arXiv subjects

Zongpeng Li

Publications and source records attributed to Zongpeng Li.

At least 19 recordsLinked to original sources

arXiv2026

A Session Interaction Framework for The Multiple-Unicast Conjecture

The multiple-unicast conjecture asserts that network coding offers no throughput advantage over routing in undirected networks. Its validity is known to imply fundamental lower bounds in computational complexity. We propose a Session Interaction Framework that reduces the conjecture to a central equivalence: the conjecture holds universally if and only if every irreducible core is independent. This result transforms the global feasibility problem into a two-stage process. First, to make the reduction phase tractable, we provide simplified sufficient conditions for session dominance, offering geometric criteria to iteratively simplify complex session sets. Second, for the remaining "irreducible core," we propose a Session Decoupling Theorem, reducing the conjecture's validity for a session set to its independent subsets. Topologically, we prove that sessions separated by high-cost cuts or cut-vertices are guaranteed to be independent. By integrating these reduction and decomposition mechanisms, our framework offers a systematic methodology to verify the conjecture across general network topologies.

cs.IT↗

arXiv2026

On the Multiple-Unicast Conjecture: Beyond Cut Metrics

Network coding allows intermediate nodes to encode received messages before transmission. The multiple-unicast conjecture asserts that coding has no throughput advantage over fractional routing for independent unicast sessions in any undirected network. Despite more than two decades of sustained study, this central open problem remains unresolved. The conjecture is deeply connected to computational complexity: a proof would yield long-sought lower bounds for fundamental problems. To study the conjecture, this paper develops a unified metric framework from the perspective that the basic objects behind the comparison between coding and routing are not cuts alone, but graph metrics. Using this framework, we prove the conjecture for three new classes of undirected networks: (a) networks with at most five terminal locations; (b) planar networks whose terminal locations lie on the boundaries of at most three designated faces, with each session's endpoints on one such face; and (c) networks with arbitrarily many nodes and terminal locations under a structural restriction on session endpoints. We give a new proof that the conjecture holds for networks with at most six coding nodes, without computer-aided search, and show that if the conjecture holds on $Γ_{3,3}$, then it holds whenever no three sessions have six distinct terminal locations.

cs.IT↗

arXiv2026

LoCAtion: Long-time Collaborative Attention Framework for High Dynamic Range Video Reconstruction

Prevailing High Dynamic Range (HDR) video reconstruction methods are fundamentally trapped in a fragile alignment-and-fusion paradigm. While explicit spatial alignment can successfully recover fine details in controlled environments, it becomes a severe bottleneck in unconstrained dynamic scenes. By forcing rigid alignment across unpredictable motions and varying exposures, these methods inevitably translate registration errors into severe ghosting artifacts and temporal flickering. In this paper, we rethink this conventional prerequisite. Recognizing that explicit alignment is inherently vulnerable to real-world complexities, we propose LoCAtion, a Long-time Collaborative Attention framework that reformulates HDR video generation from a fragile spatial warping task into a robust, alignment-free collaborative feature routing problem. Guided by this new formulation, our architecture explicitly decouples the highly entangled reconstruction task. Rather than struggling to rigidly warp neighboring frames, we anchor the scene on a continuous medium-exposure backbone and utilize collaborative attention to dynamically harvest and inject reliable irradiance cues from unaligned exposures. Furthermore, we introduce a learned global sequence solver. By leveraging bidirectional context and long-range temporal modeling, it propagates corrective signals and structural features across the entire sequence, inherently enforcing whole-video coherence and eliminating jitter. Extensive experiments demonstrate that LoCAtion achieves state-of-the-art visual quality and temporal stability, offering a highly competitive balance between accuracy and computational efficiency.

cs.CV↗

arXiv2026

Targeted Bit-Flip Attacks on LLM-Based Agents

Targeted bit-flip attacks (BFAs) exploit hardware faults to manipulate model parameters, posing a significant security threat. While prior work targets single-step inference models (e.g., image classifiers), LLM-based agents with multi-stage pipelines and external tools present new attack surfaces, which remain unexplored. This work introduces Flip-Agent, the first targeted BFA framework for LLM-based agents, manipulating both final outputs and tool invocations. Our experiments show that Flip-Agent significantly outperforms existing targeted BFAs on real-world agent tasks, revealing a critical vulnerability in LLM-based agent systems.

