Li Jiang

Wenyue Hua, Ollie Liu, Lingyao Li et al.

This paper investigates the rationality of large language models (LLMs) in strategic decision-making contexts, specifically within the framework of game theory. We evaluate several state-of-the-art LLMs across a spectrum of complete-information and incomplete-information games. Our findings reveal that LLMs frequently deviate from rational strategies, particularly as the complexity of the game increases with larger payoff matrices or deeper sequential trees. To address these limitations, we design multiple game-theoretic workflows that guide the reasoning and decision-making processes of LLMs. These workflows aim to enhance the models' ability to compute Nash Equilibria and make rational choices, even under conditions of uncertainty and incomplete information. Experimental results demonstrate that the adoption of these workflows significantly improves the rationality and robustness of LLMs in game-theoretic tasks. Specifically, with the workflow, LLMs exhibit marked improvements in identifying optimal strategies, achieving near-optimal allocations in negotiation scenarios, and reducing susceptibility to exploitation during negotiations. Furthermore, we explore the meta-strategic considerations of whether it is rational for agents to adopt such workflows, recognizing that the decision to use or forgo the workflow constitutes a game-theoretic issue in itself. Our research contributes to a deeper understanding of LLMs' decision-making capabilities in strategic contexts and provides insights into enhancing their rationality through structured workflows. The findings have implications for the development of more robust and strategically sound AI agents capable of navigating complex interactive environments. Code and data supporting this study are available at \url{https://github.com/Wenyueh/game_theory}.

Fangxin Liu, Zongwu Wang, JinHong Xia et al.

The rapid advancement of large language models (LLMs) has exacerbated the memory bottleneck due to the widening gap between model parameter scaling and hardware capabilities. While post-training quantization techniques effectively reduce memory overhead, existing methods predominantly rely on static quantization strategies, which struggle to adapt to dynamic workloads. To address this, we propose FlexQuant, a dynamic precision-switching framework that optimizes the trade-off between inference speed and accuracy. Leveraging model perplexity entropy and Kullback-Leibler divergence, FlexQuant enables fine-grained, layer-wise mixed-precision quantization and dynamically adjusts bit-widths during each token generation. FlexQuant provides a comprehensive analysis of quantization strategies, introduces a precision requirement model for optimal switching, and implements efficient fine-grained precision management. Evaluations demonstrate that FlexQuant achieves a 1.3x end-to-end speedup across diverse language tasks with negligible accuracy loss introduced. This framework offers a flexible and adaptive solution for efficient LLM deployment. Code is released at https://github.com/ZongwuWang/FlexQuant.git.

Yilin Liu, Yunkui Pang, Jiang Li et al.

Untrained networks inspired by deep image priors have shown promising capabilities in recovering high-quality images from noisy or partial measurements without requiring training sets. Their success is widely attributed to implicit regularization due to the spectral bias of suitable network architectures. However, the application of such network-based priors often entails superfluous architectural decisions, risks of overfitting, and lengthy optimization processes, all of which hinder their practicality. To address these challenges, we propose efficient architecture-agnostic techniques to directly modulate the spectral bias of network priors: 1) bandwidth-constrained input, 2) bandwidth-controllable upsamplers, and 3) Lipschitz-regularized convolutional layers. We show that, with just a few lines of code, we can reduce overfitting in underperforming architectures and close performance gaps with high-performing counterparts, minimizing the need for extensive architecture tuning. This makes it possible to employ a more compact model to achieve performance similar or superior to larger models while reducing runtime. Demonstrated on inpainting-like MRI reconstruction task, our results signify for the first time that architectural biases, overfitting, and runtime issues of untrained network priors can be simultaneously addressed without architectural modifications. Our code is publicly available.

Yu Gong, Zhihan Xu, Zhezhi He et al.

