arXiv Computer Vision August 31, 2026 By Xiaoyang Guo, Guoping Luo, Jusheng Zhang, Keze Wang, Wenhao Wang

Token-Budget Distillation: Transferring Full-Token Semantics to Compressed Video Vision-Language Models

Read the original on arXiv Computer Vision →

Token-Budget Distillation (TBD) is a parameter‑efficient fine‑tuning framework that adapts video vision‑language models to a fixed token budget. It freezes the pretrained backbone, updates only LoRA adapters, and incorporates FlashVID visual token compression. TBD uses a dual‑path teacher‑student design with full‑token supervision and compressed student optimization, enabling the student to recover full‑token semantics while remaining efficient under aggressive token reduction.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Computer Vision

4d ago

KiToke: Distribution-Aware Token Compression for Video Large Language Models

arXiv:2604.03414v2 Announce Type: replace Abstract: Video Large Language Models (Video LLMs) achieve strong performance on video understanding tasks but suffer from high inference costs due to the la...

By Haifeng Huang, Biyin Xu, Yang Li

llms rag benchmarks

arXiv Computer Vision

Oct 2

Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction

arXiv:2609.32353v2 Announce Type: replace Abstract: Visual token reduction is an effective way to accelerate multimodal large language models (MLLMs), but performance deteriorates rapidly under extre...

By Junxian Li, Ruixuan Yang, Tianao Zhang, Tiange Xu, Weisheng Dong, Yulun Zhang

llms efficiency multimodal benchmarks

arXiv Computer Vision

Aug 31

Visual Token Coding for Video Multimodal Large Language Models

The paper introduces Visual Token Coding (VTC), a token compression method for video multimodal large language models that mimics classical video coding by predicting I/P frames and measuring residuals to reduce token redundancy. VTC is extended with dynamic features—Dynamic Resolution Input, Dynamic Token Allocation, and Spatial Coverage Top‑K—forming VTC_Dy, which can be applied to existing MLLMs without additional tuning. Experiments on three MLLMs and multiple video benchmarks show that VTC_Dy retains over 100% of average performance with a 50% token budget and 97.8% with a 25% budget, while the code is publicly available.

By Chenxin Fang, Tao Chen, JunChao You, Jun Peng, Yiyi Zhou, Rongrong Ji

llms multimodal benchmarks

arXiv AI

Jul 2

Stateful Token Reduction for Long-Video Hybrid VLMs

arXiv:2603. 00198v2 Announce Type: replace-cross Abstract: Token reduction accelerates long-video vision--language models (VLMs), but existing methods target Transformers, where reduction is treated as token pruning.

By Jindong Jiang, Amala Sanjay Deshmukh, Kateryna Chumachenko, Karan Sapra, Zhiding Yu, Guilin Liu, Andrew Tao, Pavlo Molchanov, Jan Kautz, Wonmin Byeon

llms fine-tuning efficiency benchmarks

arXiv AI

Aug 12

Hybrid Token Compression for Vision-Language Models

arXiv:2512. 08240v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) rely on hundreds of visual tokens, leading to high computational and memory costs.

By Jusheng Zhang, Xiaoyang Guo, Tongyu Mo, Qinhan Lv, Wenhao Chai, Jian Wang, Keze Wang, Liang Lin

llms efficiency multimodal benchmarks

arXiv Computer Vision

Oct 2

SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation

arXiv:2610.00686v1 Announce Type: new Abstract: Recent video-based world models pair the scalability of autoregressive (AR) prediction with the visual quality of diffusion models. The choice of scene...

By Mikhail Dereviannykh, Vikram Voleti, Simon Donne, Mallikarjun Byrasandra Ramalinga Reddy, Shimon Vainer, Mark Boss

diffusion nlp safety

One email a morning, machine-written

Related stories

KiToke: Distribution-Aware Token Compression for Video Large Language Models

Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction

Visual Token Coding for Video Multimodal Large Language Models

Stateful Token Reduction for Long-Video Hybrid VLMs

Hybrid Token Compression for Vision-Language Models

SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation