arXiv subjects

Weijia Liu

Publications and source records attributed to Weijia Liu.

13 recordsLinked to original sources

arXiv2026

Bumblebee: Interleaved Mixed-Layer Building Blocks for Large-Scale Recommendation Systems

Recommendation systems have undergone significant transformations in the past years. The transition from traditional feature interaction modules to generative next-action prediction has pushed the boundaries of personalized content. Developments have largely evolved along two separate tracks. Sequence modeling approaches on the one hand and feature interaction methods on the other. In this paper, we introduce Bumblebee, a recommendation architecture that addresses the lack of interaction between the two directions through an interleaved, stackable block design. Each block implements a micro-pipeline of layers combining sequence personalization, attention-based encoding, and feature crossing into a self-contained unit. Every block produces a joint representation of both feature modalities which is consumed by the next block in the sequence. This mechanism encourages early and repeated mixture of modalities and enriches downstream features with additional contextual information. Residual connections between blocks create cross-modal information pathways and yield additional predictive performance without adding additional parameters. Blocks can be specialized by selectively dropping components, enabling flexible trade-offs between quality and throughput. We evaluate our approach on large-scale industrial data and show consistent improvements over comparable baseline models across several classification and regression tasks. Furthermore, we conduct ablation studies to confirm that the interleaved composition itself is the primary driver of these improvements. Our results suggest that interleaving heterogeneous functional units, rather than composing deep stacks, is a promising paradigm for future-generation recommendation architectures.

cs.IR↗

arXiv2026

LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation

Language-conditioned goal navigation (LGN) requires agents to locate user-specified targets without step-by-step guidance. However, existing benchmarks largely focus on category-level goals or rely on instance descriptions generated by vision-language models (VLMs), which often contain ambiguities and semantic errors, limiting systematic and reliable evaluation. We introduce HieraNav, an open-vocabulary LGN task with goals specified at four hierarchical semantic levels: scene, room, region, and instance. To this end, we present Language as a Map (LangMap), to our knowledge the first real-world 3D indoor navigation benchmark with human-verified semantic annotations to support tasks across all four goal levels. LangMap provides region labels and discriminative region and instance descriptions covering 414 object categories, produced through a rigorous contrastive annotation protocol comparing same-scene regions and instances, and contains over 18K tasks. Each target is paired with concise and detailed descriptions, enabling evaluation across instruction styles. Quantitative and qualitative analyses validate our annotation quality; notably, our instance descriptions outperform GOAT-Bench annotations by 23 percentage points in text-to-view matching. We further introduce PlaNaVid, a strong RGB-only baseline that combines Bounded Diverse Memory (BDM) with high-level planning to prime a reactive policy for multi-goal navigation. PlaNaVid achieves top-tier success rates without depth, 3D scene representations, or object masks. Further analysis shows that memory and richer context boost performance, while long-tailed categories, small objects, distant targets, and multi-goal completion remain open challenges. The benchmark is available at https://bo-miao.github.io/LangMap

cs.CV↗

arXiv2026

Enhanced Self-Learning with Epistemologically-Informed LLM Dialogue

Large Language Models (LLMs) have advanced self-learning tools, enabling more personalized interactions. However, learners struggle to engage in meaningful dialogue and process complex information. To alleviate this, we incorporate epistemological frameworks within an LLM-based approach to self-learning, reducing the cognitive load on learners and fostering deeper engagement and holistic understanding. Through a formative study (N=26), we identified epistemological differences in self-learner interaction patterns. Building upon these findings, we present \textit{CausaDisco}, a dialogue-based interactive system that integrates Aristotle's \textit{Four Causes} framework into LLM prompts to enhance cognitive support for self-learning. This approach guides learners' self-learning journeys by automatically generating coherent and contextually appropriate follow-up questions. A controlled study (N=36) demonstrated that, compared to baseline, \textit{CausaDisco} fostered more engaging interactions, inspired sophisticated exploration, and facilitated multifaceted perspectives. This research contributes to HCI by expanding the understanding of LLMs as educational agents and providing design implications for this emerging class of tools.

cs.HC↗

arXiv2025

Denoise-then-Retrieve: Text-Conditioned Video Denoising for Video Moment Retrieval

Current text-driven Video Moment Retrieval (VMR) methods encode all video clips, including irrelevant ones, disrupting multimodal alignment and hindering optimization. To this end, we propose a denoise-then-retrieve paradigm that explicitly filters text-irrelevant clips from videos and then retrieves the target moment using purified multimodal representations. Following this paradigm, we introduce the Denoise-then-Retrieve Network (DRNet), comprising Text-Conditioned Denoising (TCD) and Text-Reconstruction Feedback (TRF) modules. TCD integrates cross-attention and structured state space blocks to dynamically identify noisy clips and produce a noise mask to purify multimodal video representations. TRF further distills a single query embedding from purified video representations and aligns it with the text embedding, serving as auxiliary supervision for denoising during training. Finally, we perform conditional retrieval using text embeddings on purified video representations for accurate VMR. Experiments on Charades-STA and QVHighlights demonstrate that our approach surpasses state-of-the-art methods on all metrics. Furthermore, our denoise-then-retrieve paradigm is adaptable and can be seamlessly integrated into advanced VMR models to boost performance.

cs.CV↗

arXiv2024

A Distributionally Robust Optimization Framework for Stochastic Assessment of Power System Flexibility in Economic Dispatch

Given the complexity of power systems, particularly the high-dimensional variability of net loads, accurately depicting the entire operational range of net loads poses a challenge. To address this, recent methodologies have sought to gauge the maximum range of net load uncertainty across all buses. In this paper, we consider the stochastic nature of the net load and introduce a distributionally robust optimization framework that assesses system flexibility stochastically, accommodating a minimal extent of system violations. We verify the proposed method by solving the flexibility of the real-time economic dispatch problem on four IEEE standard test systems. Compared to traditional deterministic flexibility evaluations, our approach consistently yields less conservative flexibility outcomes.

math.OC↗

arXiv2024

Context-Enhanced Video Moment Retrieval with Large Language Models

Current methods for Video Moment Retrieval (VMR) struggle to align complex situations involving specific environmental details, character descriptions, and action narratives. To tackle this issue, we propose a Large Language Model-guided Moment Retrieval (LMR) approach that employs the extensive knowledge of Large Language Models (LLMs) to improve video context representation as well as cross-modal alignment, facilitating accurate localization of target moments. Specifically, LMR introduces a context enhancement technique with LLMs to generate crucial target-related context semantics. These semantics are integrated with visual features for producing discriminative video representations. Finally, a language-conditioned transformer is designed to decode free-form language queries, on the fly, using aligned video representations for moment retrieval. Extensive experiments demonstrate that LMR achieves state-of-the-art results, outperforming the nearest competitor by up to 3.28\% and 4.06\% on the challenging QVHighlights and Charades-STA benchmarks, respectively. More importantly, the performance gains are significantly higher for localization of complex queries.

cs.CV↗

arXiv2024

Differentially Private Average Consensus with Improved Accuracy-Privacy Trade-off

This paper studies the average consensus problem with differential privacy of initial states, for which it is widely recognized that there is a trade-off between the mean-square computation accuracy and privacy level. Considering the trade-off gap between the average consensus algorithm and the centralized averaging approach with differential privacy, we propose a distributed shuffling mechanism based on the Paillier cryptosystem to generate correlated zero-sum randomness. By randomizing each local privacy-sensitive initial state with an i.i.d. Gaussian noise and the output of the mechanism using Gaussian noises, it is shown that the resulting average consensus algorithm can eliminate the gap in the sense that the accuracy-privacy trade-off of the centralized averaging approach with differential privacy can be almost recovered by appropriately designing the variances of the added noises. We also extend such a design framework with Gaussian noises to the one using Laplace noises, and show that the improved privacy-accuracy trade-off is preserved.

eess.SY↗

arXiv2024

Distributed Least-Squares Optimization Solvers with Differential Privacy

This paper studies the distributed least-squares optimization problem with differential privacy requirement of local cost functions, for which two differentially private distributed solvers are proposed. The first is established on the distributed gradient tracking algorithm, by appropriately perturbing the initial values and parameters that contain the privacy-sensitive data with Gaussian and truncated Laplacian noises, respectively. Rigorous proofs are established to show the achievable trade-off between the (ε, δ)-differential privacy and the computation accuracy. The second solver is established on the combination of the distributed shuffling mechanism and the average consensus algorithm, which enables each agent to obtain a noisy version of parameters characterizing the global gradient. As a result, the least-squares optimization problem can be eventually solved by each agent locally in such a way that any given (ε, δ)-differential privacy requirement can be preserved while the solution may be computed with the accuracy independent of the network size, which makes the latter more suitable for large-scale distributed least-squares problems. Numerical simulations are presented to show the effectiveness of both solvers.

math.OC↗

arXiv2024

Curriculum-based Reinforcement Learning for Distribution System Critical Load Restoration

This paper focuses on the critical load restoration problem in distribution systems following major outages. To provide fast online response and optimal sequential decision-making support, a reinforcement learning (RL) based approach is proposed to optimize the restoration. Due to the complexities stemming from the large policy search space, renewable uncertainty, and nonlinearity in a complex grid control problem, directly applying RL algorithms to train a satisfactory policy requires extensive tuning to be successful. To address this challenge, this paper leverages the curriculum learning (CL) technique to design a training curriculum involving a simpler steppingstone problem that guides the RL agent to learn to solve the original hard problem in a progressive and more effective manner. We demonstrate that compared with direct learning, CL facilitates controller training to achieve better performance. To study realistic scenarios where renewable forecasts used for decision-making are in general imperfect, the experiments compare the trained RL controllers against two model predictive controllers (MPCs) using renewable forecasts with different error levels and observe how these controllers can hedge against the uncertainty. Results show that RL controllers are less susceptible to forecast errors than the baseline MPCs and can provide a more reliable restoration process.

