arXiv subjects

Bo Ji

Publications and source records attributed to Bo Ji.

At least 19 recordsLinked to original sources

arXiv2026

HypRQ-VAE: Hyperbolic Item Indexing for Long-Tail-Aware Generative Recommender Systems

Sequential recommender systems model user behavior as item ID sequences, while recent generative methods cast recommendation as a language modeling task using large language models (LLMs). While this paradigm incorporates rich textual semantics, it introduces a fundamental mismatch: LLMs operate on text tokens, whereas recommender systems depend on discrete item indices. This misalignment often leads to hallucinations in generative recommendations. Existing methods attempt to bridge this gap by learning item vocabularies in Euclidean space, but they struggle to model the inherent long-tail distribution of real-world catalogs, where a small number of head items dominate, and a vast number of tail items reflect users' niche preferences. To address this issue, we introduce Hyperbolic Residual-Quantized Variational AutoEncoder (HypRQ-VAE), the first framework to learn item indexing in hyperbolic space. HypRQ-VAE leverages the unique properties of hyperbolic geometry, whose exponential volume expansion naturally accommodates the power law structure of user-item interactions. This allows the model to encode rich textual semantics while preserving the representational fidelity of sparse, long-tail items. Experiments on three benchmark datasets show that HypRQ-VAE significantly improves the performance of recommendation, particularly in recommending tail items. Our analysis attributes these gains to the superior capacity of hyperbolic space to model item hierarchies and sparsity in generative recommendation. Our code and data are available at: https://github.com/wulongfeng/HypRQ-VAE.

cs.IR↗

arXiv2026

Breaking Ambient Trust: In-Network Per-Process Access Control Against Lateral Movement

Enterprise networks remain vulnerable to Advanced Persistent Threats (APTs), where adversaries gain an initial foothold and move laterally across the network, accumulating access permissions hop by hop to reach critical targets. Existing network defenses cannot track user movement at the process level across the network; instead, they grant ambient trust to all processes within a host. As a result, once a host is compromised, malicious processes inherit the victim's permissions, thereby expanding the attacker's access scope and enabling further lateral movement. To address this gap, we present NetZone, an in-network access control that confines each user process to a fixed access scope that persists as the user moves across the network. NetZone introduces a new abstraction, called AccessScope, which represents a lightweight access capability bound to the user's processes. Each AccessScope encodes the set of hosts a user identity is authorized to access and is embedded in the process's outgoing network traffic for validation before reaching its destination. As users pivot across hosts, AccessScope propagates with their traffic, rebinds to the receiving process, and persists across hosts. This ensures that regardless of network location, the user's processes are consistently governed by their bound AccessScope and their access permissions remain unchanged. To handle the high volume of network traffic generated by processes, we develop a data-plane co-design that integrates programmable switches with eBPF. NetZone employs a set of in-network optimizations and lightweight AccessScope persistence techniques to inspect the embedded AccessScope on the fly, enabling line-rate processing of high traffic volumes with negligible latency overhead. Our extensive evaluations show that NetZone can effectively defend against sophisticated attack scenarios without introducing noticeable overhead.

cs.CR↗

arXiv2026

EvaluatAR: A Cross-Device Evaluation Framework for Rapid Prototyping of Bystander PETs in AR

Augmented Reality (AR) headsets continuously sense their surroundings, capturing nearby bystanders and raising privacy risks. Visual bystander privacy-enhancing technologies (PETs) mitigate this risk by detecting bystanders in egocentric scene views and applying privacy transformations (e.g., obfuscation). However, traditional PET evaluation is human-dependent, high-overhead, and device-specific, making it difficult to reproduce across devices. We present EvaluatAR, a cross-device evaluation framework for rapid prototyping at the early stage of PET evaluation. Our framework enables controlled replication of experimental conditions by standardizing PET inputs (sensor data and visual stimuli) and outputs through a record-replay workflow. We validate EvaluatAR through three case studies on HoloLens 2, Magic Leap 2, and Meta Quest 3 across implicit (continuous, context-driven) and explicit (intent-driven) PETs: (1) cross-device replay of inputs to a PET to reveal device-specific privacy-performance trade-offs; (2) generalizability of the same framework workflow across implicit and explicit PET design categories; and (3) replay of privacy-relevant edge cases to diagnose failures and validate PET modifications, yielding an improvement over the state-of-the-art baseline. These results demonstrate EvaluatAR's support for rapid, iterative PET development to advance reproducible cross-device evaluation of bystander PETs at a critical moment in the emergence of ubiquitous AR.

