillmann, et al.
Pubblicazione: (2026)

Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventions
di: Gorgun, Ada, et al.
Pubblicazione: (2025)

PP-SSL : Priority-Perception Self-Supervised Learning for Fine-Grained Recognition
di: Li, ShuaiHeng, et al.
Pubblicazione: (2024)

Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model
di: Wang, Hanqing, et al.
Pubblicazione: (2025)