Scene generation with 3D assets presents a complex challenge, requiring both high-level semantic understanding and low-level geometric reasoning. While Multimodal Large Language Models (MLLMs) excel at semantic tasks, their application to 3D scene generation is hindered by their limited grounding on 3D geometry. In this paper, we investigate how to best work with MLLMs in an object placement task. Towards this goal, we introduce a novel framework, FirePlace, that applies existing MLLMs in (1) 3D geometric reasoning and the extraction of relevant geometric details from the 3D scene, (2) constructing and solving geometric constraints on the extracted low-level geometry, and (3) pruning for final placements that conform to common sense. By combining geometric reasoning with real-world understanding of MLLMs, our method can propose object placements that satisfy both geometric constraints as well as high-level semantic common-sense considerations. Our experiments show that these capabilities allow our method to place objects more effectively in complex scenes with intricate geometry, surpassing the quality of prior work.

360-degree video is on the cusp of going mainstream. Such videos have a large size (4-5⌉ the size of a regular one). Since each viewer has to wear Head-Mounted Display (HMD), screen sharing is impossible when a group is watching the same content. Multiple parallel video-streams will be required to serve a group of viewers along the last mile (think of a family or a group of friends watching Super Bowl in their HMDs). This would end up quickly choking the entire network. In this paper, we present a scheme to optimize the network bandwidth using motion-prediction-based multicast to serve concurrent viewers. Based on empirical evaluation of more than 150 viewers watching our pool of sixteen 360-degree videos, we observe that most viewers follow similar motion patterns when watching the same video. We present a data- driven scheme for temporal prediction of viewer motion from previous states, and hence optimize the multicast bandwidth consumption by sending only the portion likely to be watched by a group of viewers. Our evaluations with real viewer motion traces show a bandwidth saving of over 50%, compared to full frame video multicast, and significant bandwidth reduction compared to unicast.

Driven by the desire for a better user experience and enabled by improved data storage and processing, much of the recent work has studied user experience prediction in cellular networks. In this paper, moving beyond the prediction-only approach, we propose a data-driven resource allocation framework that uses data-generated prediction models to explicitly guide resource allocation for user experience improvement. In a closed-loop fashion, it further leverages and verifies the causal relation that often exists between certain feature values (e.g., bandwidth) and user experience in computer networks. As a case study, we consider how to reduce the number of user complaints in cellular networks. Our approach consists of three components: we train a logistic regression classifier to predict user experience, utilize the trained likelihood as the objective function to allocate network resource, and then evaluate user experience with allocated resource to (in)validate and adjust the original model. We design a DualHet algorithm to tackle the problem of multi-dimensional resource optimization with heterogeneous users. Numerical simulations based on both synthetic and real network data sets demonstrate the effectiveness of the proposed algorithms. In particular, the simulations based on real data demonstrate up to $2\times $ performance improvement compared with the baseline algorithm.

Enabled by the rapid development of virtual reality hardware and software, 360-degree video content has proliferated. From the network perspective, 360-degree video transmission imposes significant challenges because it consumes 4 6χ the bandwidth of a regular video with the same resolution. To address these challenges, in this paper, we propose a motion-prediction-based transmission mechanism that matches network video transmission to viewer needs. Ideally, if viewer motion is perfectly known in advance, we could reduce bandwidth consumption by 80%. Practically, however, to guarantee the quality of viewing experience, we have to address the random nature of viewer motion. Based on our experimental study of viewer motion (comprising 16 video clips and over 150 subjects), we found the viewer motion can be well predicted in 100~500ms. We propose a machine learning mechanism that predicts not only viewer motion but also prediction deviation itself. The latter is important because it provides valuable input on the amount of redundancy to be transmitted. Based on such predictions, we propose a targeted transmission mechanism that minimizes overall bandwidth consumption while providing probabilistic performance guarantees. Real-data-based evaluations show that the proposed scheme significantly reduces bandwidth consumption while minimizing performance degradation, typically a 45% bandwidth reduction with less than 0.1% failure ratio.