cs.CR↗

arXiv2026

Capturing Stable HDR Videos Using a Dual-Camera System

High Dynamic Range (HDR) video acquisition using the alternating exposure (AE) paradigm has garnered significant attention due to its cost-effectiveness with a single consumer camera. However, despite progress driven by deep neural networks, these methods remain prone to temporal flicker in real-world applications due to inter-frame exposure inconsistencies. To address this challenge while maintaining the cost-effectiveness of the AE paradigm, we propose a novel learning-based HDR video generation solution. Specifically, we propose a dual-stream HDR video generation paradigm that decouples temporal luminance anchoring from exposure-variant detail reconstruction, overcoming the inherent limitations of the AE paradigm. To support this, we design an asynchronous dual-camera system (DCS), which enables independent exposure control across two cameras, eliminating the need for synchronization typically required in traditional multi-camera setups. Furthermore, an exposure-adaptive fusion network (EAFNet) is formulated for the DCS system. EAFNet integrates a pre-alignment subnetwork that aligns features across varying exposures, ensuring robust feature extraction for subsequent fusion, an asymmetric cross-feature fusion subnetwork that emphasizes reference-based attention to effectively merge these features across exposures, and a reconstruction subnetwork to mitigate ghosting artifacts and preserve fine details. Extensive experimental evaluations demonstrate that the proposed method achieves state-of-the-art performance across various datasets, showing the remarkable potential of our solution in HDR video reconstruction. The codes and data captured by DCS will be available at https://zqqqyu.github.io/DCS-HDR/.

cs.CV↗

arXiv2026

Construction of MRD Codes Based on Circular-Shift Operations

Most well-known constructions of $(N \times n, q^{Nk}, d)$ maximum rank distance (MRD) codes rely on the arithmetic of $\mathbb{F}_{q^N}$, whose increasing complexity with larger $N$ hinders parameter selection and practical implementation. In this work, based on circular-shift operations, we present a construction of $(J \times n, q^{Jk}, d)$ MRD codes with efficient encoding, where $J$ equals to the Euler's totient function of a defined $L$ subject to $\gcd(q, L) = 1$. The proposed construction is performed entirely over $\mathbb{F}_q$ and avoids the arithmetic of $\mathbb{F}_{q^J}$. We further characterize the constructed MRD codes, Gabidulin codes and twisted Gabidulin codes using a set of $q$-linearized polynomials over the row vector space $\mathbb{F}_{q}^N$, and clarify their inherent difference and connection. For the case $J \neq m_L$, where $m_L$ denotes the multiplicative order of $q$ modulo $L$, we show that the proposed MRD codes, in a family of settings, are different from any Gabidulin code and any twisted Gabidulin code. For the case $J = m_L$, we prove that every constructed $(J \times n, q^{Jk}, d)$ MRD code coincides with a $(J \times n, q^{Jk}, d)$ Gabidulin code, yielding an equivalent circular-shift-based construction that operates directly over $\mathbb{F}_q$. In addition, we prove that under some parameter settings, the constructed MRD codes are equivalent to a generalization of Gabidulin codes obtained by summing and concatenating several $(m_L \times n, q^{m_Lk}, d)$ Gabidulin codes. When $q=2$, $L$ is prime and $n\leq m_L$, it is analyzed that generating a codeword of the proposed $((L-1) \times n, 2^{(L-1)k}, d)$ MRD codes requires $O(nkL)$ exclusive OR (XOR) operations, while generating a codeword of $((L-1) \times n, 2^{(L-1)k}, d)$ Gabidulin codes, based on customary construction, requires $O(nkL^2)$ XOR operations.

cs.IT↗

arXiv2024

Circular-shift-based Vector Linear Network Coding and Its Application to Array Codes