cs.CR↗

arXiv2026

EyeSpy: Inferring Eye Gaze via Side-Channel Attacks Against Foveated Rendering

While eye tracking provides valuable capabilities for virtual reality, such as gaze interaction and dynamic foveated rendering (DFR), eye-tracking data can inadvertently reveal sensitive user information if not properly protected. Current protections, such as adding permission prompts or gatekeeping gaze data, are insufficient on DFR-enabled systems because gaze data is used internally to drive DFR. When DFR is implemented, objects in the fovea (i.e., immediate gaze area) incur a higher GPU workload than those in the periphery. This gaze-contingent workload creates a novel side channel, which can be leveraged to reconstruct gaze positions. Specifically, we design a novel attack that sweeps imperceptible high-cost objects (HCOs) across the user's field of view and logs rendering performance metrics (e.g., frame rate or frame time) commonly exposed through standard game engines. Then, we correlate variation in these metrics (caused by HCO-foveal overlap) with the known HCOs' positions to infer gaze coordinates directly without using eye-tracking APIs. Our experimental results show that mean gaze prediction errors (1.1-4.4 degrees) across the Meta Quest Pro, Varjo XR-4, and desktop platforms are comparable to typical eye-tracker accuracy. We demonstrate that the attack generalizes across various hardware platforms, standard game engines, and foveated rendering pipelines. Finally, we design defense mechanisms based on supervised and unsupervised detectors that can flag the attack reliably (F1 of 0.99) over short time windows.

cs.HC↗

arXiv2026

EyeCue: Driver Cognitive Distraction Detection via Gaze-Empowered Egocentric Video Understanding

Driver cognitive distraction is a major cause of road collisions and remains difficult to detect. Unlike manual or visual distraction, cognitive distraction is diverted by thoughts unrelated to driving, even when the driver appears visually attentive and exhibits no explicit physical movements. In this work, we propose EyeCue, a gaze-empowered egocentric video understanding framework, to detect driver cognitive distraction. A key insight is that cognitive distraction manifests in the interaction between eye gaze and visual context. To capture this interaction, EyeCue integrates eye gaze with egocentric video to enable context-aware modeling of the driver's attention over time. Furthermore, to tackle the limited scale and diversity of existing datasets, we introduce CogDrive, a comprehensive multi-scenario dataset that augments four existing driving datasets with cognitive distraction annotations. Through extensive evaluations on CogDrive, we show that EyeCue achieves the highest accuracy of 74.38%, outperforming 11 baselines from 6 model families by over 7%. Notably, EyeCue can achieve an accuracy of over 70% across various driving scenarios (different road types, times of day, and weather conditions) with strong generalizability. These results highlight the importance of modeling gaze-context interactions and the effectiveness of cross-modal interaction modeling for multimodal cognitive distraction detection. Our codes and CogDrive dataset resources are available at https://github.com/langzhang2000/EyeCue.

cs.CV↗

arXiv2026

WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching

As Large Language Models (LLMs) become increasingly accessible to end users, an ever-growing number of inference requests are initiated from edge devices and computed on centralized GPU clusters. However, the resulting exponential growth in computation workload is placing significant strain on data centers, while edge devices remain largely underutilized, leading to imbalanced workloads and resource inefficiency across the network. Integrating edge devices into the LLM inference process via speculative decoding helps balance the workload between the edge and the cloud, while maintaining lossless prediction accuracy. In this paper, we identify and formalize two critical bottlenecks that limit the efficiency and scalability of distributed speculative LLM serving: Wasted Drafting Time and Verification Interference. To address these challenges, we propose WISP, an efficient and SLO-aware distributed LLM inference system that consists of an intelligent speculation controller, a verification time estimator, and a verification batch scheduler. These components collaboratively enhance drafting efficiency and optimize verification request scheduling on the server. Extensive numerical results show that WISP improves system capacity by up to 2.1x and 4.1x, and increases system goodput by up to 1.94x and 3.7x, compared to centralized serving and SLED, respectively.

