Copertina

Visual Representations inside the Language Model

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Benlin, Kamath, Amita, Grunde-McLaughlin, Madeleine, Han, Winson, Krishna, Ranjay
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

The Hard Positive Truth about Vision-Language Compositionality
di: Kamath, Amita, et al.
Pubblicazione: (2024)

Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning
di: Kamath, Amita, et al.
Pubblicazione: (2026)

Seeking and Updating with Live Visual Knowledge
di: Fu, Mingyang, et al.
Pubblicazione: (2025)

Designing LLM Chains by Adapting Techniques from Crowdsourcing Workflows
di: Grunde-McLaughlin, Madeleine, et al.
Pubblicazione: (2023)

Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models
di: Hu, Yushi, et al.
Pubblicazione: (2024)

Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models
di: Hu, Yushi, et al.
Pubblicazione: (2023)

Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment
di: Chen, Dongping, et al.
Pubblicazione: (2024)

CapNav: Benchmarking Vision Language Models on Capability-conditioned Indoor Navigation
di: Su, Xia, et al.
Pubblicazione: (2026)

Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models
di: Maharana, Adyasha, et al.
Pubblicazione: (2023)

Matryoshka Query Transformer for Large Vision-Language Models
di: Hu, Wenbo, et al.
Pubblicazione: (2024)

GenEval 2: Addressing Benchmark Drift in Text-to-Image Evaluation
di: Kamath, Amita, et al.
Pubblicazione: (2025)

Reinforced Visual Perception with Tools
di: Zhou, Zetong, et al.
Pubblicazione: (2025)

Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models
di: Che, Liwei, et al.
Pubblicazione: (2026)

Efficient Inference of Vision Instruction-Following Models with Elastic Cache
di: Liu, Zuyan, et al.
Pubblicazione: (2024)

Structure From Tracking: Distilling Structure-Preserving Motion for Video Generation
di: Fei, Yang, et al.
Pubblicazione: (2025)

m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks
di: Ma, Zixian, et al.
Pubblicazione: (2024)

NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples
di: Li, Baiqi, et al.
Pubblicazione: (2024)

Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos
di: Seyfioglu, Mehmet Saygin, et al.
Pubblicazione: (2023)

Holodeck: Language Guided Generation of 3D Embodied AI Environments
di: Yang, Yue, et al.
Pubblicazione: (2023)

Video-Based Reward Modeling for Computer-Use Agents
di: Song, Linxin, et al.
Pubblicazione: (2026)

PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning
di: Li, Shaoxuan, et al.
Pubblicazione: (2026)

Ablate-to-Validate: Are Vision-Language Models Really Using Continuous Thought Tokens?
di: Zhang, Tianyi, et al.
Pubblicazione: (2026)

Refining Skewed Perceptions in Vision-Language Contrastive Models through Visual Representations
di: Dai, Haocheng, et al.
Pubblicazione: (2024)

Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model
di: Liu, Benlin, et al.
Pubblicazione: (2024)

Semantic and Expressive Variation in Image Captions Across Languages
di: Ye, Andre, et al.
Pubblicazione: (2023)

RoboUniView: Visual-Language Model with Unified View Representation for Robotic Manipulation
di: Liu, Fanfan, et al.
Pubblicazione: (2024)

FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations
di: Hsieh, Cheng-Yu, et al.
Pubblicazione: (2025)

BLINK: Multimodal Large Language Models Can See but Not Perceive
di: Fu, Xingyu, et al.
Pubblicazione: (2024)

Iterated Learning Improves Compositionality in Large Vision-Language Models
di: Zheng, Chenhao, et al.
Pubblicazione: (2024)

VividMed: Vision Language Model with Versatile Visual Grounding for Medicine
di: Luo, Lingxiao, et al.
Pubblicazione: (2024)

Posterior Augmented Flow Matching
di: Stoica, George, et al.
Pubblicazione: (2026)

AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning
di: Song, Mingyang, et al.
Pubblicazione: (2026)

Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models
di: Li, Zhuowan, et al.
Pubblicazione: (2022)

ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers
di: Yuan, Qianhao, et al.
Pubblicazione: (2025)

Exploring the Design Space of Visual Context Representation in Video MLLMs
di: Du, Yifan, et al.
Pubblicazione: (2024)

Vision-Language Modeling in PET/CT for Visual Grounding of Positive Findings
di: Huemann, Zachary, et al.
Pubblicazione: (2025)

LongVILA: Scaling Long-Context Visual Language Models for Long Videos
di: Chen, Yukang, et al.
Pubblicazione: (2024)

Do Vision-Language Models Really Understand Visual Language?
di: Hou, Yifan, et al.
Pubblicazione: (2024)

SCoPE VLM: Selective Context Processing for Efficient Document Navigation in Vision-Language Models
di: Lim, Gyubeum, et al.
Pubblicazione: (2025)

Clean Evaluations on Contaminated Visual Language Models
di: Lu, Hongyuan, et al.
Pubblicazione: (2024)