Searcharxiv⌕ Search

arXiv subjects

Sheng Zhou

Publications and source records attributed to Sheng Zhou.

At least 37 records · Page 2Linked to original sources

DiP-SD: Distributed Pipelined Speculative Decoding for Efficient LLM Inference at the Edge

Speculative decoding has emerged as a promising technique for large language model (LLM) inference by accelerating autoregressive decoding via draft-then-verify. This paper studies a new edge scenario with multi-user inference, where draft tokens are generated locally on devices and subsequently offloaded to a centralized edge server for batch verification. The key challenge is to sustain high throughput under coupled decisions of (i) batching and pipeline scheduling and (ii) per user draft token length. We propose DiP-SD, which exploits two complementary parallelism dimensions: device-level distributed drafting and phase-level draft-verify pipelining. We formulate a throughput-maximization objective, defined as the expected number of accepted tokens per unit time, and jointly optimize the number of batches, user-to-batch assignment, and integer draft lengths. To solve the resulting fractional mixed-integer program, DiP-SD scans the batch number and iteratively alternates between an association subproblem and a draft-length subproblem. Numerical results under a Qwen3-1.7B/Qwen3-32B device-edge deployment show that DiP-SD achieves up to 17.89x throughput over autoregressive decoding (AD) and 1.93x over AD with greedy batching.

cs.IT↗

SLIDE: Simultaneous Model Downloading and Inference at the Wireless Network Edge

To support on-device inference, the next-generation mobile networks are expected to support real-time model downloading services to mobile users. However, powerful AI models typically have large model sizes, resulting in excessive end-to-end (E2E) downloading-and-inference (DAI) latency. To address this issue, we propose a simultaneous model downloading and inference (SLIDE) framework, which allows users to perform inference with downloaded layers while simultaneously receiving the remaining layers of the model. To this end, we formulate a task throughput maximization problem by jointly optimizing model provisioning, spectrum bandwidth allocation, and computing resource allocation for multi-user downlink systems. Unlike traditional DAI frameworks, SLIDE introduces recursive dependencies across layers, where inference latency depends recursively on the downloading bandwidth and computing resource allocation for each of the preceding layers. To solve this challenging problem, we design an efficient algorithm that acquires the optimal solution with polynomial-time complexity. Simulation results demonstrate that the proposed SLIDE framework significantly improves task throughput under latency and communication resource constraints compared with the conventional model downloading schemes.

cs.NI↗

Towards Scalable Lightweight GUI Agents via Multi-role Orchestration

Autonomous Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) enable digital automation on end-user devices. While scaling both parameters and data has yielded substantial gains, advanced methods still suffer from prohibitive deployment costs on resource-constrained devices. When facing complex in-the-wild scenarios, lightweight GUI agents are bottlenecked by limited capacity and poor task scalability under end-to-end episodic learning, impeding adaptation to multi-agent systems (MAS), while training multiple skill-specific experts remains costly. Can we strike an effective trade-off in this cost-scalability dilemma, enabling lightweight MLLMs to participate in realistic GUI workflows? To address these challenges, we propose the LAMO framework, which endows a lightweight MLLM with GUI-specific knowledge and task scalability, allowing multi-role orchestration to expand its capability boundary for GUI automation. LAMO combines role-oriented data synthesis with a two-stage training recipe: (i) supervised fine-tuning with Perplexity-Weighted Cross-Entropy optimization for knowledge distillation and visual perception enhancement, and (ii) reinforcement learning for role-oriented cooperative exploration. With LAMO, we develop a task-scalable native GUI agent, LAMO-3B, supporting monolithic execution and MAS-style orchestration. When paired with advanced planners as a plug-and-play policy executor, LAMO-3B can continuously benefit from planner advances, enabling a higher performance ceiling. Extensive static and online evaluations validate the effectiveness of our design.

cs.AI↗

Generalizable Self-Evolving Memory for Automatic Prompt Optimization

Automatic prompt optimization is a promising approach for adapting large language models (LLMs) to downstream tasks, yet existing methods typically search for a specific prompt specialized to a fixed task. This paradigm limits generalization across heterogeneous queries and prevents models from accumulating reusable prompting knowledge over time. In this paper, we propose MemAPO, a memory-driven framework that reconceptualizes prompt optimization as generalizable and self-evolving experience accumulation. MemAPO maintains a dual-memory mechanism that distills successful reasoning trajectories into reusable strategy templates while organizing incorrect generations into structured error patterns that capture recurrent failure modes. Given a new prompt, the framework retrieves both relevant strategies and failure patterns to compose prompts that promote effective reasoning while discouraging known mistakes. Through iterative self-reflection and memory editing, MemAPO continuously updates its memory, enabling prompt optimization to improve over time rather than restarting from scratch for each task. Experiments on diverse benchmarks show that MemAPO consistently outperforms representative prompt optimization baselines while substantially reducing optimization cost.

