arXiv subjects

Lina Yao

Publications and source records attributed to Lina Yao.

At least 73 records · Page 4Linked to original sources

arXiv2025

Maximum In-Support Return Modeling for Dynamic Recommendation with Language Model Prior

Reinforcement Learning-based recommender systems (RLRS) offer an effective way to handle sequential recommendation tasks but often face difficulties in real-world settings, where user feedback data can be sub-optimal or sparse. In this paper, we introduce MDT4Rec, an offline RLRS framework that builds on the Decision Transformer (DT) to address two major challenges: learning from sub-optimal histories and representing complex user-item interactions. First, MDT4Rec shifts the trajectory stitching procedure from the training phase to action inference, allowing the system to shorten its historical context when necessary and thereby ignore negative or unsuccessful past experiences. Second, MDT4Rec initializes DT with a pre-trained large language model (LLM) for knowledge transfer, replaces linear embedding layers with Multi-Layer Perceptrons (MLPs) for more flexible representations, and employs Low-Rank Adaptation (LoRA) to efficiently fine-tune only a small subset of parameters. We evaluate MDT4Rec on five public datasets and in an online simulation environment, demonstrating that it outperforms existing methods.

cs.IR↗

arXiv2025

GUI Agents: A Survey

Graphical User Interface (GUI) agents, powered by Large Foundation Models, have emerged as a transformative approach to automating human-computer interaction. These agents autonomously interact with digital systems or software applications via GUIs, emulating human actions such as clicking, typing, and navigating visual elements across diverse platforms. Motivated by the growing interest and fundamental importance of GUI agents, we provide a comprehensive survey that categorizes their benchmarks, evaluation metrics, architectures, and training methods. We propose a unified framework that delineates their perception, reasoning, planning, and acting capabilities. Furthermore, we identify important open challenges and discuss key future directions. Finally, this work serves as a basis for practitioners and researchers to gain an intuitive understanding of current progress, techniques, benchmarks, and critical open problems that remain to be addressed.

cs.AI↗

arXiv2025

Self-Supervised Cross-Modal Learning for Image-to-Point Cloud Registration

Bridging 2D and 3D sensor modalities is critical for robust perception in autonomous systems. However, image-to-point cloud (I2P) registration remains challenging due to the semantic-geometric gap between texture-rich but depth-ambiguous images and sparse yet metrically precise point clouds, as well as the tendency of existing methods to converge to local optima. To overcome these limitations, we introduce CrossI2P, a self-supervised framework that unifies cross-modal learning and two-stage registration in a single end-to-end pipeline. First, we learn a geometric-semantic fused embedding space via dual-path contrastive learning, enabling annotation-free, bidirectional alignment of 2D textures and 3D structures. Second, we adopt a coarse-to-fine registration paradigm: a global stage establishes superpoint-superpixel correspondences through joint intra-modal context and cross-modal interaction modeling, followed by a geometry-constrained point-level refinement for precise registration. Third, we employ a dynamic training mechanism with gradient normalization to balance losses for feature alignment, correspondence refinement, and pose estimation. Extensive experiments demonstrate that CrossI2P outperforms state-of-the-art methods by 23.7% on the KITTI Odometry benchmark and by 37.9% on nuScenes, significantly improving both accuracy and robustness.

cs.CV↗

arXiv2025

Pluralistic Off-policy Evaluation and Alignment

Personalized preference alignment for LLMs with diverse human preferences requires evaluation and alignment methods that capture pluralism. Most existing preference alignment datasets are logged under policies that differ substantially from the evaluated LLMs, and existing off-policy estimators focus solely on overall utility while ignoring preference pluralism. Extending Off-Policy Evaluation (OPE) to pluralistic preference alignment, therefore, remains an open question. Thus, we propose the Pluralistic Off-Policy Evaluation (POPE), the first framework for offline pluralistic preference evaluation and alignment in LLMs. POPE includes a unified reward function that combines (1) a collaborative utility component derived from human preference signals (e.g., upvotes or relevance scores) and (2) a diversity component inspired by entropy-based coverage measures, together reflecting pluralistic alignment. Furthermore, to estimate this reward from logged interactions, we derive decomposable inverse propensity scoring (IPS) estimators that separately evaluate relevance and diversity. Theoretically, we prove that our decomposed IPS estimators establish a lower bound on their variance. With the off-policy evaluated value function, we can directly enable off-policy optimization to further enhance pluralistic alignment. Empirical results demonstrate that POPE efficiently enhances pluralistic response generation and maintains the models' general capabilities on downstream tasks

cs.CL↗

arXiv2025

Ensemble Distribution Distillation for Self-Supervised Human Activity Recognition

