Search arXiv⌕ Search

arXiv subjects

Pengfei Xu

Publications and source records attributed to Pengfei Xu.

At least 19 recordsLinked to original sources
arXiv2026

DraMaze: A Multi-Agent Pipeline with Future-Aware Memory for Diverse Microdrama Script Generation

The rapid growth of microdramas has increased demand for high-quality script production. Long-form microdrama script generation with LLMs requires both diverse plot progression and long-range narrative coherence. Our observations reveal that candidate continuations increasingly concentrate on fewer narrative mechanisms as generation progresses, while conventional retrieval may reinforce trope reuse and overlook historical information essential to future plots. To address these challenges, we propose DraMaze, a multi-agent pipeline that explores diverse causal paths through trope memory-guided evolutionary tree search and mutation. It further constructs a Backward Narrative Dependency Tree to organize, retain, and retrieve historical memories based on future narrative goals. We also introduce MiDramaBench, a bilingual benchmark for evaluating script logic and creative quality across different script lengths, together with causal-pattern metrics for narrative repetition and diversity. Experiments show consistent improvements across three backbone LLMs. For 60-episode scripts of up to 60k words, DraMaze reduces causal-pattern repetition by 32.1% and achieves a Logic score of 82.5, outperforming the best-performing baseline by 8.5 points.

cs.CL↗
arXiv2026

ReRoom: Blending Virtual and Physical Contexts for In Situ Room Planning in Mixed Reality

Planning a real domestic space is an in situ authoring process: users evaluate candidate layouts at true scale, refine their intent, and carry accepted decisions into later iterations. Existing approaches either separate layout editing from the physical room or provide limited support for evaluating and refining whole-room proposals in situ. We present ReRoom, a mixed-reality system for in situ room-layout authoring. ReRoom presents a shared layout state through a virtual room proxy spatially registered to the target room, allowing interaction and layout generation to remain grounded in the physical context. Users refine the current proposal through direct manipulation or language and preserve accepted placements, allowing each generated update to continue the same evolving design. To balance layout quality with generation efficiency, ReRoom uses a skill-guided layout agent whose room-layout design skill operationalizes three principles that we formulate by synthesizing established interior-design guidance for real-room layout generation. The skill grounds these principles in a normalized representation of the scanned room and reusable geometric checks. Evaluations show that ReRoom produces high-quality layouts for non-rectangular rooms, while its in situ workflow improves the room-planning experience over an otherwise equivalent off-site VR workflow. Code will be released upon acceptance of the paper.

cs.GR↗
arXiv2026

LayoutShop: Content-Constrained Exploratory Design of Creative Article Layout

We present LayoutShop, a novel computational framework for designing creative layouts that frame a given article. Inspired by the actual article layout design process, we enable users to create or select layout templates for conceptualization. These templates help construct a layout design space to extract eligible layout structures. Our algorithm then determines the geometry of the extracted layout structures to frame the given article via an optimization approach. We then employ two neural networks for layout assessment, and the high-quality outputs are returned to users for selection. We conducted a user study to evaluate the framework's usability and the quality of the article layouts it produces. The results of the user study confirmed that our framework can effectively help users create high-quality article layouts.

cs.GR↗
arXiv2026

Telligram: Text-Driven Calligram Generation via Diffusion-Guided Skeleton Optimization

Compact calligram generation aims to form a semantic shape while keeping letters recognizable. Most existing methods are shape-conditioned and mainly solve downstream letter layout inside a given contour. We study text-only calligram generation without an input contour. This setting is difficult because semantic shape formation and letter readability strongly interfere with each other when optimized in a single stage. Pushing the word toward a clear figure can easily damage glyph structure, while preserving readable letters can weaken the target shape. To address this difficulty, we present Telligram, a training-free, low-tuning, two-stage framework composed of Semantic Occupancy Prior Formation and Readability-Constrained Glyph Realization. The first stage uses Variational Score Distillation (VSD) with structured skeleton optimization and hierarchical gradient projection to produce a semantic occupancy prior. The second stage converts this occupancy prior into per-letter regions and reconstructs readable glyph layouts through lightweight geometric processing. The framework generates coherent and creative word-level semantic calligrams directly from text prompts.

