arXiv subjects

Shipeng Li

Publications and source records attributed to Shipeng Li.

18 recordsLinked to original sources

arXiv2026

Denoising Implicit Feedback for Cold-start Recommendation

Implicit feedback is widely used in recommender systems due to its accessibility and generality, yet it usually presents noisy samples (e.g., clickbait, position bias). Meanwhile, recommenders inevitably face the item cold-start problem due to the continuous influx of new items. We identify that cold items are more prone to noisy samples due to the aforementioned factors, and researchers often overlook the significance of denoising implicit feedback for cold items. Previous denoising studies usually identify noisy samples based on heuristic patterns, such as higher loss values, and mitigate noise through sample selection or re-weighting. However, these methods have limited adaptability and are ineffective in cold-start scenarios. To achieve denoising implicit feedback for cold-start recommendation, we propose a model-agnostic denoising method called DIF. First, user preferences for content remain stable, which allows us to infer pseudo-labels indicating whether a user is interested in a cold item through content-similar warm items. Furthermore, to improve pseudo-label accuracy, we model the confidence of pseudo-labels based on the content similarity between the cold item and warm items, and then aggregate multiple pseudo-labels for each sample. Finally, we explicitly estimate the uncertainty of the noisy sample label by considering its relative entropy and the cold-start status of the item, which adaptively guides the role of pseudo-labels to correct the noisy labels at the sample level. DIF's superiority is supported by both theoretical justification and extensive experiments on real-world datasets. The method has been deployed on a billion-user scale short video application Kuaishou and has significantly improved various commercial metrics within cold-start scenarios.

cs.AI↗

arXiv2026

The Vertical Challenge of Low-Altitude Economy: Why We Need a Unified Height System?

The explosive growth of the low-altitude economy, driven by eVTOLs and UAVs, demands a unified digital infrastructure to ensure safety and scalability. However, the current aviation vertical references are dangerously fragmented: manned aviation relies on barometric pressure, cartography uses Mean Sea Level (MSL), and obstacle avoidance depends on Above Ground Level (AGL). This fragmentation creates significant ambiguity for autonomous systems and hinders cross-stakeholder interoperability. In this article, we propose Height Above Ellipsoid (HAE) as the standardized vertical reference for lower airspace. Unlike legacy systems prone to environmental drift and inconsistent datums, HAE provides a globally consistent, GNSS-native, and mathematically stable reference. We present a pragmatic bidirectional transformation framework to bridge HAE with legacy systems and demonstrate its efficacy through (1) real-world implementation in Shenzhen's partitioned airspace management, and (2) a probabilistic risk assessment driven by empirical flight logs from the PX4 ecosystem. Results show that transitioning to HAE reduces the required vertical separation minimum, effectively increasing dynamic airspace capacity while maintaining a target safety level. This work offers a roadmap for transitioning from analog height keeping to a digital-native vertical standard.

eess.SY↗

arXiv2026

Dynamic Water-Wave Tweezers

Following a recent demonstration of stable trapping of floating particles by stationary (monochromatic) structured water waves [Nature 638, 394 (2025)], we report dynamic water-wave tweezers that enable controllable transport of the trapped particle along an arbitrary trajectory on the water surface. Furthermore, we demonstrate simultaneous transport of two trapped particles along different trajectories. We employ a triangular lattice formed by the interference of three plane waves, which can trap particles, depending on the wave frequency and particle parameters, either at intensity maxima or at intensity zeros (vortices). By introducing small frequency detunings of the interfering waves, we control 2D motion of the lattice and trapped particles. This approach is robust and effective over a relatively broad range of particle sizes and wave frequencies, offering remarkable new possibilities for noncontact manipulation of floating (e.g., biological and soft-matter) objects in fluidic environments.

physics.flu-dyn↗

arXiv2025

Scaling Graph Chain-of-Thought Reasoning: A Multi-Agent Framework with Efficient LLM Serving

