Searcharxiv⌕ Search

arXiv subjects

Rui Liu

Publications and source records attributed to Rui Liu.

At least 127 records · Page 7Linked to original sources
arXiv2026

PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents

Current Graphical User Interface (GUI) agents operate primarily under a reactive paradigm: a user must provide an explicit instruction for the agent to execute a task. However, an intelligent AI assistant should be proactive, which is capable of anticipating user intentions directly from continuous visual inputs, such as mobile or desktop screenshots, and offering timely recommendations without explicit user prompting. Transitioning to this proactive paradigm presents significant challenges. Real-world screen activity is rarely linear; it consists of long-horizon trajectories fraught with noisy browsing, meaningless actions, and multithreaded task-switching. To address this gap, we introduce PIRA-Bench (Proactive Intent Recommendation Agent Benchmark), a novel benchmark for evaluating multimodal large language models (MLLMs) on continuous, weakly-supervised visual inputs. Unlike reactive datasets, PIRA-Bench features complex trajectories with multiple interleaved intents and noisy segments with various user profile contexts, challenging agents to detect actionable events while fitting to user preferences. Furthermore, we propose the PIRF baseline, a memory-aware, state-tracking framework that empowers general MLLMs to manage multiple task threads and handle misleading visual inputs. PIRA-Bench serves as an initial step toward robust and proactive GUI-based personal assistants.

cs.AI↗
arXiv2026

The giant anomalous Hall and Nernst effects in Kagome permanent magnets RCo5

Kagome lattice materials have attracted considerable attention due to their intriguing topological properties and potential applications in next-generation quantum and spintronic technologies. In particular, rare-earth permanent magnets with Kagome structure provide an ideal platform that combines robust magnetism with nontrivial quantum phenomena. However, their anomalous transport properties, particularly thermoelectric responses, remain insufficiently explored. In this work, we perform systematic first-principles calculations on the anomalous Hall and anomalous Nernst effects in Kagome permanent magnets RCo5 (R = Ce, La, Sm, Gd). We find that CeCo5 exhibits a pronounced anomalous Hall conductivity of about 1500 Omega^-1 cm^-1 while GdCo5 displays a substantial anomalous Nernst conductivity of 11 A m^-1 K^-1 within +/- 0.1 eV of the Fermi energy, both comparable to or surpassing the measured intrinsic values reported in many typical Weyl and Heusler magnets. These exceptional anomalous transport properties originate from Berry curvature hotspots near spin-orbit coupling induced band gaps. If validated, these theoretical predictions would be important for Berry-curvature-driven transport in magnetic intermetallics. Our results establish RCo5 compounds as versatile platforms for exploring Berry curvature-driven transport in tunable magnetic topological materials.

cond-mat.mtrl-sci↗
arXiv2026

CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verification

Developing multi-turn interactive tool-use agents is challenging because real-world user needs are often complex and ambiguous, yet agents must execute deterministic actions to satisfy them. To address this gap, we introduce \textbf{CoVe} (\textbf{Co}nstraint-\textbf{Ve}rification), a post-training data synthesis framework designed for training interactive tool-use agents while ensuring both data complexity and correctness. CoVe begins by defining explicit task constraints, which serve a dual role: they guide the generation of complex trajectories and act as deterministic verifiers for assessing trajectory quality. This enables the creation of high-quality training trajectories for supervised fine-tuning (SFT) and the derivation of accurate reward signals for reinforcement learning (RL). Our evaluation on the challenging $τ^2$-bench benchmark demonstrates the effectiveness of the framework. Notably, our compact \textbf{CoVe-4B} model achieves success rates of 43.0\% and 59.4\% in the Airline and Retail domains, respectively; its overall performance significantly outperforms strong baselines of similar scale and remains competitive with models up to $17\times$ its size. These results indicate that CoVe provides an effective and efficient pathway for synthesizing training data for state-of-the-art interactive tool-use agents. To support future research, we open-source our code, trained model, and the full set of 12K high-quality trajectories used for training.

cs.AI↗
arXiv2026

Continuous Optimization for Feature Selection with Permutation-Invariant Embedding and Policy-Guided Search