cs.GR↗
arXiv2026

SketchFlow: Zero-Shot Vector Sketch Generation via GMM Prior Flow in CLIP Latent Space

Vector sketches remain one of the most concise and immediate mediums for abstract human expression. However, generating high-quality vector strokes that exhibit human-like drawing styles remains an open challenge due to the severe scarcity of fine-grained, high-quality text-to-sketch paired data. Existing text-conditioned generation methods often rely on unstable, time-consuming optimization or struggle to generalize to unseen categories in a zero-shot manner. To address these limitations, we present SketchFlow, a novel generative framework rooted in Optimal Transport (OT) theory and flow matching. By leveraging pre-trained CLIP models to bypass labor-intensive image-level text annotations, we formulate cross-modal alignment as a continuous mapping problem directly within the CLIP latent space. To bridge the inevitable modality gap between discrete text concepts and continuous sketch features, we first inject noise into discrete category embeddings to construct a continuous Gaussian Mixture Model (GMM) prior. We then utilize an Optimal Transport Conditional Flow Matching (OT-CFM) model to learn a deterministic vector field mapping from this continuous GMM prior to the target sketch feature distribution. Finally, a Hybrid Diffusion Decoder, fusing 1D U-Net and Transformer architectures, is designed to decode these features into fast and high-fidelity stroke trajectories. Extensive experiments demonstrate that SketchFlow substantially outperforms existing baselines in visual quality and adherence to natural human drawing styles. Furthermore, our geometry-preserving framework demonstrates promising local zero-shot synthesis for prompts beyond the QuickDraw training vocabulary, including unseen concept labels and semantic modifiers, while enabling smooth, continuous semantic interpolation between distinct concepts. Source code is available at: https://github.com/doudin404/SketchFlow.

cs.CV↗
arXiv2026

Discovering Diverse Planning Policies for Multimodal Embodied Agents with Quality-Diversity Optimization

Multimodal embodied agents are increasingly required to solve long-horizon tasks by integrating visual observations, textual goals, and interaction history into closed-loop decision making. However, state-of-the-art large-model-based planners often rely on a single dominant planning style during execution. Once this execution mode becomes ineffective, the agent may remain stalled for many steps, repeatedly interacting with the environment without making meaningful progress. We address this limitation by proposing a Quality-Diversity (QD) framework for discovering diverse planning policies for multimodal embodied agents. The proposed method treats planning-policy templates as evolvable individuals and organizes them into a behavior-indexed archive rather than collapsing search to a single prompt style. In the offline stage, rollout trajectories are summarized into structured success and failure experiences, which guide policy variation through recombination and experience-guided mutation. The resulting policies are mapped into a behavior space defined by interaction intensity and goal-directedness, and the highest-quality policy in each niche is retained in the archive. In the online stage, the agent executes one policy at a time while monitoring task progress. When persistent stall is detected, the system rolls back to the latest checkpoint and switches to a behaviorally distinct archive policy to resume execution. Experiments on the ThreeDWorld transport benchmark show that the proposed framework improves both task success and interaction efficiency over representative baseline planners. These results suggest that discovering diverse policy repertoires is an effective way to support adaptive multimodal planning and online failure recovery.

cs.AI↗
arXiv2026

QoS-Aware Token Scheduling and Private Data Valuation for Multi-Modal Agentic Networks

In agentic systems, human-generated data records anchor the value of AI services. Yet cloud compute pipelines centralize processing on remote servers. Data centralization reduces personal data sovereignty and may potentially degrade the quality of service (QoS). Meanwhile, user contributions are diverse in quantity and quality: decentralized records can be biased, noisy, and heterogeneously distributed. To address the data challenge, we study fair token allocation and private data valuation for decentralized and resource-constrained agentic systems. Our approach embeds multi-modal representations in a shared semantic space and releases differentially private (DP) prototypes to preserve utility while reducing semantic leakage. With the DP guarantee, we design a fair token allocation scheme that rewards effective contributions and remains robust to data heterogeneity and AI resource scarcity. Extensive simulations demonstrate improved contribution-based fairness and QoS compared to standard benchmarks. The improved resistance to image reconstruction attacks indicates enhanced privacy for multi-modal personal data.

