Vision-Language Models (VLMs) have shown promising capabilities in handling various multimodal tasks, yet they struggle in long-context scenarios, particularly in tasks involving videos, high-resolution images, or lengthy image-text documents. In our work, we first conduct an empirical analysis of the long-context capabilities of VLMs using our augmented long-context multimodal datasets. Our findings reveal that directly applying the positional encoding mechanism used for textual tokens to visual tokens is suboptimal, and VLM performance degrades sharply when the position encoding exceeds the model's context window. To address this, we propose Variable Visual Position Encoding (V2PE), a novel positional encoding approach that employs variable and smaller increments for visual tokens, enabling more efficient management of long multimodal sequences. Our experiments demonstrate the effectiveness of V2PE to enhances VLMs' ability to effectively understand and reason over long multimodal contexts. We further integrate V2PE with our augmented long-context multimodal datasets to fine-tune the open-source VLM, InternVL2. The fine-tuned model achieves strong performance on both standard and long-context multimodal tasks. Notably, when the sequence length of the training dataset is increased to 256K tokens, the model is capable of processing multimodal sequences up to 1M tokens, highlighting its potential for real-world long-context applications.

Videos incorporate rich semantics as well as redundant information. Seeking a compact yet effective video representation, e.g., sample informative frames from the entire video, is critical to efficient video recognition. There have been works that formulate frame sampling as a sequential decision task by selecting frames one by one according to their importance. In this paper, we present a more efficient framework named OCSampler, which explores such a representation with one short clip. OCSampler designs a new paradigm of learning instance-specific video condensation policies to select frames only in a single step. Rather than picking up frames sequentially like previous methods, we simply process a whole sequence at once. Accordingly, these policies are derived from a light-weighted skim network together with a simple yet effective policy network. Moreover, we extend the proposed method with a frame number budget, enabling the framework to produce correct predictions in high confidence with as few frames as possible. Experiments on various benchmarks demonstrate the effectiveness of OCSampler over previous methods in terms of accuracy and efficiency. Specifically, it achieves 76.9% mAP and 21.7 GFLOPs on ActivityNet with an impressive throughput: 123.9 Video/s on a single TITAN Xp GPU.

Information-Centric Networking (ICN) is a commercially viable network architecture that enables content and location separation through in-network caching, reducing dupli-cate traffic and improving network resource utilisation. As with other networks, a reasonable pricing mechanism can facilitate the deployment of ICNs by encouraging operators to participate in the deployment of ICNs. A large number of studies on ICN pricing mechanisms have been conducted in which users pay for traffic on a per-unit basis, as opposed to the real-life method of paying for traffic on packages set by operators. In this paper, based on studying the interaction between users and ISPs and CPs and establishing the utility functions of each role, we analyse the caching and pricing strategies of each entity under NASH equilibrium and compare and analyse which charging model is more able to meet the needs of network entities in the ICN environment. It is found that the package billing model is more in line with the needs of operators and users in I CN s, and can achieve the objective of incentivising ICN development. This paper also contributes to the development of the best pricing strategy for ICN networks.

In Cognitive Radio (CR) networks, it is common that the spectrum holes are too narrow to support high-speed communications. Discontinuous Orthogonal Frequency Division Multiplexing (DOFDM) is a good way for a secondary user to access several spectrum fragments simultaneously with one Radio Front (RF). In this paper, a novel Channel Characteristic Aware Spectrum Aggregation (CCASA) algorithm which uses DOFDM to aggregation spectrum fragments with only one radio front is proposed in order to increase the overall throughput of a CR network. By combining Adaptive Modulation and Coding (AMC) and spectrum aggregation, the good subcarriers are assigned to the specific secondary users in CCASA algorithm thus achieving a better channel efficiency. Different bandwidth requirement and aggregation limitation of secondary users are both considered in this algorithm while maintaining a fairly low computational complexity. The simulation results show that CCASA achieves a bigger total throughput than existing aggregation algorithms.