Graph Chain-of-Thought (Graph-CoT) enables large language models (LLMs) to perform step-by-step reasoning over graph-structured knowledge, but existing pipelines suffer from low accuracy, excessive token usage, high latency, and low throughput due to single-agent monolithic prompts, repeated context re-encoding, and inefficient serving execution. We present GLM, the first multi-agent Graph-CoT system co-designed with an optimized LLM serving architecture. GLM decomposes reasoning into specialized agents for classification, reasoning, action generation, and graph retrieval, enabling branching and selective context sharing to reduce prompt length and reasoning iterations while preserving reasoning quality, thereby improving accuracy and reducing overall token consumption. To scale inference, we introduce a Graph-CoT-aware LLM inference mechanism with graph-specific KV-cache management, priority-based eviction, and pipelined execution to improve serving efficiency. Experiments demonstrate that GLM improves answer accuracy by up to 38%, reduces token cost by up to 95.7%, lowers inference latency by 90.3%, and achieves up to 15.1x higher throughput compared to state-of-the-art Graph-CoT baselines, enabling efficient adoption for complex real-world reasoning at scale.

cs.LG↗

arXiv2025

STAR: Decode-Phase Rescheduling for LLM Inference

Large Language Model (LLM) inference has emerged as a fundamental paradigm, however, variations in output length cause severe workload imbalance in the decode phase, particularly for long-output reasoning tasks. Existing systems, such as PD disaggregation architectures, rely on static prefill-to-decode scheduling, which often results in SLO violations and OOM failures under evolving decode workloads. In this paper, we propose STAR, a decode rescheduling system powered by length prediction to anticipate future workloads. Our core contributions include: (1) A lightweight and continuous LLM-native prediction method that leverages LLM hidden state to model remaining generation length with high precision (reducing MAE by 49.42%) and low overhead (cutting predictor parameters by 93.28%); (2) A rescheduling solution in decode phase with a dynamic balancing mechanism that integrates current and predicted workloads, reducing P99 TPOT by 75.1% and achieving 2.63 times higher goodput.

cs.DC↗

arXiv2025

SmartSwap: Swap-Based Memory Optimization for LLM Training under Varying Operator Sequences

The increasing size of large language models (LLMs) has led to a surge in memory requirements during training, often exceeding the capacity of high-bandwidth memory (HBM). Swap-based memory optimization incurs neither accuracy loss nor additional end-to-end overhead when effectively overlapped, thus being an attractive solution. However, existing swap methods assume consistent operator sequences, which is impractical in Eager Mode, where operator sequences can vary during change. We propose Chameleon, which redesigns the end-to-end process of swap-based memory optimization and is the first work to consider varying operator sequences in Eager Mode. Chameleon (i) introduces a lightweight online profiler to enable continuous profiling for monitoring operator sequences, (ii) generates effective swap policies with limited operator information, and (iii) optimizes the policy execution module for accurate policy application and better performance. Experimental results demonstrate that Chameleon reduces profiling overhead by 84.25%, enables training models up to 4x larger than hardware memory while adapting to changes in operator sequences, improves performance by up to 38.94% compared to recomputation or high-degree parallelism.

cs.DC↗

arXiv2025

A Relaxed Step-Ratio Constraint for Time-Fractional Cahn--Hilliard Equations: Analysis and Computation