cs.AI↗
arXiv2026

Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models

Large Language Models (LLMs) achieve impressive performance across many tasks but remain prone to hallucination, especially in long-form generation where redundant retrieved contexts and lengthy reasoning chains amplify factual errors. Recent studies highlight a critical phenomenon: the closer key information appears to the model outputs, the higher the factual accuracy. However, existing retrieval-augmented language models (RALMs) lack effective mechanisms to ensure this proximity - external evidence is injected into reasoning via multi-turn retrieval, but this cannot ensure key information stays close to the outputs. We propose Micro-Macro Retrieval (M2R), a novel retrieve-while-generate framework to fill this gap. At the macro level, M2R retrieves coarse-grained evidence from external sources; at the micro level, it extracts essential results from a key information repository built during reasoning and reuses them while generating answers. This design directly addresses the key-information-to-output proximity bottleneck, effectively reducing hallucination in long-form tasks. M2R is trained with a curriculum learning-based reinforcement learning strategy using customized rule-based rewards, enabling stable acquisition of retrieval and grounding skills. Extensive experiments across different benchmarks demonstrate the effectiveness of M2R, especially in lengthy-context settings.

cs.CL↗
arXiv2026

Next Point-of-interest (POI) Recommendation Model Based on Multi-modal Spatio-temporal Context Feature Embedding

Predicting the next pickup location of individual users is a fundamental problem in intelligent mobility systems, which requires modeling personalized travel behaviors under complex spatiotemporal contexts. Existing methods mainly learn sequential dependencies from raw trajectories, but often fail to capture high-level behavioral semantics and to effectively disentangle long-term habitual preferences from short-term contextual intentions. In this paper, we propose a semantic embedding based dual stream spatiotemporal attention model for next pickup location prediction. Raw trajectories are first transformed into semantically enriched activity sequences to encode users' stay behaviors and movement semantics. A dual stream architecture is then designed to explicitly decouple long-term historical patterns and short-term dynamic intentions, where each stream employs spatiotemporal attention mechanisms to model dependencies at different temporal scales. To integrate heterogeneous contextual information, a context aware dynamic fusion module adaptively balances the contributions of the two streams. Finally, an attention based matching strategy is used to predict the probability distribution over candidate pickup locations. Experiments on real world ride hailing datasets demonstrate that the proposed model consistently outperforms state of the art methods, validating the effectiveness of semantic trajectory abstraction and dual stream spatiotemporal attention for individualized mobility behavior modeling.

cs.IR↗
arXiv2025

SPLICE: Part-Level 3D Shape Editing from Local Semantic Extraction to Global Neural Mixing

Neural implicit representations of 3D shapes have shown great potential in 3D shape editing due to their ability to model high-level semantics and continuous geometric representations. However, existing methods often suffer from limited editability, lack of part-level control, and unnatural results when modifying or rearranging shape parts. In this work, we present SPLICE, a novel part-level neural implicit representation of 3D shapes that enables intuitive, structure-aware, and high-fidelity shape editing. By encoding each shape part independently and positioning them using parameterized Gaussian ellipsoids, SPLICE effectively isolates part-specific features while discarding global context that may hinder flexible manipulation. A global attention-based decoder is then employed to integrate parts coherently, further enhanced by an attention-guiding filtering mechanism that prevents information leakage across symmetric or adjacent components. Through this architecture, SPLICE supports various part-level editing operations, including translation, rotation, scaling, deletion, duplication, and cross-shape part mixing. These operations enable users to flexibly explore design variations while preserving semantic consistency and maintaining structural plausibility. Extensive experiments demonstrate that SPLICE outperforms existing approaches both qualitatively and quantitatively across a diverse set of shape-editing tasks.

cs.GR↗
arXiv2025

Ambiguity Awareness Optimization: Towards Semantic Disambiguation for Direct Preference Optimization