Accelerating the neural network inference by FPGA has emerged as a popular option, since the reconfigurability and high performance computing capability of FPGA intrinsically satisfies the computation demand of the fast-evolving neural algorithms. However, the popular neural accelerators on FPGA (e.g., Xilinx DPU) mainly utilize the DSP resources for constructing their processing units, while the rich LUT resources are not well exploited. Via the software-hardware co-design approach, in this work, we develop an FPGA-based heterogeneous computing system for neural network acceleration. From the hardware perspective, the proposed accelerator consists of DSP- and LUT-based GEneral Matrix-Multiplication (GEMM) computing cores, which forms the entire computing system in a heterogeneous fashion. The DSP- and LUT-based GEMM cores are computed w.r.t a unified Instruction Set Architecture (ISA) and unified buffers. Along the data flow of the neural network inference path, the computation of the convolution/fully-connected layer is split into two portions, handled by the DSP- and LUT-based GEMM cores asynchronously. From the software perspective, we mathematically and systematically model the latency and resource utilization of the proposed heterogeneous accelerator, regarding varying system design configurations. Through leveraging the reinforcement learning technique, we construct a framework to achieve end-to-end selection and optimization of the design specification of target heterogeneous accelerator, including workload split strategy, mixed-precision quantization scheme, and resource allocation of DSP- and LUT-core. In virtue of the proposed design framework and heterogeneous computing system, our design outperforms the state-of-the-art Mix&Match design with latency reduced by 1.12-1.32x with higher inference accuracy. The N3H-core is open-sourced at: https://github.com/elliothe/N3H_Core.

Xiaosong Jia, Shaoshuai Shi, Zijun Chen et al.

As an essential task in autonomous driving (AD), motion prediction aims to predict the future states of surround objects for navigation. One natural solution is to estimate the position of other agents in a step-by-step manner where each predicted time-step is conditioned on both observed time-steps and previously predicted time-steps, i.e., autoregressive prediction. Pioneering works like SocialLSTM and MFP design their decoders based on this intuition. However, almost all state-of-the-art works assume that all predicted time-steps are independent conditioned on observed time-steps, where they use a single linear layer to generate positions of all time-steps simultaneously. They dominate most motion prediction leaderboards due to the simplicity of training MLPs compared to autoregressive networks. In this paper, we introduce the GPT style next token prediction into motion forecasting. In this way, the input and output could be represented in a unified space and thus the autoregressive prediction becomes more feasible. However, different from language data which is composed of homogeneous units -words, the elements in the driving scene could have complex spatial-temporal and semantic relations. To this end, we propose to adopt three factorized attention modules with different neighbors for information aggregation and different position encoding styles to capture their relations, e.g., encoding the transformation between coordinate systems for spatial relativity while adopting RoPE for temporal relativity. Empirically, by equipping with the aforementioned tailored designs, the proposed method achieves state-of-the-art performance in the Waymo Open Motion and Waymo Interaction datasets. Notably, AMP outperforms other recent autoregressive motion prediction methods: MotionLM and StateTransformer, which demonstrates the effectiveness of the proposed designs.

Jiang Li, Yuan-Ting Li

Identifying protein-protein interactions (PPI) is crucial for gaining in-depth insights into numerous biological processes within cells and holds significant guiding value in areas such as drug development and disease treatment. Currently, most PPI prediction methods focus primarily on the study of protein sequences, neglecting the critical role of the internal structure of proteins. This paper proposes a novel PPI prediction method named MgslaPPI, which utilizes graph attention to mine protein structural information and enhances the expressive power of the protein encoder through multitask learning strategy. Specifically, we decompose the end-to-end PPI prediction process into two stages: amino acid residue reconstruction (A2RR) and protein interaction prediction (PIP). In the A2RR stage, we employ a graph attention-based residue reconstruction method to explore the internal relationships and features of proteins. In the PIP stage, in addition to the basic interaction prediction task, we introduce two auxiliary tasks, i.e., protein feature reconstruction (PFR) and masked interaction prediction (MIP). The PFR task aims to reconstruct the representation of proteins in the PIP stage, while the MIP task uses partially masked protein features for PPI prediction, with both working in concert to prompt MgslaPPI to capture more useful information. Experimental results demonstrate that MgslaPPI significantly outperforms existing state-of-the-art methods under various data partitioning schemes.