Feature selection removes redundant features to enhanc performance and computational efficiency in downstream tasks. Existing works often struggle to capture complex feature interactions and adapt to diverse scenarios. Recent advances in this domain have incorporated generative intelligence to address these drawbacks by uncovering intricate relationships between features. However, two key limitations remain: 1) embedding feature subsets in a continuous space is challenging due to permutation sensitivity, as changes in feature order can introduce biases and weaken the embedding learning process; 2) gradient-based search in the embedding space assumes convexity, which is rarely guaranteed, leading to reduced search effectiveness and suboptimal subsets. To address these limitations, we propose a new framework that can: 1) preserve feature subset knowledge in a continuous embedding space while ensuring permutation invariance; 2) effectively explore the embedding space without relying on strong convex assumptions. For the first objective, we develop an encoder-decoder paradigm to preserve feature selection knowledge into a continuous embedding space. This paradigm captures feature interactions through pairwise relationships within the subset, removing the influence of feature order on the embedding. Moreover, an inducing point mechanism is introduced to accelerate pairwise relationship computations. For the second objective, we employ a policy-based reinforcement learning (RL) approach to guide the exploration of the embedding space. The RL agent effectively navigates the space by balancing multiple objectives. By prioritizing high-potential regions adaptively and eliminating the reliance on convexity assumptions, the RL agent effectively reduces the risk of converging to local optima. Extensive experiments demonstrate the effectiveness, efficiency, robustness and explicitness of our model.

cs.LG↗
arXiv2026

Permutation-Invariant Representation Learning for Robust and Privacy-Preserving Feature Selection

Feature selection eliminates redundancy among features to improve downstream task performance while reducing computational overhead. Existing methods often struggle to capture intricate feature interactions and adapt across diverse application scenarios. Recent advances employ generative intelligence to alleviate these drawbacks. However, these methods remain constrained by permutation sensitivity in embedding and reliance on convexity assumptions in gradient-based search. To address these limitations, our initial work introduces a novel framework that integrates permutation-invariant embedding with policy-guided search. Although effective, it still left opportunities to adapt to realistic distributed scenarios. In practice, data across local clients is highly imbalanced, heterogeneous and constrained by strict privacy regulations, limiting direct sharing. These challenges highlight the need for a framework that can integrate feature selection knowledge across clients without exposing sensitive information. In this extended journal version, we advance the framework from two perspectives: 1) developing a privacy-preserving knowledge fusion strategy to derive a unified representation space without sharing sensitive raw data. 2) incorporating a sample-aware weighting strategy to address distributional imbalance among heterogeneous local clients. Extensive experiments validate the effectiveness, robustness, and efficiency of our framework. The results further demonstrate its strong generalization ability in federated learning scenarios. The code and data are publicly available: https://anonymous.4open.science/r/FedCAPS-08BF.

cs.LG↗
arXiv2026

Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steering

Automated radiology report generation using vision-language models (VLMs) is limited by the risk of prior-comparison hallucination, where the model generates historical findings unsupported by the current study. We address this challenge with a training-free, inference-time control framework termed Semantically Decoupled Latent Steering (SDLS). Unlike generic activation steering, which often suffers from semantic entanglement, our approach constructs a semantic-free intervention vector via large language model (LLM)-driven semantic decomposition followed by $QR$-based orthogonalization. This orthogonalization step is critical. It leverages geometric constraints to filter out the clinical semantics often entangled in standard principal component analysis (PCA) directions, ensuring that the steering vector targets only the ``historical comparison" axis. We validate our method on the BiomedGPT foundation model, demonstrating that it overcomes the trade-off between hallucination suppression and clinical accuracy. Extensive experiments on MIMIC-CXR, and zero-shot transfer evaluation on CheXpert Plus and IU-Xray, demonstrate the robustness of our approach. Quantitative evaluations on MIMIC-CXR show that our approach significantly reduces the probability of historical hallucinations (FilBERT score decreases from 0.2373 to 0.1889) and improves clinical label fidelity (CheXpert macro-F1 increases from 0.2242 to 0.3208). Supplementary evaluations confirm that the structural integrity of the clinical narrative is maintained.

cs.CV↗
arXiv2026

An AI-Based Structured Semantic Control Model for Stable and Coherent Dynamic Interactive Content Generation

This study addresses the challenge that generative models struggle to balance flexibility, stability, and controllability in complex interactive scenarios. It proposes a controllable generation framework for dynamic interactive content construction. The framework builds a structured semantic state space that encodes user input, environmental conditions, and historical context into actionable latent representations and generates directional control vectors to guide the content generation process. It introduces multilevel constraints, including semantic consistency constraints, structural stability constraints, and semantic drift penalties, which help the model maintain clear semantic paths and coherent logic in dynamic environments. These constraints prevent content deviation, unstable tone, or structural breaks. Based on these components, the study designs a systematic controllable generation pipeline in which semantic modeling, control signals, and generation strategies work together within one framework. Sensitivity analyses on control vector dimension, hidden layer size, noise intensity, and training sample scale are conducted on a public dialogue dataset to validate the framework. The results show that the approach improves semantic structure, contextual consistency, and controllable expression, providing a structured and effective solution for interactive content generation.