Circular-shift linear network coding (LNC) is a class of vector LNC with local encoding kernels selected from cyclic permutation matrices, so that it has low coding complexities. However, it is insufficient to exactly achieve the capacity of a multicast network, so the data units transmitted along the network need to contain redundant symbols, which affects the transmission efficiency. In this paper, as a variation of circular-shift LNC, we introduce a new class of vector LNC over arbitrary GF($p$), called circular-shift-based vector LNC, which is shown to be able to exactly achieve the capacity of a multicast network. The set of local encoding kernels in circular-shift-based vector LNC is nontrivially designed such that it is closed under multiplication by elements in itself. It turns out that the coding complexity of circular-shift-based vector LNC is comparable to and, in some cases, lower than that of circular-shift LNC. The new results in circular-shift-based vector LNC further facilitates us to characterize and design Vandermonde circulant maximum distance separable (MDS) array codes, which are built upon the structure of Vandermonde matrices and circular-shift operations. We prove that for $r \geq 2$, the largest possible $k$ for an $L$-dimensional $(k+r, k)$ Vandermonde circulant $p$-ary MDS array code is $p^{m_L}-1$, where $L$ is an integer co-prime with $p$, and $m_L$ represents the multiplicative order of $p$ modulo $L$. For $r = 2, 3$, we introduce two new types of $(k+r, k)$ $p$-ary array codes that achieves the largest $k = p^{m_L}-1$. For the special case that $p = 2$, we propose scheduling encoding algorithms for the 2 new codes, so that the encoding complexity not only asymptotically approaches the optimal $2$ XORs per original data bit, but also slightly outperforms the encoding complexity of other known Vandermonde circulant MDS array codes with $k = p^{m_L}-1$.

cs.IT↗

arXiv2024

RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendation

Large Language Models (LLMs) have demonstrated remarkable capabilities and have been extensively deployed across various domains, including recommender systems. Prior research has employed specialized \textit{prompts} to leverage the in-context learning capabilities of LLMs for recommendation purposes. More recent studies have utilized instruction tuning techniques to align LLMs with human preferences, promising more effective recommendations. However, existing methods suffer from several limitations. The full potential of LLMs is not fully elicited due to low-quality tuning data and the overlooked integration of conventional recommender signals. Furthermore, LLMs may generate inconsistent responses for different ranking tasks in the recommendation, potentially leading to unreliable results. In this paper, we introduce \textbf{RecRanker}, tailored for instruction tuning LLMs to serve as the \textbf{Ranker} for top-\textit{k} \textbf{Rec}ommendations. Specifically, we introduce an adaptive sampling module for sampling high-quality, representative, and diverse training data. To enhance the prompt, we introduce a position shifting strategy to mitigate position bias and augment the prompt with auxiliary information from conventional recommendation models, thereby enriching the contextual understanding of the LLM. Subsequently, we utilize the sampled data to assemble an instruction-tuning dataset with the augmented prompts comprising three distinct ranking tasks: pointwise, pairwise, and listwise rankings. We further propose a hybrid ranking method to enhance the model performance by ensembling these ranking tasks. Our empirical evaluations demonstrate the effectiveness of our proposed RecRanker in both direct and sequential recommendation scenarios.

cs.IR↗

arXiv2024

Hierarchical Frequency-based Upsampling and Refining for Compressed Video Quality Enhancement

Video compression artifacts arise due to the quantization operation in the frequency domain. The goal of video quality enhancement is to reduce compression artifacts and reconstruct a visually-pleasant result. In this work, we propose a hierarchical frequency-based upsampling and refining neural network (HFUR) for compressed video quality enhancement. HFUR consists of two modules: implicit frequency upsampling module (ImpFreqUp) and hierarchical and iterative refinement module (HIR). ImpFreqUp exploits DCT-domain prior derived through implicit DCT transform, and accurately reconstructs the DCT-domain loss via a coarse-to-fine transfer. Consequently, HIR is introduced to facilitate cross-collaboration and information compensation between the scales, thus further refine the feature maps and promote the visual quality of the final output. We demonstrate the effectiveness of the proposed modules via ablation experiments and visualized results. Extensive experiments on public benchmarks show that HFUR achieves state-of-the-art performance for both constant bit rate and constant QP modes.

eess.IV↗

arXiv2023

Aegis: Mitigating Targeted Bit-flip Attacks against Deep Neural Networks

Bit-flip attacks (BFAs) have attracted substantial attention recently, in which an adversary could tamper with a small number of model parameter bits to break the integrity of DNNs. To mitigate such threats, a batch of defense methods are proposed, focusing on the untargeted scenarios. Unfortunately, they either require extra trustworthy applications or make models more vulnerable to targeted BFAs. Countermeasures against targeted BFAs, stealthier and more purposeful by nature, are far from well established. In this work, we propose Aegis, a novel defense method to mitigate targeted BFAs. The core observation is that existing targeted attacks focus on flipping critical bits in certain important layers. Thus, we design a dynamic-exit mechanism to attach extra internal classifiers (ICs) to hidden layers. This mechanism enables input samples to early-exit from different layers, which effectively upsets the adversary's attack plans. Moreover, the dynamic-exit mechanism randomly selects ICs for predictions during each inference to significantly increase the attack cost for the adaptive attacks where all defense mechanisms are transparent to the adversary. We further propose a robustness training strategy to adapt ICs to the attack scenarios by simulating BFAs during the IC training phase, to increase model robustness. Extensive evaluations over four well-known datasets and two popular DNN structures reveal that Aegis could effectively mitigate different state-of-the-art targeted attacks, reducing attack success rate by 5-10$\times$, significantly outperforming existing defense methods.