cs.CL↗

RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark

The integration of visual understanding and generation into unified multimodal models represents a significant stride toward general-purpose AI. However, a fundamental question remains unanswered by existing benchmarks: does this architectural unification actually enable synergetic interaction between the constituent capabilities? Existing evaluation paradigms, which primarily assess understanding and generation in isolation, are insufficient for determining whether a unified model can leverage its understanding to enhance its generation, or use generative simulation to facilitate deeper comprehension. To address this critical gap, we introduce RealUnify, a benchmark specifically designed to evaluate bidirectional capability synergy. RealUnify comprises 1,000 meticulously human-annotated instances spanning 10 categories and 32 subtasks. It is structured around two core axes: 1) Understanding Enhances Generation, which requires reasoning (e.g., commonsense, logic) to guide image generation, and 2) Generation Enhances Understanding, which necessitates mental simulation or reconstruction (e.g., of transformed or disordered visual inputs) to solve reasoning tasks. A key contribution is our dual-evaluation protocol, which combines direct end-to-end assessment with a diagnostic stepwise evaluation that decomposes tasks into distinct understanding and generation phases. This protocol allows us to precisely discern whether performance bottlenecks stem from deficiencies in core abilities or from a failure to integrate them. Through large-scale evaluations of 12 leading unified models and 6 specialized baselines, we find that current unified models still struggle to achieve effective synergy, indicating that architectural unification alone is insufficient. These results highlight the need for new training strategies and inductive biases to fully unlock the potential of unified modeling.

cs.AI↗

CRAFT-GUI: Curriculum-Reinforced Agent For GUI Tasks

As autonomous agents become adept at understanding and interacting with graphical user interface (GUI) environments, a new era of automated task execution is emerging. Recent studies have demonstrated that Reinforcement Learning (RL) can effectively enhance agents' performance in dynamic interactive GUI environments. However, these methods face two key limitations: (1) they overlook the significant variation in difficulty across different GUI tasks by treating the entire training data as a uniform set, which hampers the agent's ability to adapt its learning process; and (2) most approaches collapse task-specific nuances into a single, coarse reward, leaving the agent with a uniform signal that yields inefficient policy updates. To address these limitations, we propose CRAFT-GUI, a curriculum learning framework based on Group Relative Policy Optimization (GRPO) that explicitly accounts for the varying difficulty across trajectories. To enable more fine-grained policy optimization, we design a reward function that combines simple rule-based signals with model-judged evaluation, providing richer and more nuanced feedback during training. Experimental results demonstrate that our method achieves significant improvements over previous state-of-the-art approaches, outperforming them by 5.6% on public benchmarks Android Control and 10.3% on our internal online benchmarks, respectively. These findings empirically validate the effectiveness of integrating reinforcement learning with curriculum learning in GUI interaction tasks.

cs.AI↗

MaS-VQA: A Mask-and-Select Framework for Knowledge-Based Visual Question Answering

Knowledge-based Visual Question Answering (KB-VQA) requires models to answer questions by integrating visual information with external knowledge. However, retrieved knowledge is often noisy, partially irrelevant, or misaligned with the visual content, while internal model knowledge is difficult to control and interpret. Naive aggregation of these sources limits reasoning effectiveness and reduces answer accuracy. To address this, we propose MaS-VQA, a selection-driven framework that tightly couples explicit knowledge filtering with implicit knowledge reasoning. MaS-VQA first retrieves candidate passages and applies a Mask-and-Select mechanism to jointly prune irrelevant image regions and weakly relevant knowledge fragments, producing compact, high-signal multimodal knowledge . This filtered knowledge then guides the activation of internal knowledge in a constrained semantic space, enabling complementary co-modeling of explicit and implicit knowledge for robust answer prediction. Experiments on Encyclopedic-VQA and InfoSeek demonstrate consistent performance gains across multiple MLLM backbones, and ablations verify that the selection mechanism effectively reduces noise and enhances knowledge utilization.

