arXiv Computer Vision

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

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.

arXiv Computer Vision
4d ago

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
Hugging Face Trending Papers
Aug 3

CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models

In video understanding, vision-language models (VLMs) must ingest massive numbers of visual tokens, causing the computational and memory cost of the prefill stage to rise sharply. Such visual sequences are highly redundant along the spatio-temporal dimension, yet a high compression ratio is often accompanied by the loss of critical details.

arXiv AI
Aug 11

Not All Visual Tokens Are Equally Safe to Remove:Consequence-Sensitive Visual Token Compression

arXiv:2608. 09176v1 Announce Type: cross Abstract: Visual token compression for vision--language models (VLMs) has largely relied on criteria such as attention, redundancy, and uncertainty to maximize average accuracy under a fixed compute budget, implicitly assuming that all errors carry equal cost.

By Jingbo Wen, Liang He, Mingyu Cao, Haoyu Wang, Minxuan Hu, Kangning Cui, Xilu Wang
arXiv Machine Learning
Jun 30

DataComp-VLM: Improved Open Datasets for Vision-Language Models

arXiv:2606. 28551v1 Announce Type: cross Abstract: Building performant Vision-Language Models (VLMs) requires carefully curating large-scale training datasets, yet the community lacks systematic benchmarks for evaluating such curation strategies.

By Matteo Farina, Vishaal Udandarao, Thao Nguyen, Selim Kuzucu, Maximilian B\"other, Andreas Hochlehnert, Adhiraj Ghosh, Marianna Nezhurina, Karsten Roth, Joschka Struber, Yuhui Zhang, Sebastian Dziadzio, Elaine Sui, Soumya Jahagirdar, Dhruba Ghosh, Hasan Hammoud, Thomas De Min, Simone Caldarella, Jehanzeb Mirza, Sedrick Keh, Mehdi Cherti, Hilde Kuehne, Bernt Schiele, Serena Yeung-Levy, Muhammad Ferjad Naeem, Federico Tombari, Ana Klimovic, Elisa Ricci, Matthias Bethge, Sewoong Oh, Ameya Prabhu, Alessio Tonioni, Jenia Jitsev, Massimiliano Mancini, Ludwig Schmidt, Nikhil Parthasarathy
arXiv AI
Aug 28

PACE: A Unified Condense-and-Extract Paradigm for Fast VLM Inference

PACE introduces a training‑free Condense‑and‑Extract framework that speeds up Vision‑Language Model inference by first adaptively downsampling visual inputs before encoding and then selectively retaining essential tokens during decoding. The Adaptive Pixel Compressor (APC) reduces encoder workload while preserving global context, and the Dynamic Dual‑Attention Extractor (DDAE) keeps task‑critical details by fusing visual and language signals. Applied to Qwen2.5‑VL‑7B, PACE maintains 93.8% of performance using only 10% of visual tokens, achieving a 3.1× speedup in time to first token.

By Junjie Liu, Shengyuan Ye, Xu Chen
arXiv AI
Aug 26

VisCache: Visual KV Cache Pruning for Efficient Vision Large Language Model Inference

VisCache introduces a two-stage, plug‑and‑play framework for pruning visual key‑value caches in Vision Large Language Models without retraining. The first stage filters out temporally redundant keyframes, while the second stage, PruneKV, applies a parabolic layer‑wise budget and asymmetric update to selectively prune keys and fuse values, preserving essential context. Experiments show up to 2.35× speedup and significant memory savings with only 19–28% of the original cache retained, outperforming existing baselines.

By Lyuke Wang, Zhuo Li, Guangxu Zhu
arXiv AI
Aug 5

Adaptive Two-Stage Visual Token Pruning for Efficient Inference in Video-Language Models

arXiv:2608. 03112v1 Announce Type: cross Abstract: Vision-language models excel at image and video understanding but suffer from high inference latency due to the need to process thousands of tokens per image, limiting their deployment on resource-constrained edge devices and in real-time surveillance applications.

By Paribesh Regmi, Qingshuang Chen, Chi Zhang, Heba Aly, Yelin Kim, Hongda Mao