Tian Lan, Xiangdong Su, Xu Liu et al.

As large language models (LLMs) are increasingly applied to various NLP tasks, their inherent biases are gradually disclosed. Therefore, measuring biases in LLMs is crucial to mitigate its ethical risks. However, most existing bias evaluation datasets focus on English and North American culture, and their bias categories are not fully applicable to other cultures. The datasets grounded in the Chinese language and culture are scarce. More importantly, these datasets usually only support single evaluation tasks and cannot evaluate the bias from multiple aspects in LLMs. To address these issues, we present a Multi-task Chinese Bias Evaluation Benchmark (McBE) that includes 4,077 bias evaluation instances, covering 12 single bias categories, 82 subcategories and introducing 5 evaluation tasks, providing extensive category coverage, content diversity, and measuring comprehensiveness. Additionally, we evaluate several popular LLMs from different series and with parameter sizes. In general, all these LLMs demonstrated varying degrees of bias. We conduct an in-depth analysis of results, offering novel insights into bias in LLMs.

Wenjie Du, Li Jiang, Keda Tao et al.

Reasoning large language models exhibit complex reasoning behaviors through the extended chain-of-thought generation, creating unprecedented Key-Value (KV) cache overhead during the decoding phase. Existing KV cache compression methods underperform on reasoning models: token-dropping methods break reasoning integrity by discarding critical information, while head-reallocating methods mistakenly compress reasoning-critical heads since they are designed for retrieval tasks, resulting in significant performance degradation as compression rates increase. We hypothesize that KV heads exhibit functional heterogeneity in reasoning models-some heads are critical for chain-of-thought consistency while others are compressible. To validate and exploit this insight, we propose RLKV, a novel reasoning-critical head identification framework, which uses reinforcement learning to directly optimize the relationship between each head's cache usage and reasoning quality. As RLKV produces rewards from actual generated samples during training, it naturally identifies heads relevant to reasoning behaviors. We then allocate full KV cache to these heads while applying compressed constant KV cache to others for efficient inference. Our experiments reveal that only a small fraction of attention heads is essential for reasoning, enabling our KV compression approach to outperform baseline methods while achieving 20-50% cache reduction with near lossless performance compared to uncompressed results.

Weidong Cao, Yilong Zhao, Adith Boloor et al.

Processing-in-memory (PIM) architectures have demonstrated great potential in accelerating numerous deep learning tasks. Particularly, resistive random-access memory (RRAM) devices provide a promising hardware substrate to build PIM accelerators due to their abilities to realize efficient in-situ vector-matrix multiplications (VMMs). However, existing PIM accelerators suffer from frequent and energy-intensive analog-to-digital (A/D) conversions, severely limiting their performance. This paper presents a new PIM architecture to efficiently accelerate deep learning tasks by minimizing the required A/D conversions with analog accumulation and neural approximated peripheral circuits. We first characterize the different dataflows employed by existing PIM accelerators, based on which a new dataflow is proposed to remarkably reduce the required A/D conversions for VMMs by extending shift and add (S+A) operations into the analog domain before the final quantizations. We then leverage a neural approximation method to design both analog accumulation circuits (S+A) and quantization circuits (ADCs) with RRAM crossbar arrays in a highly-efficient manner. Finally, we apply them to build an RRAM-based PIM accelerator (i.e., \textbf{Neural-PIM}) upon the proposed analog dataflow and evaluate its system-level performance. Evaluations on different benchmarks demonstrate that Neural-PIM can improve energy efficiency by 5.36x (1.73x) and speed up throughput by 3.43x (1.59x) without losing accuracy, compared to the state-of-the-art RRAM-based PIM accelerators, i.e., ISAAC (CASCADE).

Min Li, Yu Li, Ye Tian et al.

This paper presents AppealNet, a novel edge/cloud collaborative architecture that runs deep learning (DL) tasks more efficiently than state-of-the-art solutions. For a given input, AppealNet accurately predicts on-the-fly whether it can be successfully processed by the DL model deployed on the resource-constrained edge device, and if not, appeals to the more powerful DL model deployed at the cloud. This is achieved by employing a two-head neural network architecture that explicitly takes inference difficulty into consideration and optimizes the tradeoff between accuracy and computation/communication cost of the edge/cloud collaborative architecture. Experimental results on several image classification datasets show up to more than 40% energy savings compared to existing techniques without sacrificing accuracy.