cs.CV↗

TopKGAT: A Top-K Objective-Driven Architecture for Recommendation

Recommendation systems (RS) aim to retrieve the top-K items most relevant to users, with metrics such as Precision@K and Recall@K commonly used to assess effectiveness. The architecture of an RS model acts as an inductive bias, shaping the patterns the model is inclined to learn. In recent years, numerous recommendation architectures have emerged, spanning traditional matrix factorization, deep neural networks, and graph neural networks. However, their designs are often not explicitly aligned with the top-K objective, thereby limiting their effectiveness. To address this limitation, we propose TopKGAT, a novel recommendation architecture directly derived from a differentiable approximation of top-K metrics. The forward computation of a single TopKGAT layer is intrinsically aligned with the gradient ascent dynamics of the Precision@K metric, enabling the model to naturally improve top-K recommendation accuracy. Structurally, TopKGAT resembles a graph attention network and can be implemented efficiently. Extensive experiments on four benchmark datasets demonstrate that TopKGAT consistently outperforms state-of-the-art baselines. The code is available at https://github.com/StupidThree/TopKGAT.

cs.IR↗

Timeliness-Oriented Scheduling and Resource Allocation in Multi-Region Collaborative Perception

Collaborative perception (CP) is a critical technology in applications like autonomous driving and smart cities. It involves the sharing and fusion of information among sensors to overcome the limitations of individual perception, such as blind spots and range limitations. However, CP faces two primary challenges. First, due to the dynamic nature of the environment, the timeliness of the transmitted information is critical to perception performance. Second, with limited computational power at the sensors and constrained wireless bandwidth, the communication volume must be carefully designed to ensure feature representations are both effective and sufficient. This work studies the dynamic scheduling problem in a multi-region CP scenario, and presents a Timeliness-Aware Multi-region Prioritized (TAMP) scheduling algorithm to trade-off perception accuracy and communication resource usage. Timeliness reflects the utility of information that decays as time elapses, which is manifested by the perception performance in CP tasks. We propose an empirical penalty function that maps the joint impact of Age of Information (AoI) and communication volume to perception performance. Aiming to minimize this timeliness-oriented penalty in the long-term, and recognizing that scheduling decisions have a cumulative effect on subsequent system states, we propose the TAMP scheduling algorithm. TAMP is a Lyapunov-based optimization policy that decomposes the long-term average objective into a per-slot prioritization problem, balancing the scheduling worth against resource cost. We validate our algorithm in both intersection and corridor scenarios with the real-world Roadside Cooperative perception (RCooper) dataset. Extensive simulations demonstrate that TAMP outperforms the best-performing baseline, achieving an Average Precision (AP) improvement of up to 27% across various configurations.

cs.LG↗

OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation

Human cognition operates through two complementary modes: fast intuitive thinking and slow deliberate thinking. Vanilla large language models (LLMs) predominantly follow the fast-thinking paradigm, producing immediate responses; while recent large reasoning models (LRMs) adopt slow-thinking strategies, generating detailed reasoning chains before arriving at answers. While LRMs often achieve higher accuracy, this comes at the cost of substantially increased token usage. To address this efficiency-accuracy trade-off, we propose OThink-R1, a hybrid reasoning framework that integrates both modes within a single LRM and enables automatic mode switching based on problem characteristics. We first identify three major patterns of essential and redundant reasoning trajectories in LRMs, which guide the design of an auxiliary LLM-based judge that adaptively determines when slow thinking is necessary. Leveraging the judge's decisions, we construct a hybrid fine-tuning dataset by pruning redundant reasoning to produce fast-thinking samples and retaining complete reasoning for slow-thinking samples. This dataset is then used to fine-tune LRMs, equipping them with inherent autonomous mode-selection capabilities. Extensive experiments on mathematical and question-answering benchmarks show that OThink-R1 reduces reasoning token usage significantly while maintaining competitive accuracy. The code is available at https://github.com/AgenticIR-Lab/OThink-R1.

cs.AI↗

UniMM-V2X: MoE-Enhanced Multi-Level Fusion for End-to-End Cooperative Autonomous Driving

Autonomous driving holds transformative potential but remains fundamentally constrained by the limited perception and isolated decision-making with standalone intelligence. While recent multi-agent approaches introduce cooperation, they often focus merely on perception-level tasks, overlooking the alignment with downstream planning and control, or fall short in leveraging the full capacity of the recent emerging end-to-end autonomous driving. In this paper, we present UniMM-V2X, a novel end-to-end multi-agent framework that enables hierarchical cooperation across perception, prediction, and planning. At the core of our framework is a multi-level fusion strategy that unifies perception and prediction cooperation, allowing agents to share queries and reason cooperatively for consistent and safe decision-making. To adapt to diverse downstream tasks and further enhance the quality of multi-level fusion, we incorporate a Mixture-of-Experts (MoE) architecture to dynamically enhance the BEV representations. We further extend MoE into the decoder to better capture diverse motion patterns. Extensive experiments on the DAIR-V2X dataset demonstrate our approach achieves state-of-the-art (SOTA) performance with a 39.7% improvement in perception accuracy, a 7.2% reduction in prediction error, and a 33.2% improvement in planning performance compared with UniV2X, showcasing the strength of our MoE-enhanced multi-level cooperative paradigm.

