Large Language Models (LLMs) have achieved remarkable success in serving end-users with human-like intelligence. However, LLMs demand high computational resources, making it challenging to deploy them to satisfy various performance objectives, such as meeting the resource constraints on edge devices close to end-users or achieving high accuracy with ample resources. In this paper, we introduce CE-CoLLM, a novel cloud-edge collaboration framework that supports efficient and adaptive LLM inference for end-users at the edge with two modes, (1) low-latency edge standalone inference and (2) highly accurate cloud-edge collaborative inference. First, we show that the inherent high communication costs for transmitting LLM contextual information between the edge and cloud dominate the overall latency, making it inefficient and costly to deploy LLMs using cloud-edge collaboration. Second, we propose several critical techniques to address this challenge, including early-exit mechanism, cloud context manager, and quantization in cloud-edge collaboration to enable not only low-latency standalone edge inference but also efficient and adaptive cloud-edge collaborative inference for LLMs. Third, we perform comprehensive experimental analysis, which demonstrates that CE-CoLLM significantly reduces inference time by up to 13.81% and cloud computation costs by up to 84.55% compared to the popular cloud-based LLM deployment, while maintaining comparable model accuracy. The proposed approach effectively shifts the computational load to the edge, reduces the communication overhead, scales efficiently with multiple edge clients, and provides reliable LLM deployment using cloud-edge collaboration.
相關內容
Large Language Models (LLMs) have demonstrated remarkable proficiency in generating code. However, the misuse of LLM-generated (synthetic) code has raised concerns in both educational and industrial contexts, underscoring the urgent need for synthetic code detectors. Existing methods for detecting synthetic content are primarily designed for general text and struggle with code due to the unique grammatical structure of programming languages and the presence of numerous ''low-entropy'' tokens. Building on this, our work proposes a novel zero-shot synthetic code detector based on the similarity between the original code and its LLM-rewritten variants. Our method is based on the observation that differences between LLM-rewritten and original code tend to be smaller when the original code is synthetic. We utilize self-supervised contrastive learning to train a code similarity model and evaluate our approach on two synthetic code detection benchmarks. Our results demonstrate a significant improvement over existing SOTA synthetic content detectors, with AUROC scores increasing by 20.5% on the APPS benchmark and 29.1% on the MBPP benchmark.
Large Language Models (LLMs) have demonstrated remarkable performance across various tasks. A promising but largely under-explored area is their potential to facilitate human coordination with many agents. Such capabilities would be useful in domains including disaster response, urban planning, and real-time strategy scenarios. In this work, we introduce (1) a real-time strategy game benchmark designed to evaluate these abilities and (2) a novel framework we term HIVE. HIVE empowers a single human to coordinate swarms of up to 2,000 agents using natural language dialog with an LLM. We present promising results on this multi-agent benchmark, with our hybrid approach solving tasks such as coordinating agent movements, exploiting unit weaknesses, leveraging human annotations, and understanding terrain and strategic points. However, our findings also highlight critical limitations of current models, including difficulties in processing spatial visual information and challenges in formulating long-term strategic plans. This work sheds light on the potential and limitations of LLMs in human-swarm coordination, paving the way for future research in this area. The HIVE project page, which includes videos of the system in action, can be found here: hive.syrkis.com.
As world knowledge advances and new task schemas emerge, Continual Learning (CL) becomes essential for keeping Large Language Models (LLMs) current and addressing their shortcomings. This process typically involves continual instruction tuning (CIT) and continual pre-training (CPT) to enable these models to adapt to novel tasks and acquire critical knowledge. However, collecting sufficient CPT data and efficiently bridging knowledge gaps remain significant challenges. Inspired by the 'summarizing mistakes' strategy, we propose the Continue Evolving from Mistakes (CEM) method, a data-efficient approach aiming to collect CPT data and continually improve LLMs' performance through iterative evaluation and supplementation with mistake-relevant knowledge. To further optimize data usage and mitigate forgetting, we introduce a novel training paradigm that combines CIT and CPT. Experiments show that CEM substantially enhances multiple models' performance on both in-domain and out-of-domain QA tasks, achieving gains of up to 29.63%. Code and datasets are available on //anonymous.4open.science/r/cem-BB25.