Numerical solutions of time-fractional differential equations encounter significant challenges arising from solution singularities at the initial time. To address this issue, the construction of nonuniform temporal meshes satisfying $\tau_k/\tau_{k-1} \geq 1$ has emerged as an effective strategy, where $\tau_k$ represents the $k$-th time-step size. For the time-fractional Cahn-Hilliard equation, Liao et al.~[\textit{IMA J. Numer. Anal.}, \textbf{45} (2025), 1425--1454] developed an analytical framework using a variable-step L2 formula with the constraint $0.3960 \leq \tau_k/\tau_{k-1} \leq r^*(\alpha)$, where $r^*(\alpha) \geq 4.660$ for $\alpha \in (0,1)$. The present work makes substantial theoretical progress by introducing innovative splitting techniques that relax the step-size ratio restriction to $\tau_k/\tau_{k-1} \leq \rho^*(\alpha)$, with $\rho^*(\alpha) > \overline{\rho} \approx 4.7476114$. This advancement provides significantly greater flexibility in time-step selection. Building on this theoretical foundation, we propose a refined L2-type temporal approximation coupled with a fourth-order compact difference spatial discretization, yielding an efficient numerical scheme for the time-fractional Cahn-Hilliard problem. Our rigorous analysis establishes the scheme's fundamental properties, including unique solvability, exact discrete volume conservation, proper energy dissipation laws, and optimal convergence rates. For practical implementation, we construct a specialized nonuniform mesh that automatically satisfies the relaxed constraint $\rho^*(\alpha) > 4.7476114$.

math.NA↗

arXiv2025

LearnAlign: Data Selection for LLM Reinforcement Learning with Improved Gradient Alignment

Reinforcement learning with verifiable rewards (RLVR) has become a key technique for enhancing LLMs' reasoning abilities, yet its data inefficiency remains a major bottleneck. To address this critical yet challenging issue, we present a novel gradient-alignment-based method, named LearnAlign, which intelligently selects the learnable and representative training reasoning data for RLVR post-training. To overcome the well-known response-length bias in gradient norms, we introduce the data learnability based on the success rate, which indicates the learning potential of each data point. Experiments across five reasoning benchmarks show that our method significantly reduces training data requirements while achieving minor performance degradation or even improving performance compared to full-data training. Specifically, it reduces data requirements by up to 1,000 data points with better performance (77.5%) than that on the full dataset on the GSM8K benchmark (77.0%). Furthermore, its efficiency is demonstrated on both mathematical and code benchmarks by using much less data from the DAPO-MATH-17K dataset.

cs.LG↗

arXiv2025

Echo: Efficient Co-Scheduling of Hybrid Online-Offline Tasks for Large Language Model Serving

Large language models have been widely deployed in various applications, encompassing both interactive online tasks and batched offline tasks. Given the burstiness and latency sensitivity of online tasks, over-provisioning resources is common practice. This allows for the integration of latency-insensitive offline tasks during periods of low online load, enhancing resource utilization. However, strategically serving online and offline tasks through a preemption mechanism fails to fully leverage the flexibility of offline tasks and suffers from KV cache recomputation and irregular workloads. In this paper, we introduce Echo, a collaborative online-offline task serving system, including a scheduler, a KV cache manager, and estimation toolkits. The scheduler and KV cache manager work tightly to maximize the throughput of offline tasks, while the estimator further predicts execution time to ensure online task SLOs. The scheduler leverages the batch information of last iteration to reduce the search space for finding the optimal schedule. The KV cache manager sets the priority of the KV cache based on the type of tasks and the opportunity of prefix sharing to reduce the recomputation. Finally, the estimation toolkits predict the execution time, future memory consumption, and the throughput of offline tasks to guide the scheduler, KV cache manager, and the system deployer. Evaluation based on real-world workloads demonstrates that Echo can increase offline task throughput by up to $3.3\times$, while satisfying online task SLOs.

cs.DC↗

arXiv2024

Revisiting Service Level Objectives and System Level Metrics in Large Language Model Serving

User experience is a critical factor Large Language Model (LLM) serving systems must consider, where service level objectives (SLOs) considering the experience of individual requests and system level metrics (SLMs) considering the overall system performance are two key performance measures. However, we observe two notable issues in existing metrics: 1) manually delaying the delivery of some tokens can improve SLOs, and 2) actively abandoning requests that do not meet SLOs can improve SLMs, both of which are counterintuitive. In this paper, we revisit SLOs and SLMs in LLM serving, and propose a new SLO that aligns with user experience. Based on the SLO, we propose a comprehensive metric framework called smooth goodput, which integrates SLOs and SLMs to reflect the nature of user experience in LLM serving. Through this unified framework, we reassess the performance of different LLM serving systems under multiple workloads. Evaluation results show that our metric framework provides a more comprehensive view of token delivery and request processing, and effectively captures the optimal point of user experience and system performance with different serving strategies.