Direct Preference Optimization (DPO) is a widely used reinforcement learning from human feedback (RLHF) method across various domains. Recent research has increasingly focused on the role of token importance in improving DPO effectiveness. It is observed that identical or semantically similar content (defined as ambiguous content) frequently appears within the preference pairs. We hypothesize that the presence of ambiguous content during DPO training may introduce ambiguity, thereby limiting further improvements in alignment. Through mathematical analysis and proof-of-concept experiments, we reveal that ambiguous content may potentially introduce ambiguities, thereby degrading performance. To address this issue, we introduce Ambiguity Awareness Optimization (AAO), a simple yet effective approach that automatically re-weights ambiguous content to reduce ambiguities by calculating semantic similarity from preference pairs. Through extensive experiments, we demonstrate that AAO consistently and significantly surpasses state-of-the-art approaches in performance, without markedly increasing response length, across multiple model scales and widely adopted benchmark datasets, including AlpacaEval 2, MT-Bench, and Arena-Hard. Specifically, AAO outperforms DPO by up to 8.9 points on AlpacaEval 2 and achieves an improvement of by up to 15.0 points on Arena-Hard.

cs.CL↗
arXiv2025

StrokeFusion: Vector Sketch Generation via Joint Stroke-UDF Encoding and Latent Sequence Diffusion

In the field of sketch generation, raster-format trained models often produce non-stroke artifacts, while vector-format trained models typically lack a holistic understanding of sketches, leading to compromised recognizability. Moreover, existing methods struggle to extract common features from similar elements (e.g., eyes of animals) appearing at varying positions across sketches. To address these challenges, we propose StrokeFusion, a two-stage framework for vector sketch generation. It contains a dual-modal sketch feature learning network that maps strokes into a high-quality latent space. This network decomposes sketches into normalized strokes and jointly encodes stroke sequences with Unsigned Distance Function (UDF) maps, representing sketches as sets of stroke feature vectors. Building upon this representation, our framework exploits a stroke-level latent diffusion model that simultaneously adjusts stroke position, scale, and trajectory during generation. This enables high-fidelity sketch generation while supporting stroke interpolation editing. Extensive experiments on the QuickDraw dataset demonstrate that our framework outperforms state-of-the-art techniques, validating its effectiveness in preserving structural integrity and semantic features. Code and models will be made publicly available upon publication.

cs.GR↗
arXiv2025

Applying Large Language Models to Travel Satisfaction Analysis

As a specific domain of subjective well-being, travel satisfaction has recently attracted much research attention. Previous studies primarily relied on statistical models and, more recently, machine learning models to explore its determinants. Both approaches,however, depend on sufficiently large sample sizes and appropriate statistical assumptions. The emergence of Large Language Models (LLMs) offers a new modeling approach that can address these limitations. Pre-trained on extensive datasets, LLMs have strongcapabilities in contextual understanding and generalization, significantly reducing their dependence on task-specific data and stringent statistical assumptions. The main challenge in applying LLMs lies in the behavioral misalignment between LLMs and humans. Using household survey data collected in Shanghai, this study identifies the existence and source of misalignment, and applies a few-shot learning method to address the misalignment issue. We find that the zero-shot LLM exhibits behavioral misalignment, leading to low prediction accuracy. With just a few samples, few-shot learning can align LLMs and enable them to outperform baseline models. Discrepancies in variable importance among machine learning model, zero-shot LLM, and few-shot LLM reveal that the misalignment arises from the gap between the general knowledge embedded in pre-trained LLMs and the specific, unique characteristics of the dataset. On these bases, we propose an LLM-based modeling approach that can be applied to model travel behavior with small sample sizes. This study highlights the potential of LLMs for modeling not only travel satisfaction but also broader aspects of travel behavior.

cs.CY↗
arXiv2025

StructLayoutFormer:Conditional Structured Layout Generation via Structure Serialization and Disentanglement

Structured layouts are preferable in many 2D visual contents (\eg, GUIs, webpages) since the structural information allows convenient layout editing. Computational frameworks can help create structured layouts but require heavy labor input. Existing data-driven approaches are effective in automatically generating fixed layouts but fail to produce layout structures. We present StructLayoutFormer, a novel Transformer-based approach for conditional structured layout generation. We use a structure serialization scheme to represent structured layouts as sequences. To better control the structures of generated layouts, we disentangle the structural information from the element placements. Our approach is the first data-driven approach that achieves conditional structured layout generation and produces realistic layout structures explicitly. We compare our approach with existing data-driven layout generation approaches by including post-processing for structure extraction. Extensive experiments have shown that our approach exceeds these baselines in conditional structured layout generation. We also demonstrate that our approach is effective in extracting and transferring layout structures. The code is publicly available at %\href{https://github.com/Teagrus/StructLayoutFormer} {https://github.com/Teagrus/StructLayoutFormer}.