eess.SY↗

arXiv2024

Query-Based Knowledge Sharing for Open-Vocabulary Multi-Label Classification

Identifying labels that did not appear during training, known as multi-label zero-shot learning, is a non-trivial task in computer vision. To this end, recent studies have attempted to explore the multi-modal knowledge of vision-language pre-training (VLP) models by knowledge distillation, allowing to recognize unseen labels in an open-vocabulary manner. However, experimental evidence shows that knowledge distillation is suboptimal and provides limited performance gain in unseen label prediction. In this paper, a novel query-based knowledge sharing paradigm is proposed to explore the multi-modal knowledge from the pretrained VLP model for open-vocabulary multi-label classification. Specifically, a set of learnable label-agnostic query tokens is trained to extract critical vision knowledge from the input image, and further shared across all labels, allowing them to select tokens of interest as visual clues for recognition. Besides, we propose an effective prompt pool for robust label embedding, and reformulate the standard ranking learning into a form of classification to allow the magnitude of feature vectors for matching, which both significantly benefit label recognition. Experimental results show that our framework significantly outperforms state-of-the-art methods on zero-shot task by 5.9% and 4.5% in mAP on the NUS-WIDE and Open Images, respectively.

cs.CV↗

arXiv2023

Text as Image: Learning Transferable Adapter for Multi-Label Classification

Pre-trained vision-language models have notably accelerated progress of open-world concept recognition. Their impressive zero-shot ability has recently been transferred to multi-label image classification via prompt tuning, enabling to discover novel labels in an open-vocabulary manner. However, this paradigm suffers from non-trivial training costs, and becomes computationally prohibitive for a large number of candidate labels. To address this issue, we note that vision-language pre-training aligns images and texts in a unified embedding space, making it potential for an adapter network to identify labels in visual modality while be trained in text modality. To enhance such cross-modal transfer ability, a simple yet effective method termed random perturbation is proposed, which enables the adapter to search for potential visual embeddings by perturbing text embeddings with noise during training, resulting in better performance in visual modality. Furthermore, we introduce an effective approach to employ large language models for multi-label instruction-following text generation. In this way, a fully automated pipeline for visual label recognition is developed without relying on any manual data. Extensive experiments on public benchmarks show the superiority of our method in various multi-label classification tasks.

cs.CV↗

arXiv2019

Community Detection Across Multiple Social Networks based on Overlapping Users

With the rapid development of Internet technology, online social networks (OSNs) have got fast development and become increasingly popular. Meanwhile, the research works across multiple social networks attract more and more attention from researchers, and community detection is an important one across OSNs for online security problems, such as the user behavior analysis and abnormal community discovery. In this paper, a community detection method is proposed across multiple social networks based on overlapping users. First, the concept of overlapping users is defined, then an algorithm CMN NMF is designed to discover the stub communities from overlapping users based on the social relevance. After that, we extend each stub community in different social networks by adding the users with strong similarity, and in the end different communities are excavated out across networks. Experimental results show the advantage on effectiveness of our method over other methods under real data sets.

cs.SI↗

arXiv2019

An Accurate Bilinear Cavern Model for Compressed Air Energy Storage

Compressed air energy storage is suitable for large-scale electrical energy storage, which is important for integrating renewable energy sources into electric power systems. A typical compressed air energy storage plant consists of compressors, expanders, caverns, and a motor/generator set. Current cavern models used for compressed air energy storage are either accurate but highly nonlinear or linear but inaccurate. The application of highly nonlinear cavern models in power system optimization problems renders them computationally challenging to solve. In this regard, an accurate bilinear cavern model for compressed air energy storage is proposed in this paper. The charging and discharging processes in a cavern are divided into several real/virtual states. The first law of thermodynamics and ideal gas law are then utilized to derive a cavern model, i.e., a model for the variation of temperature and pressure in these processes. Thereafter, the heat transfer between the air in the cavern and the cavern wall is considered and integrated into the cavern model. By subsequently eliminating several negligible terms, the cavern model reduces to a bilinear model. The accuracy of the bilinear cavern model is verified via comparison with both an accurate nonlinear model and two sets of field-measured data. The bilinear cavern model can be easily linearized and is then suitable for integration into optimization problems considering compressed air energy storage. This is verified via comparatively solving a self-scheduling problem of compressed air energy storage using different cavern models.

eess.SP↗