Human Activity Recognition (HAR) has seen significant advancements with the adoption of deep learning techniques, yet challenges remain in terms of data requirements, reliability and robustness. This paper explores a novel application of Ensemble Distribution Distillation (EDD) within a self-supervised learning framework for HAR aimed at overcoming these challenges. By leveraging unlabeled data and a partially supervised training strategy, our approach yields an increase in predictive accuracy, robust estimates of uncertainty, and substantial increases in robustness against adversarial perturbation; thereby significantly improving reliability in real-world scenarios without increasing computational complexity at inference. We demonstrate this with an evaluation on several publicly available datasets. The contributions of this work include the development of a self-supervised EDD framework, an innovative data augmentation technique designed for HAR, and empirical validation of the proposed method's effectiveness in increasing robustness and reliability.

cs.LG↗

arXiv2025

CoMMIT: Coordinated Multimodal Instruction Tuning

Instruction tuning in multimodal large language models (MLLMs) generally involves cooperative learning between a backbone LLM and a feature encoder of non-text input modalities. The major challenge is how to efficiently find the synergy between the two modules so that LLMs can adapt their reasoning abilities to downstream tasks while feature encoders can adjust to provide more task-specific information about its modality. In this paper, we analyze the MLLM instruction tuning from both theoretical and empirical perspectives, where we find the unbalanced learning between the feature encoder and the LLM can cause problems of oscillation and biased learning that lead to sub-optimal convergence. Inspired by our findings, we propose a Multimodal Balance Coefficient that enables quantitative measurement of the balance of learning. Based on this, we further design a dynamic learning scheduler that better coordinates the learning between the LLM and feature encoder, alleviating the problems of oscillation and biased learning. In addition, we introduce an auxiliary regularization on the gradient to promote updating with larger step sizes, which potentially allows for a more accurate estimation of the proposed MultiModal Balance Coefficient and further improves the training sufficiency. Our proposed approach is agnostic to the architecture of LLM and feature encoder, so it can be generically integrated with various MLLMs. We conduct experiments on multiple downstream tasks with various MLLMs, demonstrating that the proposed method is more effective than the baselines in MLLM instruction tuning.

cs.LG↗

arXiv2025

Beyond Negative Transfer: Disentangled Preference-Guided Diffusion for Cross-Domain Sequential Recommendation

Cross-Domain Sequential Recommendation (CDSR) leverages user behaviors across domains to enhance recommendation quality. However, naive aggregation of sequential signals can introduce conflicting domain-specific preferences, leading to negative transfer. While Sequential Recommendation (SR) already suffers from noisy behaviors such as misclicks and impulsive actions, CDSR further amplifies this issue due to domain heterogeneity arising from diverse item types and user intents. The core challenge is disentangling three intertwined signals: domain-invariant preferences, domain-specific preferences, and noise. Diffusion Models (DMs) offer a generative denoising framework well-suited for disentangling complex user preferences and enhancing robustness to noise. Their iterative refinement process enables gradual denoising, making them effective at capturing subtle preference signals. However, existing applications in recommendation face notable limitations: sequential DMs often conflate shared and domain-specific preferences, while cross-domain collaborative filtering DMs neglect temporal dynamics, limiting their ability to model evolving user preferences. To bridge these gaps, we propose \textbf{DPG-Diff}, a novel Disentangled Preference-Guided Diffusion Model, the first diffusion-based approach tailored for CDSR, to or best knowledge. DPG-Diff decomposes user preferences into domain-invariant and domain-specific components, which jointly guide the reverse diffusion process. This disentangled guidance enables robust cross-domain knowledge transfer, mitigates negative transfer, and filters sequential noise. Extensive experiments on real-world datasets demonstrate that DPG-Diff consistently outperforms state-of-the-art baselines across multiple metrics.