cs.HC↗
arXiv2026

The dynamics of innovation diffusion: A survey of Bass-type models

This paper synthesises the existing research on the dynamics of innovation diffusion, with a focus on Bass-type models and their extensions. The theoretical foundation of innovation diffusion proposed by Rogers (1962) and the seminal work of Bass (1969) serve as a starting point for the analysis. We identify and examine various generalizations and stochastic extensions of the Bass model, including counting processes, diffusion processes, and uncertain processes, as well as parameter estimation techniques, from classical statistical techniques to more advanced techniques such as Bayesian filtering and metaheuristic optimisation. We finally explore alternative models of innovation diffusion, with a particular focus on agent-based models. This overview of the evolution of Bass-type models illustrates the progress made in innovation diffusion research over the past decades.

econ.GN↗
arXiv2026

Eureka-Audio: Triggering Audio Intelligence in Compact Language Models

We present Eureka-Audio, a compact yet high-performance audio language model that achieves competitive performance against models that are 4 to 18 times larger across a broad range of audio understanding benchmarks. Despite containing only 1.7B parameters, Eureka-Audio demonstrates strong performance on automatic speech recognition (ASR), audio understanding, and dense audio captioning, matching or surpassing multiple 7B to 30B audio and omni-modal baselines. The model adopts a unified end-to-end architecture composed of a lightweight language backbone, a Whisper-based audio encoder, and a sparsely activated Mixture-of-Experts (MoE) adapter that explicitly accounts for audio heterogeneity and alleviates cross-modal optimization conflicts under limited capacity. To further enhance paralinguistic reasoning, we introduce DataFlux, a closed loop audio instruction data synthesis and verification pipeline that constructs high quality, logically consistent supervision from raw audio. Extensive evaluations across ASR, knowledge reasoning, safety, instruction following, and paralinguistic benchmarks, demonstrate that Eureka-Audio achieves an efficient balance between computational cost and performance. These results establish Eureka Audio as a strong and practical baseline for lightweight audio understanding models.

cs.SD↗
arXiv2026

KoopGen: Koopman Generator Networks for Representing and Predicting Dynamical Systems with Continuous Spectra

Representing and predicting high-dimensional and spatiotemporally chaotic dynamical systems remains a fundamental challenge in dynamical systems and machine learning. Although data-driven models can achieve accurate short-term forecasts, they often lack stability, interpretability, and scalability in regimes dominated by broadband or continuous spectra. Koopman-based approaches provide a principled linear perspective on nonlinear dynamics, but existing methods rely on restrictive finite-dimensional assumptions or explicit spectral parameterizations that degrade in high-dimensional settings. Against these issues, we introduce KoopGen, a generator-based neural Koopman framework that models dynamics through a structured, state-dependent representation of Koopman generators. By exploiting the intrinsic Cartesian decomposition into skew-adjoint and self-adjoint components, KoopGen separates conservative transport from irreversible dissipation while enforcing exact operator-theoretic constraints during learning. Across systems ranging from nonlinear oscillators to high-dimensional chaotic and spatiotemporal dynamics, KoopGen improves prediction accuracy and stability, while clarifying which components of continuous-spectrum dynamics admit interpretable and learnable representations.

cs.LG↗
arXiv2026

EEG2GAIT: A Hierarchical Graph Convolutional Network for EEG-based Gait Decoding

Decoding gait dynamics from EEG signals presents significant challenges due to the complex spatial dependencies of motor processes, the need for accurate temporal and spectral feature extraction, and the scarcity of high-quality gait EEG datasets. To address these issues, we propose EEG2GAIT, a novel hierarchical graph-based model that captures multi-level spatial embeddings of EEG channels using a Hierarchical Graph Convolutional Network (GCN) Pyramid. To further improve decoding performance, we introduce a Hybrid Temporal-Spectral Reward (HTSR) loss function, which integrates time-domain, frequency-domain, and reward-based loss components. In addition, we contribute a new Gait-EEG Dataset (GED), consisting of synchronized EEG and lower-limb joint angle data collected from 50 participants across two laboratory visits. Extensive experiments demonstrate that EEG2GAIT with HTSR achieves superior performance on the GED dataset, reaching a Pearson correlation coefficient (r) of 0.959, a coefficient of determination of 0.914, and a Mean Absolute Error (MAE) of 0.193. On the MoBI dataset, EEG2GAIT likewise consistently outperforms existing methods, achieving an r of 0.779, a coefficient of determination of 0.597, and an MAE of 4.384. Statistical analyses confirm that these improvements are significant compared to all prior models. Ablation studies further validate the contributions of the hierarchical GCN modules and the proposed HTSR loss, while saliency analysis highlights the involvement of motor-related brain regions in decoding tasks. Collectively, these findings underscore EEG2GAIT's potential for advancing brain-computer interface applications, particularly in lower-limb rehabilitation and assistive technologies.