As the Internet of Things (IoT) industry advances, the imperative to secure IoT devices has become increasingly critical. Current practices in both industry and academia advocate for the enhancement of device security through key installation. However, it has been observed that, in practice, IoT vendors frequently assign shared keys to batches of devices. This practice can expose devices to risks, such as data theft by attackers or large-scale Distributed Denial of Service (DDoS) attacks. To address this issue, our intuition is to assign a unique key to each device. Unfortunately, this strategy proves to be highly complex within the IoT context, as existing keys are typically hardcoded into the firmware, necessitating the creation of bespoke firmware for each device. Furthermore, correct pairing of device keys with their respective devices is crucial. Errors in this pairing process would incur substantial human and temporal resources to rectify and require extensive communication between IoT vendors, device manufacturers, and cloud platforms, leading to significant communication overhead. To overcome these challenges, we propose the OTA-Key scheme. This approach fundamentally decouples device keys from the firmware features stored in flash memory, utilizing an intermediary server to allocate unique device keys in two distinct stages and update keys. We conducted a formal security verification of our scheme using ProVerif and assessed its performance through a series of evaluations. The results demonstrate that our scheme is secure and effectively manages the large-scale distribution and updating of unique device keys. Additionally, it achieves significantly lower update times and data transfer volumes compared to other schemes.
Graph Neural Networks (GNNs) have become invaluable intellectual property in graph-based machine learning. However, their vulnerability to model stealing attacks when deployed within Machine Learning as a Service (MLaaS) necessitates robust Ownership Demonstration (OD) techniques. Watermarking is a promising OD framework for Deep Neural Networks, but existing methods fail to generalize to GNNs due to the non-Euclidean nature of graph data. Previous works on GNN watermarking have primarily focused on node and graph classification, overlooking Link Prediction (LP). In this paper, we propose GENIE (watermarking Graph nEural Networks for lInk prEdiction), the first-ever scheme to watermark GNNs for LP. GENIE creates a novel backdoor for both node-representation and subgraph-based LP methods, utilizing a unique trigger set and a secret watermark vector. Our OD scheme is equipped with Dynamic Watermark Thresholding (DWT), ensuring high verification probability (>99.99%) while addressing practical issues in existing watermarking schemes. We extensively evaluate GENIE across 4 model architectures (i.e., SEAL, GCN, GraphSAGE and NeoGNN) and 7 real-world datasets. Furthermore, we validate the robustness of GENIE against 11 state-of-the-art watermark removal techniques and 3 model extraction attacks. We also show GENIE's resilience against ownership piracy attacks. Finally, we discuss a defense strategy to counter adaptive attacks against GENIE.
The introduction of Feature Pyramid Network (FPN) has significantly improved object detection performance. However, substantial challenges remain in detecting tiny objects, as their features occupy only a very small proportion of the feature maps. Although FPN integrates multi-scale features, it does not directly enhance or enrich the features of tiny objects. Furthermore, FPN lacks spatial perception ability. To address these issues, we propose a novel High Frequency and Spatial Perception Feature Pyramid Network (HS-FPN) with two innovative modules. First, we designed a high frequency perception module (HFP) that generates high frequency responses through high pass filters. These high frequency responses are used as mask weights from both spatial and channel perspectives to enrich and highlight the features of tiny objects in the original feature maps. Second, we developed a spatial dependency perception module (SDP) to capture the spatial dependencies that FPN lacks. Our experiments demonstrate that detectors based on HS-FPN exhibit competitive advantages over state-of-the-art models on the AI-TOD dataset for tiny object detection.
Diffusion Probability Models (DPMs) have made impressive advancements in various machine learning domains. However, achieving high-quality synthetic samples typically involves performing a large number of sampling steps, which impedes the possibility of real-time sample synthesis. Traditional accelerated sampling algorithms via knowledge distillation rely on pre-trained model weights and discrete time step scenarios, necessitating additional training sessions to achieve their goals. To address these issues, we propose the Catch-Up Distillation (CUD), which encourages the current moment output of the velocity estimation model ``catch up'' with its previous moment output. Specifically, CUD adjusts the original Ordinary Differential Equation (ODE) training objective to align the current moment output with both the ground truth label and the previous moment output, utilizing Runge-Kutta-based multi-step alignment distillation for precise ODE estimation while preventing asynchronous updates. Furthermore, we investigate the design space for CUDs under continuous time-step scenarios and analyze how to determine the suitable strategies. To demonstrate CUD's effectiveness, we conduct thorough ablation and comparison experiments on CIFAR-10, MNIST, and ImageNet-64. On CIFAR-10, we obtain a FID of 2.80 by sampling in 15 steps under one-session training and the new state-of-the-art FID of 3.37 by sampling in one step with additional training. This latter result necessitated only 620k iterations with a batch size of 128, in contrast to Consistency Distillation, which demanded 2100k iterations with a larger batch size of 256. Our code is released at //anonymous.4open.science/r/Catch-Up-Distillation-E31F.