cs.RO↗

History-Aware Reasoning for GUI Agents

Advances in Multimodal Large Language Models have significantly enhanced Graphical User Interface (GUI) automation. Equipping GUI agents with reliable episodic reasoning capabilities is essential for bridging the gap between users' concise task descriptions and the complexities of real-world execution. Current methods integrate Reinforcement Learning (RL) with System-2 Chain-of-Thought, yielding notable gains in reasoning enhancement. For long-horizon GUI tasks, historical interactions connect each screen to the goal-oriented episode chain, and effectively leveraging these clues is crucial for the current decision. However, existing native GUI agents exhibit weak short-term memory in their explicit reasoning, interpreting the chained interactions as discrete screen understanding, i.e., unawareness of the historical interactions within the episode. This history-agnostic reasoning challenges their performance in GUI automation. To alleviate this weakness, we propose a History-Aware Reasoning (HAR) framework, which encourages an agent to reflect on its own errors and acquire episodic reasoning knowledge from them via tailored strategies that enhance short-term memory in long-horizon interaction. The framework mainly comprises constructing a reflective learning scenario, synthesizing tailored correction guidelines, and designing a hybrid RL reward function. Using the HAR framework, we develop a native end-to-end model, HAR-GUI-3B, which alters the inherent reasoning mode from history-agnostic to history-aware, equipping the GUI agent with stable short-term memory and reliable perception of screen details. Comprehensive evaluations across a range of GUI-related benchmarks demonstrate the effectiveness and generalization of our method.

cs.AI↗

ProBench: Benchmarking GUI Agents with Accurate Process Information

With the deep integration of artificial intelligence and interactive technology, Graphical User Interface (GUI) Agent, as the carrier connecting goal-oriented natural language and real-world devices, has received widespread attention from the community. Contemporary benchmarks aim to evaluate the comprehensive capabilities of GUI agents in GUI operation tasks, generally determining task completion solely by inspecting the final screen state. However, GUI operation tasks consist of multiple chained steps while not all critical information is presented in the final few pages. Although a few research has begun to incorporate intermediate steps into evaluation, accurately and automatically capturing this process information still remains an open challenge. To address this weakness, we introduce ProBench, a comprehensive mobile benchmark with over 200 challenging GUI tasks covering widely-used scenarios. Remaining the traditional State-related Task evaluation, we extend our dataset to include Process-related Task and design a specialized evaluation method. A newly introduced Process Provider automatically supplies accurate process information, enabling presice assessment of agent's performance. Our evaluation of advanced GUI agents reveals significant limitations for real-world GUI scenarios. These shortcomings are prevalent across diverse models, including both large-scale generalist models and smaller, GUI-specific models. A detailed error analysis further exposes several universal problems, outlining concrete directions for future improvements.

cs.AI↗

Towards Scalable Web Accessibility Audit with MLLMs as Copilots

Ensuring web accessibility is crucial for advancing social welfare, justice, and equality in digital spaces, yet the vast majority of website user interfaces remain non-compliant, due in part to the resource-intensive and unscalable nature of current auditing practices. While WCAG-EM offers a structured methodology for site-wise conformance evaluation, it involves great human efforts and lacks practical support for execution at scale. In this work, we present an auditing framework, AAA, which operationalizes WCAG-EM through a human-AI partnership model. AAA is anchored by two key innovations: GRASP, a graph-based multimodal sampling method that ensures representative page coverage via learned embeddings of visual, textual, and relational cues; and MaC, a multimodal large language model-based copilot that supports auditors through cross-modal reasoning and intelligent assistance in high-effort tasks. Together, these components enable scalable, end-to-end web accessibility auditing, empowering human auditors with AI-enhanced assistance for real-world impact. We further contribute four novel datasets designed for benchmarking core stages of the audit pipeline. Extensive experiments demonstrate the effectiveness of our methods, providing insights that small-scale language models can serve as capable experts when fine-tuned.

cs.AI↗

Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness-Generalization Perspective