cs.DC↗

arXiv2025

Optimizing Resource Allocation for Geographically-Distributed Inference by Large Language Models

Large language models have demonstrated extraordinary performance in many AI tasks but are expensive to use, even after training, due to their requirement of high-end GPUs. Recently, a distributed system called PETALS was developed to lower the barrier for deploying LLMs by splitting the model blocks across multiple servers with low-end GPUs distributed over the Internet, which was much faster than swapping the model parameters between the GPU memory and other cheaper but slower local storage media. However, the performance of such a distributed system critically depends on the resource allocation, and how to do so optimally remains unknown. In this work, we present the first systematic study of the resource allocation problem in distributed LLM inference, with focus on two important decisions: block placement and request routing. Our main results include: experimentally validated performance models that can predict the inference performance under given block placement and request routing decisions, a formulation of the offline optimization of block placement and request routing as a mixed integer linear programming problem together with the NP-hardness proof and a polynomial-complexity algorithm with guaranteed performance, and an adaptation of the offline algorithm for the online setting with the same performance guarantee under bounded load. Through both experiments and experimentally-validated simulations, we have verified that the proposed solution can substantially reduce the inference time compared to the state-of-the-art solution in diverse settings with geographically-distributed servers. As a byproduct, we have also developed a light-weighted CPU-only simulator capable of predicting the performance of distributed LLM inference on GPU servers, which can evaluate large deployments and facilitate future research for researchers with limited GPU access.

cs.DC↗

arXiv2025

iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inference

Large Language Model (LLM) agent systems have advanced rapidly, driven by their strong generalization in zero-shot settings. To further enhance reasoning and accuracy on complex tasks, Multi-Agent Debate (MAD) has emerged as a promising framework that engages multiple LLM agents in structured debates to encourage diverse reasoning. However, triggering MAD for every query is inefficient, as it incurs substantial computational (token) cost and may even degrade accuracy by overturning correct single-agent answers. To address these limitations, we propose intelligent Multi-Agent Debate (iMAD), a token-efficient framework that selectively triggers MAD only when it is likely to be beneficial (i.e., correcting an initially wrong answer). To achieve this goal, iMAD learns generalizable model behaviors to make accurate debate decisions. Specifically, iMAD first prompts a single agent to produce a structured self-critique response, from which we extract 41 interpretable linguistic and semantic features capturing hesitation cues. Then, iMAD uses a lightweight debate-decision classifier, trained using our proposed FocusCal loss, to determine whether to trigger MAD, enabling robust debate decisions without test dataset-specific tuning. Through extensive experiments using six (visual) question answering datasets against five competitive baselines, we have shown that iMAD significantly reduces token usage (by up to 92%) while also improving final answer accuracy (by up to 13.5%).

cs.CL↗

arXiv2025

Odin: Effective End-to-End SLA Decomposition for 5G/6G Network Slicing via Online Learning

Network slicing plays a crucial role in realizing 5G/6G advances, enabling diverse Service Level Agreement (SLA) requirements related to latency, throughput, and reliability. Since network slices are deployed end-to-end (E2E), across multiple domains including access, transport, and core networks, it is essential to efficiently decompose an E2E SLA into domain-level targets, so that each domain can provision adequate resources for the slice. However, decomposing SLAs is highly challenging due to the heterogeneity of domains, dynamic network conditions, and the fact that the SLA orchestrator is oblivious to the domain's resource optimization. In this work, we propose Odin, a Bayesian Optimization-based solution that leverages each domain's online feedback for provably-efficient SLA decomposition. Through theoretical analyses and rigorous evaluations, we demonstrate that Odin's E2E orchestrator can achieve up to 45% performance improvement in SLA satisfaction when compared with baseline solutions whilst reducing overall resource costs even in the presence of noisy feedback from the individual domains.