Liu Fangxin, Zhao Wenbo, Wang Yanzhi et al.

Quantization is essential to simplify DNN inference in edge applications. Existing uniform and non-uniform quantization methods, however, exhibit an inherent conflict between the representing range and representing resolution, and thereby result in either underutilized bit-width or significant accuracy drop. Moreover, these methods encounter three drawbacks: i) the absence of a quantitative metric for in-depth analysis of the source of the quantization errors; ii) the limited focus on the image classification tasks based on CNNs; iii) the unawareness of the real hardware and energy consumption reduced by lowering the bit-width. In this paper, we first define two quantitative metrics, i.e., the Clipping Error and rounding error, to analyze the quantization error distribution. We observe that the boundary- and rounding- errors vary significantly across layers, models and tasks. Consequently, we propose a novel quantization method to quantize the weight and activation. The key idea is to Approximate the Uniform quantization by Adaptively Superposing multiple Non-uniform quantized values, namely AUSN. AUSN is consist of a decoder-free coding scheme that efficiently exploits the bit-width to its extreme, a superposition quantization algorithm that can adapt the coding scheme to different DNN layers, models and tasks without extra hardware design effort, and a rounding scheme that can eliminate the well-known bit-width overflow and re-quantization issues. Theoretical analysis~(see Appendix A) and accuracy evaluation on various DNN models of different tasks show the effectiveness and generalization of AUSN. The synthesis~(see Appendix B) results on FPGA show $2\times$ reduction of the energy consumption, and $2\times$ to $4\times$ reduction of the hardware resource.

Qi Yan, Li Jiang, Solmaz Kia

This paper studies the measurement scheduling problem for a group of N mobile robots moving on a flat surface that are preforming cooperative localization (CL). We consider a scenario in which due to the limited on-board resources such as battery life and communication bandwidth only a given number of relative measurements per robot are allowed at observation and update stage. Optimal selection of which teammates a robot should take a relative measurement from such that the updated joint localization uncertainty of the team is minimized is an NP-hard problem. In this paper, we propose a suboptimal greedy approach that allows each robot to choose its landmark robots locally in polynomial time. Our method, unlike the known results in the literature, does not assume full-observability of CL algorithm. Moreover, it does not require inter-robot communication at scheduling stage. That is, there is no need for the robots to collaborate to carry out the landmark robot selections. We discuss the application of our method in the context of an state-of-the-art decentralized CL algorithm and demonstrate its effectiveness through numerical simulations. Even though our solution does not come with rigorous performance guarantees, its low computational cost along with no communication requirement makes it an appealing solution for operatins with resource constrained robots.

Geng Yuan, Xiaolong Ma, Caiwen Ding et al.

The high computation and memory storage of large deep neural networks (DNNs) models pose intensive challenges to the conventional Von-Neumann architecture, incurring substantial data movements in the memory hierarchy. The memristor crossbar array has emerged as a promising solution to mitigate the challenges and enable low-power acceleration of DNNs. Memristor-based weight pruning and weight quantization have been seperately investigated and proven effectiveness in reducing area and power consumption compared to the original DNN model. However, there has been no systematic investigation of memristor-based neuromorphic computing (NC) systems considering both weight pruning and weight quantization. In this paper, we propose an unified and systematic memristor-based framework considering both structured weight pruning and weight quantization by incorporating alternating direction method of multipliers (ADMM) into DNNs training. We consider hardware constraints such as crossbar blocks pruning, conductance range, and mismatch between weight value and real devices, to achieve high accuracy and low power and small area footprint. Our framework is mainly integrated by three steps, i.e., memristor-based ADMM regularized optimization, masked mapping and retraining. Experimental results show that our proposed framework achieves 29.81X (20.88X) weight compression ratio, with 98.38% (96.96%) and 98.29% (97.47%) power and area reduction on VGG-16 (ResNet-18) network where only have 0.5% (0.76%) accuracy loss, compared to the original DNN models. We share our models at link http://bit.ly/2Jp5LHJ.

