Copertina

From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lian, Niu, Wang, Yuting, Yao, Hanshu, Wang, Jinpeng, Chen, Bin, Wang, Yaowei, Zhang, Min, Xia, Shu-Tao
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Information Retrieval Multimedia
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

AutoSSVH: Exploring Automated Frame Sampling for Efficient Self-Supervised Video Hashing
di: Lian, Niu, et al.
Pubblicazione: (2025)

Imagine Before Concentration: Diffusion-Guided Registers Enhance Partially Relevant Video Retrieval
di: Li, Jun, et al.
Pubblicazione: (2026)

HLFormer: Enhancing Partially Relevant Video Retrieval with Hyperbolic Learning
di: Li, Jun, et al.
Pubblicazione: (2025)

Efficient Self-Supervised Video Hashing with Selective State Spaces
di: Wang, Jinpeng, et al.
Pubblicazione: (2024)

GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval
di: Wang, Yuting, et al.
Pubblicazione: (2023)

Revisiting Uncertainty: On Evidential Learning for Partially Relevant Video Retrieval
di: Li, Jun, et al.
Pubblicazione: (2026)

Love Me, Love My Label: Rethinking the Role of Labels in Prompt Retrieval for Visual In-Context Learning
di: Luo, Tianci, et al.
Pubblicazione: (2026)

Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval
di: Xiao, Jian, et al.
Pubblicazione: (2025)

SemCORE: A Semantic-Enhanced Generative Cross-Modal Retrieval Framework with MLLMs
di: Li, Haoxuan, et al.
Pubblicazione: (2025)

From Swath to Full-Disc: Advancing Precipitation Retrieval with Multimodal Knowledge Expansion
di: Wang, Zheng, et al.
Pubblicazione: (2025)

Beyond Static Collision Handling: Adaptive Semantic ID Learning for Multimodal Recommendation at Industrial Scale
di: Pan, Yongsen, et al.
Pubblicazione: (2026)

Dynamic Multimodal Fusion via Meta-Learning Towards Micro-Video Recommendation
di: Liu, Han, et al.
Pubblicazione: (2025)

Balancing Semantic Relevance and Engagement in Related Video Recommendations
di: Jaspal, Amit, et al.
Pubblicazione: (2025)

Multimodal Misinformation Detection using Large Vision-Language Models
di: Tahmasebi, Sahar, et al.
Pubblicazione: (2024)

Hierarchical Vision-Language Reasoning for Multimodal Multiple-Choice Question Answering
di: Zhou, Ao, et al.
Pubblicazione: (2025)

AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agents
di: Jin, Jiarui, et al.
Pubblicazione: (2026)

VisTopics: A Visual Semantic Unsupervised Approach to Topic Modeling of Video and Image Data
di: Lokmanoglu, Ayse D, et al.
Pubblicazione: (2025)

MCA: Modality Composition Awareness for Robust Composed Multimodal Retrieval
di: Wu, Qiyu, et al.
Pubblicazione: (2025)

Why Multi-Interest Fairness Matters: Hypergraph Contrastive Multi-Interest Learning for Fair Conversational Recommender System
di: Zheng, Yongsen, et al.
Pubblicazione: (2025)

Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval
di: Kong, Fanheng, et al.
Pubblicazione: (2025)

MMSRARec: Summarization and Retrieval Augumented Sequential Recommendation Based on Multimodal Large Language Model
di: Wang, Haoyu, et al.
Pubblicazione: (2025)

Very Efficient Listwise Multimodal Reranking for Long Documents
di: Sun, Yiqun, et al.
Pubblicazione: (2026)

CM$^3$: Calibrating Multimodal Recommendation
di: Zhou, Xin, et al.
Pubblicazione: (2025)

GenState-AI: State-Aware Dataset for Text-to-Video Retrieval on AI-Generated Videos
di: Li, Minghan, et al.
Pubblicazione: (2026)

Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval
di: Ning, Hailong, et al.
Pubblicazione: (2025)

CoPRS: Learning Positional Prior from Chain-of-Thought for Reasoning Segmentation
di: Lu, Zhenyu, et al.
Pubblicazione: (2025)

Interactive Multi-Turn Retrieval for Health Videos
di: Wu, Chengzheng, et al.
Pubblicazione: (2026)

Any2Any: Incomplete Multimodal Retrieval with Conformal Prediction
di: Li, Po-han, et al.
Pubblicazione: (2024)

VKIE: The Application of Key Information Extraction on Video Text
di: An, Siyu, et al.
Pubblicazione: (2023)

Benchmarking Multimodal Large Language Models for Missing Modality Completion in Product Catalogues
di: Fu, Junchen, et al.
Pubblicazione: (2026)

Automating Steering for Safe Multimodal Large Language Models
di: Wu, Lyucheng, et al.
Pubblicazione: (2025)

CLEAR: Null-Space Projection for Cross-Modal De-Redundancy in Multimodal Recommendation
di: Zhan, Hao, et al.
Pubblicazione: (2026)

Learning Partially-Decorrelated Common Spaces for Ad-hoc Video Search
di: Hu, Fan, et al.
Pubblicazione: (2025)

OTCR: Optimal Transmission, Compression and Representation for Multimodal Information Extraction
di: Li, Yang, et al.
Pubblicazione: (2025)

CLOSP: A Unified Semantic Space for SAR, MSI, and Text in Remote Sensing
di: Cambrin, Daniele Rege, et al.
Pubblicazione: (2025)

CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image Perception
di: Li, Liupeng, et al.
Pubblicazione: (2026)

Mitigating Modality Bias in Multi-modal Entity Alignment from a Causal Perspective
di: Su, Taoyu, et al.
Pubblicazione: (2025)

Verifying Cross-modal Entity Consistency in News using Vision-language Models
di: Tahmasebi, Sahar, et al.
Pubblicazione: (2025)

PREMISE: Matching-based Prediction for Accurate Review Recommendation
di: Han, Wei, et al.
Pubblicazione: (2025)

Multimodal Neural Databases
di: Trappolini, Giovanni, et al.
Pubblicazione: (2023)