cs.NI↗

arXiv2025

Modulation Instability-Induced Multimode Squeezing in Quadratic Frequency Combs

Lithium niobate (LN) microring resonators, characterized by an exceptionally high second-order nonlinear coefficient and superior electro-optic tunability, serve as an outstanding platform for the precise control of integrated quantum frequency combs (QFCs). In this study, we introduce a bipartite entanglement criterion to investigate the pairwise entanglement characteristics of QFCs generated via the spontaneous parametric down-conversion (SPDC) process in lithium niobate microring resonators operating below threshold. Furthermore, we propose a universal framework for analyzing multimode squeezing in quadratic frequency combs, enabling the realization of ultrabroadband and high-degree multimode squeezing. We further reveal the underlying physical mechanism: modulation instability (MI), regulated by temporal walk-off control, not only enables the formation of frequency combs but also induces multimode squeezing in the corresponding resonant modes. This study uncovers the previously unexplored role of on-chip multimode squeezing in quadratic frequency combs while facilitating collective noise suppression across multiple modes, thus holding substantial potential for advancing quantum precision measurement and quantum information processing.

quant-ph↗

arXiv2025

Multimodal Remote Inference

We consider a remote inference system with multiple modalities, where a multimodal machine learning (ML) model performs real-time inference using features collected from remote sensors. When sensor observations evolve dynamically over time, fresh features are critical for inference tasks. However, timely delivery of features from all modalities is often infeasible under limited network resources. To address this challenge, we formulate a multimodal scheduling problem to minimize the ML model's inference error. We model this error as a general function of the Age of Information (AoI) vector, where AoI quantifies data freshness. We cast the problem as a semi-Markov decision process (SMDP) and derive an equivalent reformulation with a reduced state set. We then show that the problem has fundamentally different chain structures in the two-modality and multi-modality cases. For the two-modality case, we prove that the optimal policy has an index-based threshold structure. For the general multi-modality case (i.e., with more than two modalities), we develop the optimal error-aware switching-and-transmission policy (EAST), which is computed using a multichain policy iteration algorithm (MPI). To further reduce complexity, we also develop two low-complexity policies under special settings: the error-aware transmission policy (EAT) and the fixed threshold policy (FT). Numerical results from three case studies show that the proposed policies outperform several simple heuristics, including round-robin, greedy, and uniform random policies. In particular, EAST reduces the inference error by up to 44.8% compared with the best baseline in each case. In the five-modality case, EAT and FT reduce computation time by 6.6$\times$ and 3000$\times$, respectively, relative to EAST, while increasing the inference error by 20.2% and 38.6%, respectively.

cs.LG↗

arXiv2025

Rethinking Privacy Indicators in Extended Reality: Multimodal Design for Situationally Impaired Bystanders

As Extended Reality (XR) devices become increasingly prevalent in everyday settings, they raise significant privacy concerns for bystanders: individuals in the vicinity of an XR device during its use, whom the device sensors may accidentally capture. Current privacy indicators, such as small LEDs, often presume that bystanders are attentive enough to interpret the privacy signals. However, these cues can be easily overlooked when bystanders are distracted or have limited vision. We define such individuals as situationally impaired bystanders. This study explores XR privacy indicator designs that are effective for situationally impaired bystanders. A focus group with eight participants was conducted to design five novel privacy indicators. We evaluated these designs through a user study with seven additional participants. Our results show that visual-only indicators, typical in commercial XR devices, received low ratings for perceived usefulness in impairment scenarios. In contrast, multimodal indicators were preferred in privacy-sensitive scenarios with situationally impaired bystanders. Ultimately, our results highlight the need to move toward adaptable, multimodal, and situationally aware designs that effectively support bystander privacy in everyday XR environments.

cs.HC↗

arXiv2025

S2M3: Split-and-Share Multi-Modal Models for Distributed Multi-Task Inference on the Edge

