Cover Image

Reasoning Resides in Layers: Restoring Temporal Reasoning in Video-Language Models with Layer-Selective Merging

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fu, Zihang, Wang, Haonan, Kang, Jian, Kawaguchi, Kenji, Wu, Jiaying
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Fostering Video Reasoning via Next-Event Prediction
by: Wang, Haonan, et al.
Published: (2025)

STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models
by: Liang, Yiming, et al.
Published: (2026)

Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models
by: Wu, Jiaying, et al.
Published: (2025)

Temporal Reasoning Transfer from Text to Video
by: Li, Lei, et al.
Published: (2024)

STAIR: Spatial-Temporal Reasoning with Auditable Intermediate Results for Video Question Answering
by: Wang, Yueqian, et al.
Published: (2024)

Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoning
by: Hua, Jiacheng, et al.
Published: (2026)

Deep Temporal Reasoning in Video Language Models: A Cross-Linguistic Evaluation of Action Duration and Completion through Perfect Times
by: Loginova, Olga, et al.
Published: (2025)

Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data
by: Wang, Haonan, et al.
Published: (2023)

Interleaved Latent Visual Reasoning with Selective Perceptual Modeling
by: Dong, Shuai, et al.
Published: (2025)

TemMed-Bench: Evaluating Temporal Medical Image Reasoning in Vision-Language Models
by: Zhang, Junyi, et al.
Published: (2025)

On the Cultural Anachronism and Temporal Reasoning in Vision Language Models
by: Ranjan, Mukul, et al.
Published: (2026)

IdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language Models
by: You, Haoxuan, et al.
Published: (2023)

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

Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models
by: Bachu, Saketh, et al.
Published: (2024)

FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding
by: Cao, Zhuo, et al.
Published: (2024)

VideoAVE: A Multi-Attribute Video-to-Text Attribute Value Extraction Dataset and Benchmark Models
by: Cheng, Ming, et al.
Published: (2025)

HyperGVL: Benchmarking and Improving Large Vision-Language Models in Hypergraph Understanding and Reasoning
by: Wei, Yanbin, et al.
Published: (2026)

InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models
by: Liu, Xinxin, et al.
Published: (2026)

HFS: Holistic Query-Aware Frame Selection for Efficient Video Reasoning
by: Yang, Yiqing, et al.
Published: (2025)

PROGRESSLM: Towards Progress Reasoning in Vision-Language Models
by: Zhang, Jianshu, et al.
Published: (2026)

On Asymmetric Optimization of Reasoning and Perception in Vision-Language Model Post-Training
by: Wu, Xueqing, et al.
Published: (2026)

RiskCueBench: Benchmarking Anticipatory Reasoning from Early Risk Cues in Video-Language Models
by: Luo, Sha, et al.
Published: (2026)

AOR: Anatomical Ontology-Guided Reasoning for Medical Large Multimodal Model in Chest X-Ray Interpretation
by: Li, Qingqiu, et al.
Published: (2025)

Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models
by: Zhan, Xiaoyu, et al.
Published: (2025)

Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models
by: Liao, Yuan-Hong, et al.
Published: (2024)

Understanding Museum Exhibits using Vision-Language Reasoning
by: Balauca, Ada-Astrid, et al.
Published: (2024)

Investigating Video Reasoning Capability of Large Language Models with Tropes in Movies
by: Su, Hung-Ting, et al.
Published: (2024)

Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models
by: Wang, Lu, et al.
Published: (2026)

Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning
by: Tang, Yihong, et al.
Published: (2024)

Visually Descriptive Language Model for Vector Graphics Reasoning
by: Wang, Zhenhailong, et al.
Published: (2024)

ReasVQA: Advancing VideoQA with Imperfect Reasoning Process
by: Liang, Jianxin, et al.
Published: (2025)

Layer-Aware Video Composition via Split-then-Merge
by: Kara, Ozgur, et al.
Published: (2025)

Do Vision-Language Models Truly Perform Vision Reasoning? A Rigorous Study of the Modality Gap
by: Xu, Yige, et al.
Published: (2026)

MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos
by: Zhu, Kejian, et al.
Published: (2025)

Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm
by: Tong, Jingqi, et al.
Published: (2025)

Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment
by: Fei, Hao, et al.
Published: (2024)

StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos
by: Lee, Daeun, et al.
Published: (2025)

Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge
by: Wang, Yuxuan, et al.
Published: (2024)

Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models
by: Li, Yunxin, et al.
Published: (2025)

ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models
by: Wan, Zifu, et al.
Published: (2025)