Cover Image

Stateful Token Reduction for Long-Video Hybrid VLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Jindong, Deshmukh, Amala Sanjay, Chumachenko, Kateryna, Sapra, Karan, Yu, Zhiding, Liu, Guilin, Tao, Andrew, Molchanov, Pavlo, Kautz, Jan, Byeon, Wonmin
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Éclair -- Extracting Content and Layout with Integrated Reading Order for Documents
by: Karmanov, Ilia, et al.
Published: (2025)

STORM: Token-Efficient Long Video Understanding for Multimodal LLMs
by: Jiang, Jindong, et al.
Published: (2025)

AIDE: Agentically Improve Visual Language Model with Domain Experts
by: Chiu, Ming-Chang, et al.
Published: (2025)

LITA: Language Instructed Temporal-Localization Assistant
by: Huang, De-An, et al.
Published: (2024)

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding
by: Huang, De-An, et al.
Published: (2025)

Minifinetuning: Low-Data Generation Domain Adaptation through Corrective Self-Distillation
by: Belcak, Peter, et al.
Published: (2025)

AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One
by: Ranzinger, Mike, et al.
Published: (2023)

FeatSharp: Your Vision Model Features, Sharper
by: Ranzinger, Mike, et al.
Published: (2025)

Hymba: A Hybrid-head Architecture for Small Language Models
by: Dong, Xin, et al.
Published: (2024)

Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models
by: Chen, Guo, et al.
Published: (2025)

Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models
by: Fu, Yonggan, et al.
Published: (2025)

MMA-DFER: MultiModal Adaptation of unimodal models for Dynamic Facial Expression Recognition in-the-wild
by: Chumachenko, Kateryna, et al.
Published: (2024)

X-VILA: Cross-Modality Alignment for Large Language Model
by: Ye, Hanrong, et al.
Published: (2024)

C-RADIOv4 (Tech Report)
by: Ranzinger, Mike, et al.
Published: (2026)

FasterViT: Fast Vision Transformers with Hierarchical Attention
by: Hatamizadeh, Ali, et al.
Published: (2023)

RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models
by: Heinrich, Greg, et al.
Published: (2024)

Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders
by: Shi, Min, et al.
Published: (2024)

Universal Deep Research: Bring Your Own Model and Strategy
by: Belcak, Peter, et al.
Published: (2025)

Scaling RL to Long Videos
by: Chen, Yukang, et al.
Published: (2025)

Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning
by: Zhang, Shaokun, et al.
Published: (2025)

GSPN-2: Efficient Parallel Sequence Modeling
by: Wang, Hongjun, et al.
Published: (2025)

MEVG: Multi-event Video Generation with Text-to-Video Models
by: Oh, Gyeongrok, et al.
Published: (2023)

Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models
by: Li, Zhiqi, et al.
Published: (2025)

Flextron: Many-in-One Flexible Large Language Model
by: Cai, Ruisi, et al.
Published: (2024)

LongMamba: Enhancing Mamba's Long Context Capabilities via Training-Free Receptive Field Enlargement
by: Ye, Zhifan, et al.
Published: (2025)

Parallel Sequence Modeling via Generalized Spatial Propagation Network
by: Wang, Hongjun, et al.
Published: (2025)

A deeper look at depth pruning of LLMs
by: Siddiqui, Shoaib Ahmed, et al.
Published: (2024)

VILA: On Pre-training for Visual Language Models
by: Lin, Ji, et al.
Published: (2023)

LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models
by: Shi, Dachuan, et al.
Published: (2025)

International security Jstor-WOS 2010-2024
by: Chumachenko, Artem
Published: (2025)

PhyCritic: Multimodal Critic Models for Physical AI
by: Xiong, Tianyi, et al.
Published: (2026)

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

OMCAT: Omni Context Aware Transformer
by: Goel, Arushi, et al.
Published: (2024)

TwinTURBO: Semi-Supervised Fine-Tuning of Foundation Models via Mutual Information Decompositions for Downstream Task and Latent Spaces
by: Quétant, Guillaume, et al.
Published: (2025)

COIN: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimation
by: Li, Jiefeng, et al.
Published: (2024)

MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models
by: Fang, Gongfan, et al.
Published: (2024)

X-Token: Projection-Guided Cross-Tokenizer Knowledge Distillation
by: Sreenivas, Sharath Turuvekere, et al.
Published: (2026)

Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders
by: Jiang, Yitong, et al.
Published: (2026)

PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation
by: Ranzinger, Mike, et al.
Published: (2024)

TiDAR: Think in Diffusion, Talk in Autoregression
by: Liu, Jingyu, et al.
Published: (2025)