cs.IR↗

arXiv2025

MMiC: Mitigating Modality Incompleteness in Clustered Federated Learning

In the era of big data, data mining has become indispensable for uncovering hidden patterns and insights from vast and complex datasets. The integration of multimodal data sources further enhances its potential. Multimodal Federated Learning (MFL) is a distributed approach that enhances the efficiency and quality of multimodal learning, ensuring collaborative work and privacy protection. However, missing modalities pose a significant challenge in MFL, often due to data quality issues or privacy policies across the clients. In this work, we present MMiC, a framework for Mitigating Modality incompleteness in MFL within the Clusters. MMiC replaces partial parameters within client models inside clusters to mitigate the impact of missing modalities. Furthermore, it leverages the Banzhaf Power Index to optimize client selection under these conditions. Finally, MMiC employs an innovative approach to dynamically control global aggregation by utilizing Markovitz Portfolio Optimization. Extensive experiments demonstrate that MMiC consistently outperforms existing federated learning architectures in both global and personalized performance on multimodal datasets with missing modalities, confirming the effectiveness of our proposed solution. Our code is available at https://github.com/gotobcn8/MMiC.

cs.LG↗

arXiv2025

SAND: Boosting LLM Agents with Self-Taught Action Deliberation

Large Language Model (LLM) agents are commonly tuned with supervised finetuning on ReAct-style expert trajectories or preference optimization over pairwise rollouts. Most of these methods focus on imitating specific expert behaviors or promoting chosen reasoning thoughts and actions over rejected ones. However, without reasoning and comparing over alternatives actions, LLM agents finetuned with these methods may over-commit towards seemingly plausible but suboptimal actions due to limited action space exploration. To address this, in this paper we propose Self-taught ActioN Deliberation (SAND) framework, enabling LLM agents to explicitly deliberate over candidate actions before committing to one. To tackle the challenges of when and what to deliberate given large action space and step-level action evaluation, we incorporate self-consistency action sampling and execution-guided action critique to help synthesize step-wise action deliberation thoughts using the base model of the LLM agent. In an iterative manner, the deliberation trajectories are then used to finetune the LLM agent itself. Evaluating on two representative interactive agent tasks, SAND achieves an average 20% improvement over initial supervised finetuning and also outperforms state-of-the-art agent tuning approaches.

cs.CL↗

arXiv2025

DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfer

Large language model-based agents, empowered by in-context learning (ICL), have demonstrated strong capabilities in complex reasoning and tool-use tasks. However, existing works have shown that the effectiveness of ICL is highly sensitive to the choice of demonstrations, with suboptimal examples often leading to unstable or degraded performance. While prior work has explored example selection, including in some agentic or multi-step settings, existing approaches typically rely on heuristics or task-specific designs and lack a general, theoretically grounded criterion for what constitutes an effective demonstration across reasoning steps. Therefore, it is non-trivial to develop a principled, general-purpose method for selecting demonstrations that consistently benefit agent performance. In this paper, we address this challenge with DICE, Dynamic In-Context Example Selection for LLM Agents, a theoretically grounded ICL framework for agentic tasks that selects the most relevant demonstrations at each step of reasoning. Our approach decomposes demonstration knowledge into transferable and non-transferable components through a causal lens, showing how the latter can introduce spurious dependencies that impair generalization. We further propose a stepwise selection criterion with a formal guarantee of improved agent performance. Importantly, DICE is a general, framework-agnostic solution that can be integrated as a plug-in module into existing agentic frameworks without any additional training cost. Extensive experiments across diverse domains demonstrate our method's effectiveness and generality, highlighting the importance of principled, context-aware demo selection for robust and efficient LLM agents.