eess.SP↗
arXiv2026

EEG-to-Gait Decoding via Phase-Aware Representation Learning

Accurate decoding of lower-limb motion from EEG signals is essential for advancing brain-computer interface (BCI) applications in movement intent recognition and control. This study presents NeuroDyGait, a two-stage, phase-aware EEG-to-gait decoding framework that explicitly models temporal continuity and domain relationships. To address challenges of causal, phase-consistent prediction and cross-subject variability, Stage I learns semantically aligned EEG-motion embeddings via relative contrastive learning with a cross-attention-based metric, while Stage II performs domain relation-aware decoding through dynamic fusion of session-specific heads. Comprehensive experiments on two benchmark datasets (GED and FMD) show substantial gains over baselines, including a recent 2025 model EEG2GAIT. The framework generalizes to unseen subjects and maintains inference latency below 5 ms per window, satisfying real-time BCI requirements. Visualization of learned attention and phase-specific cortical saliency maps further reveals interpretable neural correlates of gait phases. Future extensions will target rehabilitation populations and multimodal integration.

eess.SP↗
arXiv2026

Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing

Parallel thinking has emerged as a promising paradigm for reasoning, yet it imposes significant computational burdens. Existing efficiency methods primarily rely on local, per-trajectory signals and lack principled mechanisms to exploit global dynamics across parallel branches. We introduce 2D probing, an interface that exposes the width-depth dynamics of parallel thinking by periodically eliciting intermediate answers from all branches. Our analysis reveals three key insights: non-monotonic scaling across width-depth allocations, heterogeneous reasoning branch lengths, and early stabilization of global consensus. Guided by these insights, we introduce $\textbf{Parallel-Probe}$, a training-free controller designed to optimize online parallel thinking. Parallel-Probe employs consensus-based early stopping to regulate reasoning depth and deviation-based branch pruning to dynamically adjust width. Extensive experiments across three benchmarks and multiple models demonstrate that Parallel-Probe establishes a superior Pareto frontier for test-time scaling. Compared to standard majority voting, it reduces sequential tokens by up to $\textbf{35.8}$% and total token cost by over $\textbf{25.8}$% while maintaining competitive accuracy.

cs.CL↗
arXiv2026

AffectGPT-R1: Leveraging Reinforcement Learning for Open-Vocabulary Multimodal Emotion Recognition

Open-Vocabulary Multimodal Emotion Recognition (OV-MER) aims to predict emotions without being constrained by label spaces, enabling fine-grained emotion understanding. Unlike traditional discriminative methods, OV-MER leverages generative models to capture the full spectrum of emotions and employs emotion wheels (EWs) for metric calculation. Previous approaches (e.g., AffectGPT) primarily rely on token-level loss during training. However, this objective is misaligned with the metrics used in OV-MER, while these metrics cannot be optimized via gradient backpropagation. To address this limitation, we propose AffectGPT-R1, a reinforcement learning framework that treats EW-based metrics as a reward function and applies policy optimization to maximize this reward. Additionally, we introduce an explicit reasoning process and examine its necessity in OV-MER. To further guide model behavior, we incorporate auxiliary rewards that regularize both emotion reasoning and emotion prediction. We also apply length penalties to mitigate reward hacking. Experimental results demonstrate that AffectGPT-R1 yields significant performance improvements on OV-MER. Moreover, our approach enhances generalized emotion understanding, achieving state-of-the-art results on MER-UniBench. Our code is provided in the supplementary material and will be released to facilitate future research.

cs.HC↗
arXiv2026

VisionDirector: Vision-Language Guided Closed-Loop Refinement for Generative Image Synthesis

Generative models can now produce photorealistic imagery, yet they still struggle with the long, multi-goal prompts that professional designers issue. To expose this gap and better evaluate models' performance in real-world settings, we introduce Long Goal Bench (LGBench), a 2,000-task suite (1,000 T2I and 1,000 I2I) whose average instruction contains 18 to 22 tightly coupled goals spanning global layout, local object placement, typography, and logo fidelity. We find that even state-of-the-art models satisfy fewer than 72 percent of the goals and routinely miss localized edits, confirming the brittleness of current pipelines. To address this, we present VisionDirector, a training-free vision-language supervisor that (i) extracts structured goals from long instructions, (ii) dynamically decides between one-shot generation and staged edits, (iii) runs micro-grid sampling with semantic verification and rollback after every edit, and (iv) logs goal-level rewards. We further fine-tune the planner with Group Relative Policy Optimization, yielding shorter edit trajectories (3.1 versus 4.2 steps) and stronger alignment. VisionDirector achieves new state of the art on GenEval (plus 7 percent overall) and ImgEdit (plus 0.07 absolute) while producing consistent qualitative improvements on typography, multi-object scenes, and pose editing.