cs.LG↗

arXiv2015

Content adaptive screen image scaling

This paper proposes an efficient content adaptive screen image scaling scheme for the real-time screen applications like remote desktop and screen sharing. In the proposed screen scaling scheme, a screen content classification step is first introduced to classify the screen image into text and pictorial regions. Afterward, we propose an adaptive shift linear interpolation algorithm to predict the new pixel values with the shift offset adapted to the content type of each pixel. The shift offset for each screen content type is offline optimized by minimizing the theoretical interpolation error based on the training samples respectively. The proposed content adaptive screen image scaling scheme can achieve good visual quality and also keep the low complexity for real-time applications.

cs.CV↗

arXiv2015

Group $K$-Means

We study how to learn multiple dictionaries from a dataset, and approximate any data point by the sum of the codewords each chosen from the corresponding dictionary. Although theoretically low approximation errors can be achieved by the global solution, an effective solution has not been well studied in practice. To solve the problem, we propose a simple yet effective algorithm \textit{Group $K$-Means}. Specifically, we take each dictionary, or any two selected dictionaries, as a group of $K$-means cluster centers, and then deal with the approximation issue by minimizing the approximation errors. Besides, we propose a hierarchical initialization for such a non-convex problem. Experimental results well validate the effectiveness of the approach.

cs.CV↗

arXiv2014

Optimized Cartesian $K$-Means

Product quantization-based approaches are effective to encode high-dimensional data points for approximate nearest neighbor search. The space is decomposed into a Cartesian product of low-dimensional subspaces, each of which generates a sub codebook. Data points are encoded as compact binary codes using these sub codebooks, and the distance between two data points can be approximated efficiently from their codes by the precomputed lookup tables. Traditionally, to encode a subvector of a data point in a subspace, only one sub codeword in the corresponding sub codebook is selected, which may impose strict restrictions on the search accuracy. In this paper, we propose a novel approach, named Optimized Cartesian $K$-Means (OCKM), to better encode the data points for more accurate approximate nearest neighbor search. In OCKM, multiple sub codewords are used to encode the subvector of a data point in a subspace. Each sub codeword stems from different sub codebooks in each subspace, which are optimally generated with regards to the minimization of the distortion errors. The high-dimensional data point is then encoded as the concatenation of the indices of multiple sub codewords from all the subspaces. This can provide more flexibility and lower distortion errors than traditional methods. Experimental results on the standard real-life datasets demonstrate the superiority over state-of-the-art approaches for approximate nearest neighbor search.

cs.CV↗

arXiv2013

Fast Approximate $K$-Means via Cluster Closures

$K$-means, a simple and effective clustering algorithm, is one of the most widely used algorithms in multimedia and computer vision community. Traditional $k$-means is an iterative algorithm---in each iteration new cluster centers are computed and each data point is re-assigned to its nearest center. The cluster re-assignment step becomes prohibitively expensive when the number of data points and cluster centers are large. In this paper, we propose a novel approximate $k$-means algorithm to greatly reduce the computational complexity in the assignment step. Our approach is motivated by the observation that most active points changing their cluster assignments at each iteration are located on or near cluster boundaries. The idea is to efficiently identify those active points by pre-assembling the data into groups of neighboring points using multiple random spatial partition trees, and to use the neighborhood information to construct a closure for each cluster, in such a way only a small number of cluster candidates need to be considered when assigning a data point to its nearest cluster. Using complexity analysis, image data clustering, and applications to image retrieval, we show that our approach out-performs state-of-the-art approximate $k$-means algorithms in terms of clustering quality and efficiency.

