Effective token compression remains a critical challenge for scaling models to handle increasingly complex and diverse datasets. A novel mechanism based on contextual reinforcement is introduced, dynamically adjusting token importance through interdependencies and semantic relevance. This approach enables substantial reductions in token usage while preserving the quality and coherence of information representation. Incorporating graph-based algorithms and adaptive weighting, the method captures subtle contextual relationships across textual and multimodal data, ensuring robust alignment and performance in downstream tasks. Evaluations across varied domains reveal significant improvements in accuracy and semantic retention, particularly for tasks requiring detailed cross-modal interactions. Memory usage analyses demonstrate improved computational efficiency, with minimal overhead despite the additional reinforcement processes. Performance gains are further validated through error distribution analyses, showing reduced semantic loss and syntactic inconsistencies compared to baseline models. The modular architecture ensures compatibility with a wide range of open-source frameworks, facilitating scalable implementation for real-world applications. These findings highlight the potential of contextual reinforcement in redefining token management strategies and advancing large-scale model design.
MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues
University of Notre Dame(诺丁汉大学);University of California, Los Angeles(加州大学洛杉矶分校);Georgia Institute of Technology(佐治亚理工学院);University of Montreal(蒙特利尔大学)
Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors
School of Computer Science and Engineering, Northeastern University, Shenyang, China(东北大学计算机科学与工程学院,中国沈阳);NiuTrans Research, Shenyang, China(沈阳NiuTrans研究院,中国);Kunming University of Science and Technology, Kunming, China(昆明理工大学,中国昆明)
Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression
Ping An Technology (Shenzhen) Co., Ltd., China(平安科技(深圳)有限公司,中国);University of Science and Technology of China(中国科学技术大学);University of Electronic Science and Technology of China(电子科技大学)
ContextNav: Towards Agentic Multimodal In-Context Learning
The University of Queensland(昆士兰大学);Nanjing University(南京大学);University of California, Los Angeles(加州大学洛杉矶分校);University of California, Merced(加州大学默塞德分校)
Revisiting Multimodal KV Cache Compression: A Frequency-Domain-Guided Outlier-KV-Aware Approach
College of Future Information Technology, Fudan University(未来信息科技学院,复旦大学);Shanghai Innovation Institute(上海创新研究院);The Chinese University of Hong Kong(香港中文大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Zhangjiang Laboratory(张江实验室)
AdaTok: Adaptive Token Compression with Object-Aware Representations for Efficient Multimodal LLMs
Institute of Medical Technology, Peking University Health Science Center(北京大学医学部医学技术研究所);Department of Biomedical Engineering, Peking University(北京大学生物医学工程系);National Biomedical Imaging Center, Peking University(北京大学国家生物医学成像中心)
HybridKV: Hybrid KV Cache Compression for Efficient Multimodal Large Language Model Inference
The State Key Laboratory of Blockchain and Data Security, Zhejiang University(浙江大学区块链与数据安全国家重点实验室);Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security(杭州高新区(滨江)区块链与数据安全研究院);Hangzhou Dianzi University(杭州电子科技大学)
Dependency, Compression, and Synergy: A Unified Information-Theoretic View of Multimodal Learning
School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics(西南财经大学计算机与人工智能学院);Beijing Humanoid Robot Innovation Center (X-Humanoid)(北京人形机器人创新中心(X-Humanoid));Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);University of Electronic Science and Technology of China(电子科技大学)
Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring
School of Software Engineering, Xi’an Jiaotong University(西安交通大学软件工程学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Harbin Institute of Technology, Shenzhen(深圳哈尔滨工业大学);University of Science and Technology Beijing(北京科技大学)
UniICL: An Efficient Unified Framework Unifying Compression, Selection, and Generation
School of Computer Science and Technology, Soochow University(苏州大学计算机科学与技术学院);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳));Hong Kong Polytechnic University(香港理工大学);Stepfun
SpikeMLLM: Spike-based Multimodal Large Language Models via Modality-Specific Temporal Scales and Temporal Compression
1 Institute of Automation, Chinese Academy of Sciences 2 University of Chinese Academy of Sciences 3 Beijing Academy of Artificial Intelligence 4 Zhongguancun Academy 5 Peking University 6 Key Laboratory of Brain Cognition;Brain-inspired Intelligence Technology 7 Spiking Intelligence Lab, Tianqiao \& Chrissy Chen Institute [0.5em] Equal contribution Corresponding authors
PiCo: Jailbreaking Multimodal Large Language Models via Pictorial Code Contextualization
School of Artificial Intelligence, Wuhan University(武汉大学人工智能学院);School of Electronic and Computer Engineering, Peking University(北京大学电子与计算机工程学院);Beijing Academy of Artificial Intelligence(北京人工智能研究院)
ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University(厦门大学多媒体可信感知与高效计算教育部重点实验室);National University of Defense Technology(国防科技大学)