Graph Neural Networks (GNNs) have achieved great success but are often considered to be challenged by varying levels of homophily in graphs. Recent \textit{empirical} studies have surprisingly shown that homophilic GNNs can perform well across datasets of different homophily levels with proper hyperparameter tuning, but the underlying theory and effective architectures remain unclear. To advance GNN universality across varying homophily, we theoretically revisit GNN message passing and uncover a novel \textit{smoothness-generalization dilemma}, where increasing hops inevitably enhances smoothness at the cost of generalization. This dilemma hinders learning in high-order homophilic neighborhoods and all heterophilic ones, where generalization is critical due to complex neighborhood class distributions that are sensitive to shifts induced by noise or sparsity. To address this, we introduce the Inceptive Graph Neural Network (IGNN) built on three simple yet effective design principles, which alleviate the dilemma by enabling distinct hop-wise generalization alongside improved overall generalization with adaptive smoothness. Benchmarking against 30 baselines demonstrates IGNN's superiority and reveals notable universality in certain homophilic GNN variants. Our code and datasets are available at \href{https://github.com/galogm/IGNN}{https://github.com/galogm/IGNN}.

cs.LG↗

Joint Memory Frequency and Computing Frequency Scaling for Energy-efficient DNN Inference

Deep neural networks (DNNs) have been widely applied in diverse applications, but the problems of high latency and energy overhead are inevitable on resource-constrained devices. To address this challenge, most researchers focus on the dynamic voltage and frequency scaling (DVFS) technique to balance the latency and energy consumption by changing the computing frequency of processors. However, the adjustment of memory frequency is usually ignored and not fully utilized to achieve efficient DNN inference, which also plays a significant role in the inference time and energy consumption. In this paper, we first investigate the impact of joint memory frequency and computing frequency scaling on the inference time and energy consumption with a model-based and data-driven method. Then by combining with the fitting parameters of different DNN models, we give a preliminary analysis for the proposed model to see the effects of adjusting memory frequency and computing frequency simultaneously. Finally, simulation results in local inference and cooperative inference cases further validate the effectiveness of jointly scaling the memory frequency and computing frequency to reduce the energy consumption of devices.

cs.LG↗

Robust DNN Partitioning and Resource Allocation Under Uncertain Inference Time

In edge intelligence systems, deep neural network (DNN) partitioning and data offloading can provide real-time task inference for resource-constrained mobile devices. However, the inference time of DNNs is typically uncertain and cannot be precisely determined in advance, presenting significant challenges in ensuring timely task processing within deadlines. To address the uncertain inference time, we propose a robust optimization scheme to minimize the total energy consumption of mobile devices while meeting task probabilistic deadlines. The scheme only requires the mean and variance information of the inference time, without any prediction methods or distribution functions. The problem is formulated as a mixed-integer nonlinear programming (MINLP) that involves jointly optimizing the DNN model partitioning and the allocation of local CPU/GPU frequencies and uplink bandwidth. To tackle the problem, we first decompose the original problem into two subproblems: resource allocation and DNN model partitioning. Subsequently, the two subproblems with probability constraints are equivalently transformed into deterministic optimization problems using the chance-constrained programming (CCP) method. Finally, the convex optimization technique and the penalty convex-concave procedure (PCCP) technique are employed to obtain the optimal solution of the resource allocation subproblem and a stationary point of the DNN model partitioning subproblem, respectively. The proposed algorithm leverages real-world data from popular hardware platforms and is evaluated on widely used DNN models. Extensive simulations show that our proposed algorithm effectively addresses the inference time uncertainty with probabilistic deadline guarantees while minimizing the energy consumption of mobile devices.

cs.DC↗

FedTeddi: Temporal Drift and Divergence Aware Scheduling for Timely Federated Edge Learning

Federated edge learning (FEEL) enables collaborative model training across distributed clients over wireless networks without exposing raw data. While most existing studies assume static datasets, in real-world scenarios clients may continuously collect data with time-varying and non-independent and identically distributed (non-i.i.d.) characteristics. A critical challenge is how to adapt models in a timely yet efficient manner to such evolving data. In this paper, we propose FedTeddi, a temporal-drift-and-divergence-aware scheduling algorithm that facilitates fast convergence of FEEL under dynamic data evolution and communication resource limits. We first quantify the temporal dynamics and non-i.i.d. characteristics of data using temporal drift and collective divergence, respectively, and represent them as the Earth Mover's Distance (EMD) of class distributions for classification tasks. We then propose a novel optimization objective and develop a joint scheduling and bandwidth allocation algorithm, enabling the FEEL system to learn from new data quickly without forgetting previous knowledge. Experimental results show that our algorithm achieves higher test accuracy and faster convergence compared to benchmark methods, improving the rate of convergence by 58.4% on CIFAR-10 and 49.2% on CIFAR-100 compared to random scheduling.

cs.LG↗