With the rising tide of large language models (LLMs), there has been a growing interest in developing general-purpose instruction-following models, e.g., ChatGPT. To this end, we present LLaMA-Adapter, a lightweight adaption method for efficient instruction tuning of LLaMA. Using 52K self-instruct demonstrations, LLaMA-Adapter only introduces 1.2M learnable parameters upon the frozen LLaMA 7B model, and costs less than one hour for fine-tuning. Specifically, a zero-initialized attention mechanism is proposed. It adopts a learnable zero gating to adaptively inject the instructional cues into LLaMA within self-attention layers, contributing to a stable training process and superior final performance. In this way, LLaMA-Adapter can generate high-quality responses to diverse language instructions, comparable to Alpaca with fully fine-tuned 7B parameters. Besides language commands, by incorporating an image encoder, our approach can be simply extended to a multi-modal LLM for image-conditioned instruction following, which achieves superior multi-modal reasoning capacity on several popular benchmarks (MME, MMBench, LVLM-eHub). Furthermore, we also verify the proposed zero-initialized attention mechanism for fine-tuning other pre-trained models (ViT, RoBERTa, CLIP) on traditional vision and language tasks, demonstrating the effectiveness and generalizability of our approach. Code and models are released at https://github.com/OpenGVLab/LLaMA-Adapter.

Distributed protocols such as 2PC and Paxos lie at the core of many systems in the cloud, but standard implementations do not scale. New scalable distributed protocols are developed through careful analysis and rewrites, but this process is ad hoc and error-prone. This paper presents an approach for scaling any distributed protocol by applying rule-driven rewrites, borrowing from query optimization. Distributed protocol rewrites entail a new burden: reasoning about spatiotemporal correctness. We leverage order-insensitivity and data dependency analysis to systematically identify correct coordination-free scaling opportunities. We apply this analysis to create preconditions and mechanisms for coordination-free decoupling and partitioning, two fundamental vertical and horizontal scaling techniques. Manual rule-driven applications of decoupling and partitioning improve the throughput of 2PC by 5× and Paxos by 3×, and match state-of-the-art throughput in recent work. These results point the way toward automated optimizers for distributed protocols based on correct-by-construction rewrite rules.

Private blockchain as a replicated transactional system shares many commonalities with distributed database. However, the intimacy between private blockchain and deterministic database has never been studied. In essence, private blockchain and deterministic database both ensure replica consistency by determinism. In this paper, we present a comprehensive analysis to uncover the connections between private blockchain and deterministic database. While private blockchains have started to pursue deterministic transaction executions recently, deterministic databases have already studied deterministic concurrency control protocols for almost a decade. This motivates us to propose Harmony, a novel deterministic concurrency control protocol designed for blockchain use. We use Harmony to build a new relational blockchain, namely HarmonyBC, which features low abort rates, hotspot resiliency, and inter-block parallelism, all of which are especially important to disk-oriented blockchain. Empirical results on Smallbank, YCSB, and TPC-C show that HarmonyBC offers 2.0x to 3.5x throughput better than the state-of-the-art private blockchains.

The impressive accuracy of deep neural networks (DNNs) has created great demands on practical analytics over video data. Although efficient and accurate, the latest video analytic systems have not supported analytics beyond selection and aggregation queries. In data analytics, Top-K is a very important analytical operation that enables analysts to focus on the most important entities. In this demonstration, we present Everest, the first system that supports efficient and accurate Top-K video analytics. Everest ranks and identifies the most interesting frames/clips from videos with probabilistic guarantees. Furthermore, it supports user-defined functions to rank frames/clips based on different semantics using different deep vision models. Everest leverages techniques from computer vision, uncertain databases, and Top-K query processing to return results quickly.

Recently, numerous promising results have shown that updatable learned indexes can perform better than traditional indexes with much lower memory space consumption. But it is unknown how these learned indexes compare against each other and against the traditional ones under realistic workloads with changing data distributions and concurrency levels. This makes practitioners still wary about how these new indexes would actually behave in practice. To fill this gap, this paper conducts the first comprehensive evaluation on updatable learned indexes. Our evaluation uses ten real datasets and various workloads to challenge learned indexes in three aspects: performance, memory space efficiency and robustness. Based on the results, we give a series of takeaways that can guide the future development and deployment of learned indexes.

The impressive accuracy of deep neural networks (DNNs) has created great demands on practical analytics over video data. Although efficient and accurate, the latest video analytic systems have not supported analytics beyond selection and aggregation queries. In data analytics, Top-K is a very important analytical operation that enables analysts to focus on the most important entities. In this paper, we present Everest, the first system that supports efficient and accurate Top-K video analytics. Everest ranks and identifies the most interesting frames/moments from videos with probabilistic guarantees. Everest is a system built with a careful synthesis of deep computer vision models, uncertain data management, and Top-K query processing. Evaluations on real-world videos and the latest Visual Road benchmark show that Everest achieves between 14.3x to 20.6x higher efficiency than baseline approaches with high result accuracy.