cs.AI↗

arXiv2025

Causality-aligned Prompt Learning via Diffusion-based Counterfactual Generation

Prompt learning has garnered attention for its efficiency over traditional model training and fine-tuning. However, existing methods, constrained by inadequate theoretical foundations, encounter difficulties in achieving causally invariant prompts, ultimately falling short of capturing robust features that generalize effectively across categories. To address these challenges, we introduce the $\textit{\textbf{DiCap}}$ model, a theoretically grounded $\textbf{Di}$ffusion-based $\textbf{C}$ounterf$\textbf{a}$ctual $\textbf{p}$rompt learning framework, which leverages a diffusion process to iteratively sample gradients from the marginal and conditional distributions of the causal model, guiding the generation of counterfactuals that satisfy the minimal sufficiency criterion. Grounded in rigorous theoretical derivations, this approach guarantees the identifiability of counterfactual outcomes while imposing strict bounds on estimation errors. We further employ a contrastive learning framework that leverages the generated counterfactuals, thereby enabling the refined extraction of prompts that are precisely aligned with the causal features of the data. Extensive experimental results demonstrate that our method performs excellently across tasks such as image classification, image-text retrieval, and visual question answering, with particularly strong advantages in unseen categories.

cs.AI↗

arXiv2025

Graph and Sequential Neural Networks in Session-based Recommendation: A Survey

Recent years have witnessed the remarkable success of recommendation systems (RSs) in alleviating the information overload problem. As a new paradigm of RSs, session-based recommendation (SR) specializes in users' short-term preference capture and aims to provide a more dynamic and timely recommendation based on the ongoing interacted actions. In this survey, we will give a comprehensive overview of the recent works on SR. First, we clarify the definitions of various SR tasks and introduce the characteristics of session-based recommendation against other recommendation tasks. Then, we summarize the existing methods in two categories: sequential neural network based methods and graph neural network (GNN) based methods. The standard frameworks and technical are also introduced. Finally, we discuss the challenges of SR and new research directions in this area.

cs.IR↗

arXiv2025

Diffusion Policies for Risk-Averse Behavior Modeling in Offline Reinforcement Learning

Offline reinforcement learning (RL) presents distinct challenges as it relies solely on observational data. A central concern in this context is ensuring the safety of the learned policy by quantifying uncertainties associated with various actions and environmental stochasticity. Traditional approaches primarily emphasize mitigating epistemic uncertainty by learning risk-averse policies, often overlooking environmental stochasticity. In this study, we propose an uncertainty-aware distributional offline RL method to simultaneously address both epistemic uncertainty and environmental stochasticity. We propose a model-free offline RL algorithm capable of learning risk-averse policies and characterizing the entire distribution of discounted cumulative rewards, as opposed to merely maximizing the expected value of accumulated discounted returns. Our method is rigorously evaluated through comprehensive experiments in both risk-sensitive and risk-neutral benchmarks, demonstrating its superior performance.

cs.LG↗

arXiv2025

Efficient and Generalizable Environmental Understanding for Visual Navigation

Visual Navigation is a core task in Embodied AI, enabling agents to navigate complex environments toward given objectives. Across diverse settings within Navigation tasks, many necessitate the modelling of sequential data accumulated from preceding time steps. While existing methods perform well, they typically process all historical observations simultaneously, overlooking the internal association structure within the data, which may limit the potential for further improvements in task performance. We address this by examining the unique characteristics of Navigation tasks through the lens of causality, introducing a causal framework to highlight the limitations of conventional sequential methods. Leveraging this insight, we propose Causality-Aware Navigation (CAN), which incorporates a Causal Understanding Module to enhance the agent's environmental understanding capability. Empirical evaluations show that our approach consistently outperforms baselines across various tasks and simulation environments. Extensive ablations studies attribute these gains to the Causal Understanding Module, which generalizes effectively in both Reinforcement and Supervised Learning settings without computational overhead.

cs.AI↗

arXiv2025

Weakly-supervised VLM-guided Partial Contrastive Learning for Visual Language Navigation

Visual Language Navigation (VLN) is a fundamental task within the field of Embodied AI, focusing on the ability of agents to navigate complex environments based on natural language instructions. Despite the progress made by existing methods, these methods often present some common challenges. First, they rely on pre-trained backbone models for visual perception, which struggle with the dynamic viewpoints in VLN scenarios. Second, the performance is limited when using pre-trained LLMs or VLMs without fine-tuning, due to the absence of VLN domain knowledge. Third, while fine-tuning LLMs and VLMs can improve results, their computational costs are higher than those without fine-tuning. To address these limitations, we propose Weakly-supervised Partial Contrastive Learning (WPCL), a method that enhances an agent's ability to identify objects from dynamic viewpoints in VLN scenarios by effectively integrating pre-trained VLM knowledge into the perception process, without requiring VLM fine-tuning. Our method enhances the agent's ability to interpret and respond to environmental cues while ensuring computational efficiency. Experimental results have shown that our method outperforms the baseline methods on multiple benchmarks, which validate the effectiveness, robustness and generalizability of our method.

