Cover Image

Fwd2Bot: LVLM Visual Token Compression with Double Forward Bottleneck

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bulat, Adrian, Ouali, Yassine, Tzimiropoulos, Georgios
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FFF: Fixing Flawed Foundations in contrastive pre-training results in very strong Vision-Language models
by: Bulat, Adrian, et al.
Published: (2024)

VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions
by: Bulat, Adrian, et al.
Published: (2026)

CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs
by: Ouali, Yassine, et al.
Published: (2024)

VladVA: Discriminative Fine-tuning of LVLMs
by: Ouali, Yassine, et al.
Published: (2024)

Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions
by: Ntinou, Ioanna, et al.
Published: (2025)

Beyond Sight: Towards Cognitive Alignment in LVLM via Enriched Visual Knowledge
by: Zhao, Yaqi, et al.
Published: (2024)

LLaVA-Zip: Adaptive Visual Token Compression with Intrinsic Image Information
by: Wang, Ke, et al.
Published: (2024)

Make Your LVLM KV Cache More Lightweight
by: Chen, Xihao, et al.
Published: (2026)

Free$^2$Guide: Training-Free Text-to-Video Alignment using Image LVLM
by: Kim, Jaemin, et al.
Published: (2024)

Hierarchical Image Tokenization for Multi-Scale Image Super Resolution
by: Hadji, Isma, et al.
Published: (2026)

Unveiling the Lack of LVLM Robustness to Fundamental Visual Variations: Why and Path Forward
by: Fan, Zhiyuan, et al.
Published: (2025)

Uncertainty-DTW for Sequences and Visual Tokens
by: Wang, Lei, et al.
Published: (2026)

VIBE: Visual Instruction Based Editor
by: Alekseenko, Grigorii, et al.
Published: (2026)

Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution
by: Wang, Ying, et al.
Published: (2023)

Explanation Bottleneck Models
by: Yamaguchi, Shin'ya, et al.
Published: (2024)

SceneTok: A Compressed, Diffusable Token Space for 3D Scenes
by: Asim, Mohammad, et al.
Published: (2026)

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers
by: You, Haoran, et al.
Published: (2024)

PRE: Vision-Language Prompt Learning with Reparameterization Encoder
by: Pham, Thi Minh Anh, et al.
Published: (2023)

The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design
by: Liu, Anjie, et al.
Published: (2026)

Communication Efficient Split Learning of ViTs with Attention-based Double Compression
by: Alvetreti, Federico, et al.
Published: (2025)

Token Activation Map to Visually Explain Multimodal LLMs
by: Li, Yi, et al.
Published: (2025)

VTBench: Evaluating Visual Tokenizers for Autoregressive Image Generation
by: Lin, Huawei, et al.
Published: (2025)

Mixture of Nested Experts: Adaptive Processing of Visual Tokens
by: Jain, Gagan, et al.
Published: (2024)

Editable Concept Bottleneck Models
by: Hu, Lijie, et al.
Published: (2024)

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens
by: Qin, Yiming, et al.
Published: (2025)

Sign Lock-In: Randomly Initialized Weight Signs Persist and Bottleneck Sub-Bit Model Compression
by: Sakai, Akira, et al.
Published: (2026)

Convolutional Channel-wise Competitive Learning for the Forward-Forward Algorithm
by: Papachristodoulou, Andreas, et al.
Published: (2023)

Perception Tokens Enhance Visual Reasoning in Multimodal Language Models
by: Bigverdi, Mahtab, et al.
Published: (2024)

Continual Learning: Applications and the Road Forward
by: Verwimp, Eli, et al.
Published: (2023)

Analyzing The Language of Visual Tokens
by: Chan, David M., et al.
Published: (2024)

Zero-shot Concept Bottleneck Models
by: Yamaguchi, Shin'ya, et al.
Published: (2025)

Process-Guided Concept Bottleneck Model
by: Asiyabi, Reza M., et al.
Published: (2026)

Semi-supervised Concept Bottleneck Models
by: Hu, Lijie, et al.
Published: (2024)

Pushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail Targeting
by: Zhao, Xiaohan, et al.
Published: (2026)

Thinking with Patterns: Breaking the Perceptual Bottleneck in Visual Planning via Pattern Induction
by: Jian, Yichang, et al.
Published: (2026)

Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models
by: Wang, Yubo, et al.
Published: (2024)

Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters
by: Li, Kevin Y., et al.
Published: (2024)

TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration
by: Olszewski, Jan, et al.
Published: (2023)

SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise
by: Feng, Chen, et al.
Published: (2021)

DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models
by: Alvar, Saeed Ranjbar, et al.
Published: (2025)