Recent years, many applications have been driven advances by the use of Machine Learning (ML). Nowadays, it is common to see industrial-strength machine learning jobs that involve millions of model parameters, terabytes of training data, and weeks of training. Good efficiency, i.e., fast completion time of running a specific ML training job, therefore, is a key feature of a successful ML system. While the completion time of a long-running ML job is determined by the time required to reach model convergence, that is also largely influenced by the values of various system settings. In this paper, we contribute techniques towards building self-tuning parameter servers. Parameter Server (PS) is a popular system architecture for large-scale machine learning systems; and by self-tuning we mean while a long-running ML job is iteratively training the expert-suggested model, the system is also iteratively learning which system setting is more efficient for that job and applies it online. Our techniques are general enough to various PS-style ML systems. Experiments on TensorFlow show that our techniques can reduce the completion times of a variety of long-running TensorFlow jobs from 1.4× to 18×.

In this paper, we investigate the issue of knowledge distillation for training compact semantic segmentation networks by making use of cumbersome networks. We start from the straightforward scheme, pixel-wise distillation, which applies the distillation scheme originally introduced for image classification and performs knowledge distillation for each pixel separately. We further propose to distill the structured knowledge from cumbersome networks into compact networks, which is motivated by the fact that semantic segmentation is a structured prediction problem. We study two such structured distillation schemes: (i) pair-wise distillation that distills the pairwise similarities, and (ii) holistic distillation that uses adversarial training to distill holistic knowledge. The effectiveness of our knowledge distillation approaches is demonstrated by extensive experiments on three scene parsing datasets: Cityscapes, Camvid and ADE20K.

The closest interval join problem is to find all the closest intervals between two interval sets R and S. Applications of closest interval join include bioinformatics and other data science. Interval data can be very large and continue to increase in size due to the advancement of data acquisition technology. In this paper, we present efficient MapReduce algorithms to compute closest interval join. Experiments based on both real and synthetic interval data demonstrated that our algorithms are efficient.

SNR enhancement of a 6-band WCDMA/ HSDPA+ directconversion transceiver supporting 21 Mbps High Speed Downlink Packet Access Evolved (HSDPA+) in a single CMOS die is evaluated in this paper. The paper mainly focuses on enhancing SNR performance of a WCDMA/HSDPA+ receiver by minimizing the error vector magnitude (EVM) with the digital compensations of the amplitude and group delay variations of the analog channel selection filter, and bandwidth optimization in the cases of the absence and presence of the adjacent channel interferers (ACIs). The measurement results show that the receiver achieves RX EVM below 3% and 4%, respectively, for WCDMA QPSK and HSDPA+ 64-QAM signals across a very wide input signal power range in all bands, and negligible SNR degradation in the presence of the ACIs.

Securing the routing of message in mobile ad hoc networks (MANETs) is still a challenging issue. This paper proposes an enhanced trust-based multipath Dynamic Source Routing (DSR) protocol (so-called ETB-MDSR) to securely transmit messages in MANETs. Our method consists in a combination of soft-encryption, novel trust management strategy, and multipath DSR routing. Simulation results are presented to validate our proposal, showing that our ETB-MDSR scheme outperforms a recently proposed Trust-Based Multipath DSR message scheme (TB-MDSR), in terms of route selection time.

Sports video analysis has attracted great attention in recent years. In the past decade, numerous sports video indexing approaches have been proposed at different semantic levels. In this paper, an individual level sports video indexing (ILSVI) scheme is proposed. The individual level refers to the indexing of a sports video on a player basis, i.e. to recognize each player in a multi-player game. Since the jersey number is always "worn'' by a player as the player's identity in a game, it is feasible to recognize jersey numbers for individual level indexing in sports videos. To solve the jersey number recognition problem, a principal-axis based contour descriptor is proposed. Compared to the state-of-the-art approaches, the proposed descriptor can achieve higher recognition rate and only consume much less computation power. In addition, we developed an interactive system to realize the individual level sports video indexing (ILSVI). This interactive system includes a player detection and a jersey number detection sub-systems. The interactive system can help complete the individual level sports video indexing task. We shall use basketball game videos as the basis to develop real-world systems.

This paper presents a novel game-like advertising system called GameSense, which is driven by the compelling contents of online images. Given a Web page which typically contains images, GameSense is able to select suitable images to create online in-image games for advertising. The contextually relevant ads (i.e., product logos) are embedded at appropriate positions within the online games. The ads are selected based on not only textual relevance but also visual content similarity. The game is able to provide viewers rich experience and thus promote the embedded ads to provide more effective advertising.