Hongyu Chen, Li Jiang

Ubiquitous anomalies endanger the security of our system constantly. They may bring irreversible damages to the system and cause leakage of privacy. Thus, it is of vital importance to promptly detect these anomalies. Traditional supervised methods such as Decision Trees and Support Vector Machine (SVM) are used to classify normality and abnormality. However, in some case the abnormal status are largely rarer than normal status, which leads to decision bias of these methods. Generative adversarial network (GAN) has been proposed to handle the case. With its strong generative ability, it only needs to learn the distribution of normal status, and identify the abnormal status through the gap between it and the learned distribution. Nevertheless, existing GAN-based models are not suitable to process data with discrete values, leading to immense degradation of detection performance. To cope with the discrete features, in this paper, we propose an efficient GAN-based model with specifically-designed loss function. Experiment results show that our model outperforms state-of-the-art models on discrete dataset and remarkably reduce the overhead.

Haiyue Song, Chengwen Xu, Qiang Xu et al.

Neural approximate computing gains enormous energy-efficiency at the cost of tolerable quality-loss. A neural approximator can map the input data to output while a classifier determines whether the input data are safe to approximate with quality guarantee. However, existing works cannot maximize the invocation of the approximator, resulting in limited speedup and energy saving. By exploring the mapping space of those target functions, in this paper, we observe a nonuniform distribution of the approximation error incurred by the same approximator. We thus propose a novel approximate computing architecture with a Multiclass-Classifier and Multiple Approximators (MCMA). These approximators have identical network topologies and thus can share the same hardware resource in a neural processing unit(NPU) clip. In the runtime, MCMA can swap in the invoked approximator by merely shipping the synapse weights from the on-chip memory to the buffers near MAC within a cycle. We also propose efficient co-training methods for such MCMA architecture. Experimental results show a more substantial invocation of MCMA as well as the gain of energy-efficiency.

Zhenghao Peng, Xuyang Chen, Chengwen Xu et al.

Neural network based approximate computing is a universal architecture promising to gain tremendous energy-efficiency for many error resilient applications. To guarantee the approximation quality, existing works deploy two neural networks (NNs), e.g., an approximator and a predictor. The approximator provides the approximate results, while the predictor predicts whether the input data is safe to approximate with the given quality requirement. However, it is non-trivial and time-consuming to make these two neural network coordinate---they have different optimization objectives---by training them separately. This paper proposes a novel neural network structure---AXNet---to fuse two NNs to a holistic end-to-end trainable NN. Leveraging the philosophy of multi-task learning, AXNet can tremendously improve the invocation (proportion of safe-to-approximate samples) and reduce the approximation error. The training effort also decrease significantly. Experiment results show 50.7% more invocation and substantial cuts of training time when compared to existing neural network based approximate computing framework.

Zhuoran Song, Ru Wang, Dongyu Ru et al.

The training phases of Deep neural network~(DNN) consumes enormous processing time and energy. Compression techniques utilizing the sparsity of DNNs can effectively accelerate the inference phase of DNNs. However, it can be hardly used in the training phase because the training phase involves dense matrix-multiplication using General Purpose Computation on Graphics Processors (GPGPU), which endorse regular and structural data layout. In this paper, we propose the Approximate Random Dropout that replaces the conventional random dropout of neurons and synapses with a regular and predefined patterns to eliminate the unnecessary computation and data access. To compensate the potential performance loss we develop a SGD-based Search Algorithm to produce the distribution of dropout patterns. We prove our approach is statistically equivalent to the previous dropout method. Experiments results on MLP and LSTM using well-known benchmarks show that the proposed Approximate Random Dropout can reduce the training time by $20\%$-$77\%$ ($19\%$-$60\%$) when dropout rate is $0.3$-$0.7$ on MLP (LSTM) with marginal accuracy drop.