One way to enhance the reasoning capability of Large Language Models (LLMs) is to conduct Supervised Fine-Tuning (SFT) using Chain-of-Thought (CoT) annotations. This approach does not show sufficiently strong generalization ability, however, because the training only relies on the given CoT data. In math problem-solving, for example, there is usually only one annotated reasoning path for each question in the training data. Intuitively, it would be better for the algorithm to learn from multiple annotated reasoning paths given a question. To address this issue, we propose a simple yet effective approach called Reinforced Fine-Tuning (ReFT) to enhance the generalizability of learning LLMs for reasoning, with math problem-solving as an example. ReFT first warmups the model with SFT, and then employs on-line reinforcement learning, specifically the PPO algorithm in this paper, to further fine-tune the model, where an abundance of reasoning paths are automatically sampled given the question and the rewards are naturally derived from the ground-truth answers. Extensive experiments on GSM8K, MathQA, and SVAMP datasets show that ReFT significantly outperforms SFT, and the performance can be potentially further boosted by combining inference-time strategies such as majority voting and re-ranking. Note that ReFT obtains the improvement by learning from the same training questions as SFT, without relying on extra or augmented training questions. This indicates a superior generalization ability for ReFT.
The Material Point Method (MPM) has become a cornerstone of physics-based simulation, widely used in geomechanics and computer graphics for modeling phenomena such as granular flows, viscoelasticity, fracture mechanics, etc. Despite its versatility, the original MPM suffers from cell-crossing instabilities caused by discontinuities in particle-grid transfer kernels. Existing solutions mitigate these issues by adopting smoother shape functions, but at the cost of increased computational overhead due to larger kernel support. In this paper, we propose a novel $C^2$-continuous compact kernel for MPM that achieves a unique balance between stability and computational efficiency. Our method integrates seamlessly with Affine Particle-In-Cell (APIC) and Moving Least Squares (MLS) MPM, while only doubling the number of grid nodes associated with each particle compared to linear kernels. At its core is an innovative dual-grid framework, which associates particles with grid nodes exclusively within the cells they occupy on two staggered grids, ensuring consistent and stable force computations. To further accelerate performance, we present a GPU-optimized implementation inspired by state-of-the-art massively parallel MPM techniques, achieving an additional $2\times$ speedup in G2P2G transfers over quadratic B-spline MPM. Comprehensive validation through unit tests, comparative studies, and stress tests demonstrates the efficacy of our approach in conserving both linear and angular momentum, handling stiff materials, and scaling efficiently for large-scale simulations. Our results highlight the transformative potential of compact, high-order kernels in advancing MPM's capabilities for stable, high-performance simulations, paving the way for more computationally efficient applications in computer graphics and beyond.
Named entity recognition (NER) in Chinese is essential but difficult because of the lack of natural delimiters. Therefore, Chinese Word Segmentation (CWS) is usually considered as the first step for Chinese NER. However, models based on word-level embeddings and lexicon features often suffer from segmentation errors and out-of-vocabulary (OOV) words. In this paper, we investigate a Convolutional Attention Network called CAN for Chinese NER, which consists of a character-based convolutional neural network (CNN) with local-attention layer and a gated recurrent unit (GRU) with global self-attention layer to capture the information from adjacent characters and sentence contexts. Also, compared to other models, not depending on any external resources like lexicons and employing small size of char embeddings make our model more practical. Extensive experimental results show that our approach outperforms state-of-the-art methods without word embedding and external lexicon resources on different domain datasets including Weibo, MSRA and Chinese Resume NER dataset.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191