cs.CR↗

arXiv2022

Completion Delay of Random Linear Network Coding in Full-Duplex Relay Networks

As the next-generation wireless networks thrive, full-duplex and relay techniques are combined to improve the network performance. Random linear network coding (RLNC) is another popular technique to enhance the efficiency and reliability of wireless communications. In this paper, in order to explore the potential of RLNC in full-duplex relay networks, we investigate two fundamental perfect RLNC schemes and theoretically analyze their completion delay performance. The first scheme is a straightforward application of conventional perfect RLNC studied in wireless broadcast, so it involves no additional process at the relay. Its performance serves as an upper bound for all perfect RLNC schemes. The other scheme allows sufficiently large buffer and unconstrained linear coding at the relay. It attains the optimal performance and serves as a lower bound for all RLNC schemes. For both schemes, closed-form formulae to characterize the expected completion delay at a single receiver as well as for the whole system are derived. Numerical results are also demonstrated to validate the theoretical characterizations, and compare the two fundamental schemes with the existing one.

cs.IT↗

arXiv2021

Online Service Placement and Request Scheduling in MEC Networks

Mobile edge computing (MEC) emerges as a promising solution for servicing delay-sensitive tasks at the edge network. A body of recent literature started to focus on cost-efficient service placement and request scheduling. This work investigates the joint optimization of service placement and request scheduling in a dense MEC network, and develops an efficient online algorithm that achieves close-to-optimal performance. Our online algorithm consists of two basic modules: (1) a regularization with look-ahead approach from competitive online convex optimization, for decomposing the offline relaxed minimization problem into multiple sub-problems, each of which can be efficiently solved in each time slot; (2) a randomized rounding method to transform the fractional solution of offline relaxed problem into integer solution of the original minimization problem, guaranteeing a low competitive ratio. Both theoretical analysis and simulation studies corroborate the efficacy of our proposed online MEC optimization algorithm.

cs.DC↗

arXiv2021

Energy-aware Task Scheduling with Deadline Constraint in DVFS-enabled Heterogeneous Clusters

Energy conservation of large data centers for high-performance computing workloads, such as deep learning with big data, is of critical significance, where cutting down a few percent of electricity translates into million-dollar savings. This work studies energy conservation on emerging CPU-GPU hybrid clusters through dynamic voltage and frequency scaling (DVFS). We aim at minimizing the total energy consumption of processing a batch of offline tasks or a sequence of real-time tasks under deadline constraints. We derive a fast and accurate analytical model to compute the appropriate voltage/frequency setting for each task and assign multiple tasks to the cluster with heuristic scheduling algorithms. In particular, our model stresses the nonlinear relationship between task execution time and processor speed for GPU-accelerated applications, for more accurately capturing real-world GPU energy consumption. In performance evaluation driven by real-world power measurement traces, our scheduling algorithm shows comparable energy savings to the theoretical upper bound. With a GPU scaling interval where analytically at most 36% of energy can be saved, we record 33-35% of energy savings. Our results are applicable to energy management on modern heterogeneous clusters.

cs.DC↗

arXiv2020

Perceptual Generative Autoencoders

Modern generative models are usually designed to match target distributions directly in the data space, where the intrinsic dimension of data can be much lower than the ambient dimension. We argue that this discrepancy may contribute to the difficulties in training generative models. We therefore propose to map both the generated and target distributions to a latent space using the encoder of a standard autoencoder, and train the generator (or decoder) to match the target distribution in the latent space. Specifically, we enforce the consistency in both the data space and the latent space with theoretically justified data and latent reconstruction losses. The resulting generative model, which we call a perceptual generative autoencoder (PGA), is then trained with a maximum likelihood or variational autoencoder (VAE) objective. With maximum likelihood, PGAs generalize the idea of reversible generative models to unrestricted neural network architectures and arbitrary number of latent dimensions. When combined with VAEs, PGAs substantially improve over the baseline VAEs in terms of sample quality. Compared to other autoencoder-based generative models using simple priors, PGAs achieve state-of-the-art FID scores on CIFAR-10 and CelebA.