With the advancement of Artificial Intelligence (AI) towards multiple modalities (language, vision, speech, etc.), multi-modal models have increasingly been used across various applications (e.g., visual question answering or image generation/captioning). Despite the success of AI as a service for multi-modal applications, it relies heavily on clouds, which are constrained by bandwidth, latency, privacy concerns, and unavailability under network or server failures. While on-device AI becomes popular, supporting multiple tasks on edge devices imposes significant resource challenges. To address this, we introduce S2M3, a split-and-share multi-modal architecture for multi-task inference on edge devices. Inspired by the general-purpose nature of multi-modal models, which are composed of multiple modules (encoder, decoder, classifier, etc.), we propose to split multi-modal models at functional-level modules; and then share common modules to reuse them across tasks, thereby reducing resource usage. To address cross-model dependency arising from module sharing, we propose a greedy module-level placement with per-request parallel routing by prioritizing compute-intensive modules. Through experiments on a testbed consisting of 14 multi-modal models across 5 tasks and 10 benchmarks, we demonstrate that S2M3 can reduce memory usage by up to 50% and 62% in single-task and multi-task settings, respectively, without sacrificing accuracy. Furthermore, S2M3 achieves optimal placement in 89 out of 95 instances (93.7%) while reducing inference latency by up to 56.9% on resource-constrained devices, compared to cloud AI.

cs.DC↗

arXiv2025

MARVEL: An End-to-End Framework for Generating Model-Class Aware Custom RISC-V Extensions for Lightweight AI

Deploying deep neural networks (DNNs) on resource-constrained IoT devices remains a challenging problem, often requiring hardware modifications tailored to individual AI models. Existing accelerator-generation tools, such as AMD's FINN, do not adequately address extreme resource limitations faced by IoT endpoints operating in bare-metal environments without an operating system (OS). To overcome these constraints, we propose MARVEL-an automated, end-to-end framework that generates custom RISC-V ISA extensions tailored to specific DNN model classes, with a primary focus on convolutional neural networks (CNNs). The proposed method profiles high-level DNN representations in Python and generates an ISA-extended RISC-V core with associated compiler tools for efficient deployment. The flow leverages (1) Apache TVM for translating high-level Python-based DNN models into optimized C code, (2) Synopsys ASIP Designer for identifying compute-intensive kernels, modeling, and generating a custom RISC-V and (3) Xilinx Vivado for FPGA implementation. Beyond a model class specific RISC-V, our approach produces an optimized bare-metal C implementation, eliminating the need for an OS or extensive software dependencies. Unlike conventional deployment pipelines relying on TensorFlow/PyTorch runtimes, our solution enables seamless execution in highly resource-constrained environments. We evaluated the flow on popular DNN models such as LeNet-5*, MobileNetV1, ResNet50, VGG16, MobileNetV2 and DenseNet121 using the Synopsys trv32p3 RISC-V core as a baseline. Results show a 2x speedup in inference and upto 2x reduction in energy per inference at a 28.23% area overhead when implemented on an AMD Zynq UltraScale+ ZCU104 FPGA platform.

cs.AR↗

arXiv2025

P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices

Split Learning (SL) is an emerging privacy-preserving machine learning technique that enables resource constrained edge devices to participate in model training by partitioning a model into client-side and server-side sub-models. While SL reduces computational overhead on edge devices, it encounters significant challenges in heterogeneous environments where devices vary in computing resources, communication capabilities, environmental conditions, and privacy requirements. Although recent studies have explored heterogeneous SL frameworks that optimize split points for devices with varying resource constraints, they often neglect personalized privacy requirements and local model customization under varying environmental conditions. To address these limitations, we propose P3SL, a Personalized Privacy-Preserving Split Learning framework designed for heterogeneous, resource-constrained edge device systems. The key contributions of this work are twofold. First, we design a personalized sequential split learning pipeline that allows each client to achieve customized privacy protection and maintain personalized local models tailored to their computational resources, environmental conditions, and privacy needs. Second, we adopt a bi-level optimization technique that empowers clients to determine their own optimal personalized split points without sharing private sensitive information (i.e., computational resources, environmental conditions, privacy requirements) with the server. This approach balances energy consumption and privacy leakage risks while maintaining high model accuracy. We implement and evaluate P3SL on a testbed consisting of 7 devices including 4 Jetson Nano P3450 devices, 2 Raspberry Pis, and 1 laptop, using diverse model architectures and datasets under varying environmental conditions.