cs.CV↗
arXiv2026

Active Asymmetric Multi-Agent Multimodal Learning under Uncertainty

Multi-agent systems are increasingly equipped with heterogeneous multimodal sensors, enabling richer perception but introducing modality-specific and agent-dependent uncertainty. Existing multi-agent collaboration frameworks typically reason at the agent level, assume homogeneous sensing, and handle uncertainty implicitly, limiting robustness under sensor corruption. We propose Active Asymmetric Multi-Agent Multimodal Learning under Uncertainty (A2MAML), a principled approach for uncertainty-aware, modality-level collaboration. A2MAML models each modality-specific feature as a stochastic estimate with uncertainty prediction, actively selects reliable agent-modality pairs, and aggregates information via Bayesian inverse-variance weighting. This formulation enables fine-grained, modality-level fusion, supports asymmetric modality availability, and provides a principled mechanism to suppress corrupted or noisy modalities. Extensive experiments on connected autonomous driving scenarios for collaborative accident detection demonstrate that A2MAML consistently outperforms both single-agent and collaborative baselines, achieving up to 18.7% higher accident detection rate.

cs.LG↗
arXiv2026

Mathematical Modeling of Common-Pool Resources: A Comprehensive Review of Bioeconomics, Strategic Interaction, and Complex Adaptive Systems

The governance of common-pool resources-resource systems characterized by high subtractability of yield and difficulty of exclusion-constitutes one of the most persistent and intricate challenges in the fields of economics, ecology, and applied mathematics. This comprehensive review delineates the historical and theoretical evolution of the mathematical frameworks developed to analyze, predict, and manage these systems. We trace the intellectual trajectory from the early, deterministic bioeconomic models of the mid-20th century, which established the fundamental tension between individual profit maximization and collective efficiency, to the contemporary era of complex coupled human-environment system models. Our analysis systematically dissects the formalization of the "Tragedy of the Commons" through the lens of classical cooperative and non-cooperative game theory, examining how the N-person Prisoner's Dilemma and Nash Equilibrium concepts provided the initial, albeit pessimistic, predictive baseline. We subsequently explore the "Ostrom Turn," which necessitated the integration of institutional realism-specifically monitoring, graduated sanctions, and communication-into formal game-theoretic structures. The review further investigates the relaxation of rationality assumptions via evolutionary game theory and behavioral economics, highlighting the destabilizing roles of prospect theory and hyperbolic discounting. Finally, we synthesize recent advances in stochastic differential equations and agent-based computational economics, which capture the critical roles of spatial heterogeneity, noise-induced regime shifts, and early warning signals of collapse. By unifying these diverse mathematical threads, this review elucidates the shifting paradigm from static optimization to dynamic resilience in the management of the commons.

econ.GN↗
arXiv2026

PhoStream: Benchmarking Real-World Streaming for Omnimodal Assistants in Mobile Scenarios

Multimodal Large Language Models excel at offline audio-visual understanding, but their ability to serve as mobile assistants in continuous real-world streams remains underexplored. In daily phone use, mobile assistants must track streaming audio-visual inputs and respond at the right time, yet existing benchmarks are often restricted to multiple-choice questions or use shorter videos. In this paper, we introduce PhoStream, the first mobile-centric streaming benchmark that unifies on-screen and off-screen scenarios to evaluate video, audio, and temporal reasoning. PhoStream contains 5,572 open-ended QA pairs from 578 videos across 4 scenarios and 10 capabilities. We build it with an Automated Generative Pipeline backed by rigorous human verification, and evaluate models using a realistic Online Inference Pipeline and LLM-as-a-Judge evaluation for open-ended responses. Experiments reveal a temporal asymmetry in LLM-judged scores (0-100): models perform well on Instant and Backward tasks (Gemini 3 Pro exceeds 80), but drop sharply on Forward tasks (16.40), largely due to early responses before the required visual and audio cues appear. This highlights a fundamental limitation: current MLLMs struggle to decide when to speak, not just what to say. Code and datasets used in this work will be made publicly accessible at https://github.com/Lucky-Lance/PhoStream.

cs.CV↗