cs.LG↗

arXiv2019

Circular-shift Linear Network Codes with Arbitrary Odd Block Lengths

Circular-shift linear network coding (LNC) is a class of vector LNC with low encoding and decoding complexities, and with local encoding kernels chosen from cyclic permutation matrices. When $L$ is a prime with primitive root $2$, it was recently shown that a scalar linear solution over GF($2^{L-1}$) induces an $L$-dimensional circular-shift linear solution at rate $(L-1)/L$. In this work, we prove that for arbitrary odd $L$, every scalar linear solution over GF($2^{m_L}$), where $m_L$ refers to the multiplicative order of $2$ modulo $L$, can induce an $L$-dimensional circular-shift linear solution at a certain rate. Based on the generalized connection, we further prove that for such $L$ with $m_L$ beyond a threshold, every multicast network has an $L$-dimensional circular-shift linear solution at rate $ϕ(L)/L$, where $ϕ(L)$ is the Euler's totient function of $L$. An efficient algorithm for constructing such a solution is designed. Finally, we prove that every multicast network is asymptotically circular-shift linearly solvable.

cs.IT↗

arXiv2018

Device-to-Device Load Balancing for Cellular Networks

Small-cell architecture is widely adopted by cellular network operators to increase network capacity. By reducing the size of cells, operators can pack more (low-power) base stations in an area to better serve the growing demands, without causing extra interference. However, this approach suffers from low spectrum temporal efficiency. When a cell becomes smaller and covers fewer users, its total traffic fluctuates significantly due to insufficient traffic aggregation and exhibiting a large "peak-to-mean" ratio. As operators customarily provision spectrum for peak traffic, large traffic temporal fluctuation inevitably leads to low spectrum temporal efficiency. In this paper, we advocate device-to-device (D2D) load-balancing as a useful mechanism to address the fundamental drawback of small-cell architecture. The idea is to shift traffic from a congested cell to its adjacent under-utilized cells by leveraging inter-cell D2D communication, so that the traffic can be served without using extra spectrum, effectively improving the spectrum temporal efficiency. We provide theoretical modeling and analysis to characterize the benefit of D2D load balancing, in terms of total spectrum requirements of all individual cells. We also derive the corresponding cost, in terms of incurred D2D traffic overhead. We carry out empirical evaluations based on real-world 4G data traces to gauge the benefit and cost of D2D load balancing under practical settings. The results show that D2D load balancing can reduce the spectrum requirement by 25% as compared to the standard scenario without D2D load balancing, at the expense of negligible 0.7% D2D traffic overhead.

cs.NI↗

arXiv2018

Removing the Feature Correlation Effect of Multiplicative Noise

Multiplicative noise, including dropout, is widely used to regularize deep neural networks (DNNs), and is shown to be effective in a wide range of architectures and tasks. From an information perspective, we consider injecting multiplicative noise into a DNN as training the network to solve the task with noisy information pathways, which leads to the observation that multiplicative noise tends to increase the correlation between features, so as to increase the signal-to-noise ratio of information pathways. However, high feature correlation is undesirable, as it increases redundancy in representations. In this work, we propose non-correlating multiplicative noise (NCMN), which exploits batch normalization to remove the correlation effect in a simple yet effective way. We show that NCMN significantly improves the performance of standard multiplicative noise on image classification tasks, providing a better alternative to dropout for batch-normalized networks. Additionally, we present a unified view of NCMN and shake-shake regularization, which explains the performance gain of the latter.

cs.LG↗

arXiv2018

Normalized Direction-preserving Adam

Adaptive optimization algorithms, such as Adam and RMSprop, have shown better optimization performance than stochastic gradient descent (SGD) in some scenarios. However, recent studies show that they often lead to worse generalization performance than SGD, especially for training deep neural networks (DNNs). In this work, we identify the reasons that Adam generalizes worse than SGD, and develop a variant of Adam to eliminate the generalization gap. The proposed method, normalized direction-preserving Adam (ND-Adam), enables more precise control of the direction and step size for updating weight vectors, leading to significantly improved generalization performance. Following a similar rationale, we further improve the generalization performance in classification tasks by regularizing the softmax logits. By bridging the gap between SGD and Adam, we also hope to shed light on why certain optimization algorithms generalize better than others.

cs.LG↗