cs.LG↗

arXiv2025

Polymorph: Energy-Efficient Multi-Label Classification for Video Streams on Embedded Devices

Real-time multi-label video classification on embedded devices is constrained by limited compute and energy budgets. Yet, video streams exhibit structural properties such as label sparsity, temporal continuity, and label co-occurrence that can be leveraged for more efficient inference. We introduce Polymorph, a context-aware framework that activates a minimal set of lightweight Low Rank Adapters (LoRA) per frame. Each adapter specializes in a subset of classes derived from co-occurrence patterns and is implemented as a LoRA weight over a shared backbone. At runtime, Polymorph dynamically selects and composes only the adapters needed to cover the active labels, avoiding full-model switching and weight merging. This modular strategy improves scalability while reducing latency and energy overhead. Polymorph achieves 40% lower energy consumption and improves mAP by 9 points over strong baselines on the TAO dataset. Polymorph is open source at https://github.com/inference-serving/polymorph/.

cs.CV↗

arXiv2025

QPART: Adaptive Model Quantization and Dynamic Workload Balancing for Accuracy-aware Edge Inference

As machine learning inferences increasingly move to edge devices, adapting to diverse computational capabilities, hardware, and memory constraints becomes more critical. Instead of relying on a pre-trained model fixed for all future inference queries across diverse edge devices, we argue that planning an inference pattern with a request-specific model tailored to the device's computational capacity, accuracy requirements, and time constraints is more cost-efficient and robust to diverse scenarios. To this end, we propose an accuracy-aware and workload-balanced inference system that integrates joint model quantization and inference partitioning. In this approach, the server dynamically responds to inference queries by sending a quantized model and adaptively sharing the inference workload with the device. Meanwhile, the device's computational power, channel capacity, and accuracy requirements are considered when deciding. Furthermore, we introduce a new optimization framework for the inference system, incorporating joint model quantization and partitioning. Our approach optimizes layer-wise quantization bit width and partition points to minimize time consumption and cost while accounting for varying accuracy requirements of tasks through an accuracy degradation metric in our optimization model. To our knowledge, this work represents the first exploration of optimizing quantization layer-wise bit-width in the inference serving system, by introducing theoretical measurement of accuracy degradation. Simulation results demonstrate a substantial reduction in overall time and power consumption, with computation payloads decreasing by over 80% and accuracy degradation kept below 1%.

cs.DC↗

arXiv2025

RLPR: Extrapolating RLVR to General Domains without Verifiers

Reinforcement Learning with Verifiable Rewards (RLVR) demonstrates promising potential in advancing the reasoning capabilities of LLMs. However, its success remains largely confined to mathematical and code domains. This primary limitation stems from the heavy reliance on domain-specific verifiers, which results in prohibitive complexity and limited scalability. To address the challenge, our key observation is that LLM's intrinsic probability of generating a correct free-form answer directly indicates its own evaluation of the reasoning reward (i.e., how well the reasoning process leads to the correct answer). Building on this insight, we propose RLPR, a simple verifier-free framework that extrapolates RLVR to broader general domains. RLPR uses the LLM's own token probability scores for reference answers as the reward signal and maximizes the expected reward during training. We find that addressing the high variance of this noisy probability reward is crucial to make it work, and propose prob-to-reward and stabilizing methods to ensure a precise and stable reward from LLM intrinsic probabilities. Comprehensive experiments in four general-domain benchmarks and three mathematical benchmarks show that RLPR consistently improves reasoning capabilities in both areas for Gemma, Llama, and Qwen based models. Notably, RLPR outperforms concurrent VeriFree by 7.6 points on TheoremQA and 7.5 points on Minerva, and even surpasses strong verifier-model-dependent approaches General-Reasoner by 1.6 average points across seven benchmarks.

cs.LG↗