cs.CV↗

arXiv2025

Federated In-Context Learning: Iterative Refinement for Improved Answer Quality

For question-answering (QA) tasks, in-context learning (ICL) enables language models to generate responses without modifying their parameters by leveraging examples provided in the input. However, the effectiveness of ICL heavily depends on the availability of high-quality examples, which are often scarce due to data privacy constraints, annotation costs, and distribution disparities. A natural solution is to utilize examples stored on client devices, but existing approaches either require transmitting model parameters - incurring significant communication overhead - or fail to fully exploit local datasets, limiting their effectiveness. To address these challenges, we propose Federated In-Context Learning (Fed-ICL), a general framework that enhances ICL through an iterative, collaborative process. Fed-ICL progressively refines responses by leveraging multi-round interactions between clients and a central server, improving answer quality without the need to transmit model parameters. We establish theoretical guarantees for the convergence of Fed-ICL and conduct extensive experiments on standard QA benchmarks, demonstrating that our proposed approach achieves strong performance while maintaining low communication costs.

cs.LG↗

arXiv2025

Flexiffusion: Segment-wise Neural Architecture Search for Flexible Denoising Schedule

Diffusion models are cutting-edge generative models adept at producing diverse, high-quality images. Despite their effectiveness, these models often require significant computational resources owing to their numerous sequential denoising steps and the significant inference cost of each step. Recently, Neural Architecture Search (NAS) techniques have been employed to automatically search for faster generation processes. However, NAS for diffusion is inherently time-consuming as it requires estimating thousands of diffusion models to search for the optimal one. In this paper, we introduce Flexiffusion, a novel training-free NAS paradigm designed to accelerate diffusion models by concurrently optimizing generation steps and network structures. Specifically, we partition the generation process into isometric step segments, each sequentially composed of a full step, multiple partial steps, and several null steps. The full step computes all network blocks, while the partial step involves part of the blocks, and the null step entails no computation. Flexiffusion autonomously explores flexible step combinations for each segment, substantially reducing search costs and enabling greater acceleration compared to the state-of-the-art (SOTA) method for diffusion models. Our searched models reported speedup factors of $2.6\times$ and $1.5\times$ for the original LDM-4-G and the SOTA, respectively. The factors for Stable Diffusion V1.5 and the SOTA are $5.1\times$ and $2.0\times$. We also verified the performance of Flexiffusion on multiple datasets, and positive experiment results indicate that Flexiffusion can effectively reduce redundancy in diffusion models.

cs.CV↗

arXiv2025

Flexiffusion: Training-Free Segment-Wise Neural Architecture Search for Efficient Diffusion Models

Diffusion models (DMs) are powerful generative models capable of producing high-fidelity images but are constrained by high computational costs due to iterative multi-step inference. While Neural Architecture Search (NAS) can optimize DMs, existing methods are hindered by retraining requirements, exponential search complexity from step-wise optimization, and slow evaluation relying on massive image generation. To address these challenges, we propose Flexiffusion, a training-free NAS framework that jointly optimizes generation schedules and model architectures without modifying pre-trained parameters. Our key insight is to decompose the generation process into flexible segments of equal length, where each segment dynamically combines three step types: full (complete computation), partial (cache-reused computation), and null (skipped computation). This segment-wise search space reduces the candidate pool exponentially compared to step-wise NAS while preserving architectural diversity. Further, we introduce relative FID (rFID), a lightweight evaluation metric for NAS that measures divergence from a teacher model's outputs instead of ground truth, slashing evaluation time by over $90\%$. In practice, Flexiffusion achieves at least $2\times$ acceleration across LDMs, Stable Diffusion, and DDPMs on ImageNet and MS-COCO, with FID degradation under $5\%$, outperforming prior NAS and caching methods. Notably, it attains $5.1\times$ speedup on Stable Diffusion with near-identical CLIP scores. Our work pioneers a resource-efficient paradigm for searching high-speed DMs without sacrificing quality.

cs.CV↗