360-degree video transmission consumes 4∼6× the bandwidth of a regular video, and thus imposes significant challenges to networks. To address this challenge, in this paper, we propose a motion-prediction-based transmission mechanism that matches network video transmission to viewer needs. Ideally, if viewer motion is perfectly known in advance, we could reduce bandwidth consumption by 80%. Practically, however, we have to address the random nature of viewer motion, in order to guarantee the quality of the viewing experience. Based on our experimental study of viewer motion (comprising 16 video clips and over 150 subjects), we propose a machine learning mechanism that predicts viewer motion. Based on such predictions, we propose a partial-content-transmission mechanism that reduces the overall bandwidth consumption while providing probabilistic performance guarantees. Real-trace-based evaluations show that the proposed scheme significantly reduces bandwidth consumption with negligible performance degradation. For example, given a failure ratio of 0.1%, we can reduce bandwidth consumption by more than 40%.

Machine learning methods have been widely used in modeling and predicting network user experience. In this paper, moving beyond user experience prediction, we propose a closed-loop approach that uses data-generated prediction models to explicitly guide resource allocation for user experience improvement. The closed-loop approach leverages and verifies the causal relation that often exists between certain feature values (e.g., bandwidth) and user experience in computer networks. The approach consists of three components: we train a neural network classifier to predict user experience, utilize the trained neural network classifier as the objective function to allocate network resource, and then evaluate user experience with allocated resource to (in)validate and adjust the original model. Specifically, we propose a dual decomposition algorithm to solve the neural network-based resource optimization problem, which is complex and non-convex. We further develop an iterative mechanism for classifier optimization. Numerical results show that the dual algorithm reduces the expected number of unsatisfied users by up to 2x compared with the baseline, and the optimized classifier further improves the performance by 50%.

In cellular networks, the coverage of base stations (BSs) belonging to different operators often overlaps. As a result, when the traffic load is lower than the peak volume, there are opportunities to turn off a subset of BSs to save power, potentially from different operators, leaving their users to be served by other BSs. Because in this case the active BSs can be shared among different operators, it is rational to assume that operators are self-interested and hold their own private information, such as their own traffic loads. In this paper, we consider the problem of how to motivate operators to cooperate and reveal their private information such that the overall utility can be maximized, which is also called social efficiency in mechanism design. A new BS utility model that depends on the BS's energy consumption is proposed. Based on this, a game theoretic mechanism with money transfer between operators is designed, which has been proved to be incentive compatible and budget-balanced. Simulation results under various traffic load distributions show that when the operators have similar traffic load distributions, they would like to participate the cooperation voluntarily.

In this paper, we study how to use the solar radiation model to predict energy arrivals and to allocate energy resource at an energy harvesting base station (BS). First, some primary knowledge about solar radiation is reviewed and summarized. We present two solar energy models for cloudless days and cloudy days, respectively. Then artificial neural network (ANN) is used to predict solar energy arrivals in a short period, which has an improved performance compared with the previous linear model. In the end, the allocation of received energy is considered, and one optimal offline algorithm and four heuristics online algorithms are proposed. We evaluate the performance of the algorithms using Denver's solar radiation data in recent 27 years from National Renewable Energy Laboratory (NERL). Simulation results show our prediction and optimization algorithm achieves nearly optimal performance.

In this paper, we address the problem of providing video-on-demand (VoD) services to numerous clients energy-efficiently. To reduce energy consumption, multiple requests for the same video are batched and served by one single multicast stream. However, this brings additional delay to most clients. Utilizing client pre-caching is an efficient way to eliminate the delay: while the server is batching multiple requests, the clients can play the locally cached prefix of the requested video. The multicast session containing the later part of a video can be delayed till the prefix is played out. Our evaluation demonstrates that with a carefully designed pre-caching scheme, even a small cache (with the size of a video) can reduce 50% energy consumption. Moreover, we determine the optimal client cache allocation scheme to maximize the utilization of client cache and further minimize the energy consumption.