cs.CV↗

arXiv2013

Fast Neighborhood Graph Search using Cartesian Concatenation

In this paper, we propose a new data structure for approximate nearest neighbor search. This structure augments the neighborhood graph with a bridge graph. We propose to exploit Cartesian concatenation to produce a large set of vectors, called bridge vectors, from several small sets of subvectors. Each bridge vector is connected with a few reference vectors near to it, forming a bridge graph. Our approach finds nearest neighbors by simultaneously traversing the neighborhood graph and the bridge graph in the best-first strategy. The success of our approach stems from two factors: the exact nearest neighbor search over a large number of bridge vectors can be done quickly, and the reference vectors connected to a bridge (reference) vector near the query are also likely to be near the query. Experimental results on searching over large scale datasets (SIFT, GIST and HOG) show that our approach outperforms state-of-the-art ANN search algorithms in terms of efficiency and accuracy. The combination of our approach with the IVFADC system also shows superior performance over the BIGANN dataset of $1$ billion SIFT features compared with the best previously published result.

cs.CV↗

arXiv2013

Hybrid Affinity Propagation

In this paper, we address a problem of managing tagged images with hybrid summarization. We formulate this problem as finding a few image exemplars to represent the image set semantically and visually, and solve it in a hybrid way by exploiting both visual and textual information associated with images. We propose a novel approach, called homogeneous and heterogeneous message propagation ($\text{H}^\text{2}\text{MP}$). Similar to the affinity propagation (AP) approach, $\text{H}^\text{2}\text{MP}$ reduce the conventional \emph{vector} message propagation to \emph{scalar} message propagation to make the algorithm more efficient. Beyond AP that can only handle homogeneous data, $\text{H}^\text{2}\text{MP}$ generalizes it to exploit extra heterogeneous relations and the generalization is non-trivial as the reduction to scalar messages from vector messages is more challenging. The main advantages of our approach lie in 1) that $\text{H}^\text{2}\text{MP}$ exploits visual similarity and in addition the useful information from the associated tags, including the associations relation between images and tags and the relations within tags, and 2) that the summary is both visually and semantically satisfactory. In addition, our approach can also present a textual summary to a tagged image collection, which can be used to automatically generate a textual description. The experimental results demonstrate the effectiveness and efficiency of the roposed approach.

cs.CV↗

arXiv2013

Scalable $k$-NN graph construction

The $k$-NN graph has played a central role in increasingly popular data-driven techniques for various learning and vision tasks; yet, finding an efficient and effective way to construct $k$-NN graphs remains a challenge, especially for large-scale high-dimensional data. In this paper, we propose a new approach to construct approximate $k$-NN graphs with emphasis in: efficiency and accuracy. We hierarchically and randomly divide the data points into subsets and build an exact neighborhood graph over each subset, achieving a base approximate neighborhood graph; we then repeat this process for several times to generate multiple neighborhood graphs, which are combined to yield a more accurate approximate neighborhood graph. Furthermore, we propose a neighborhood propagation scheme to further enhance the accuracy. We show both theoretical and empirical accuracy and efficiency of our approach to $k$-NN graph construction and demonstrate significant speed-up in dealing with large scale visual data.

cs.CV↗

arXiv2013

Image Tag Refinement by Regularized Latent Dirichlet Allocation

Tagging is nowadays the most prevalent and practical way to make images searchable. However, in reality many manually-assigned tags are irrelevant to image content and hence are not reliable for applications. A lot of recent efforts have been conducted to refine image tags. In this paper, we propose to do tag refinement from the angle of topic modeling and present a novel graphical model, regularized Latent Dirichlet Allocation (rLDA). In the proposed approach, tag similarity and tag relevance are jointly estimated in an iterative manner, so that they can benefit from each other, and the multi-wise relationships among tags are explored. Moreover, both the statistics of tags and visual affinities of images in the corpus are explored to help topic modeling. We also analyze the superiority of our approach from the deep structure perspective. The experiments on tag ranking and image retrieval demonstrate the advantages of the proposed method.

cs.IR↗