cs.GR↗
arXiv2025

AIMMerging: Adaptive Iterative Model Merging Using Training Trajectories for Language Model Continual Learning

Continual learning (CL) is essential for deploying large language models (LLMs) in dynamic real-world environments without the need for costly retraining. Recent model merging-based methods have attracted significant attention, but they still struggle to effectively manage the trade-off between learning new knowledge and preventing forgetting, a challenge largely stemming from suboptimal number of merges and merging frequency. In this paper, we introduce Adaptive Iterative Model Merging (AimMerging), a novel CL framework that utilizes learning and forgetting signals from the training trajectory to dynamically monitor the model's training status. Guided by dynamic monitoring, the training trajectory-guided merge controller adaptively determines the timing and frequency of iterative fusion, while the rehearsal-based knowledge fusion module computes the merging weights and executes the fusion. Comprehensive experiments on three CL benchmarks with various model sizes (from 770M to 13B) demonstrate that AimMerging achieves significant performance improvements over existing state-of-the-art methods, with an average relative improvement of 80% and 59% on FWT and BWT, respectively. The source code is provided for reproducibility.

cs.CL↗
arXiv2025

A Knowledge-Guided Cross-Modal Feature Fusion Model for Local Traffic Demand Prediction

Traffic demand prediction plays a critical role in intelligent transportation systems. Existing traffic prediction models primarily rely on temporal traffic data, with limited efforts incorporating human knowledge and experience for urban traffic demand forecasting. However, in real-world scenarios, traffic knowledge and experience derived from human daily life significantly influence precise traffic prediction. Such knowledge and experiences can guide the model in uncovering latent patterns within traffic data, thereby enhancing the accuracy and robustness of predictions. To this end, this paper proposes integrating structured temporal traffic data with textual data representing human knowledge and experience, resulting in a novel knowledge-guided cross-modal feature representation learning (KGCM) model for traffic demand prediction. Based on regional transportation characteristics, we construct a prior knowledge dataset using a large language model combined with manual authoring and revision, covering both regional and global knowledge and experiences. The KGCM model then learns multimodal data features through designed local and global adaptive graph networks, as well as a cross-modal feature fusion mechanism. A proposed reasoning-based dynamic update strategy enables dynamic optimization of the graph model's parameters, achieving optimal performance. Experiments on multiple traffic datasets demonstrate that our model accurately predicts future traffic demand and outperforms existing state-of-the-art (SOTA) models.

cs.LG↗
arXiv2025

AI shares emotion with humans across languages and cultures

Effective and safe human-machine collaboration requires the regulated and meaningful exchange of emotions between humans and artificial intelligence (AI). Current AI systems based on large language models (LLMs) can provide feedback that makes people feel heard. Yet it remains unclear whether LLMs represent emotion in language as humans do, or whether and how the emotional tone of their output can be controlled. We assess human-AI emotional alignment across linguistic-cultural groups and model-families, using interpretable LLM features translated from concept-sets for over twenty nuanced emotion categories (including six basic emotions). Our analyses reveal that LLM-derived emotion spaces are structurally congruent with human perception, underpinned by the fundamental affective dimensions of valence and arousal. Furthermore, these emotion-related features also accurately predict large-scale behavioural data on word ratings along these two core dimensions, reflecting both universal and language-specific patterns. Finally, by leveraging steering vectors derived solely from human-centric emotion concepts, we show that model expressions can be stably and naturally modulated across distinct emotion categories, which provides causal evidence that human emotion concepts can be used to systematically induce LLMs to produce corresponding affective states when conveying content. These findings suggest AI not only shares emotional representations with humans but its affective outputs can be precisely guided using psychologically grounded emotion concepts.

cs.CL↗
arXiv2025

Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks

(Frankle & Carbin, 2019) shows that there exist winning tickets (small but critical subnetworks) for dense, randomly initialized networks, that can be trained alone to achieve comparable accuracies to the latter in a similar number of iterations. However, the identification of these winning tickets still requires the costly train-prune-retrain process, limiting their practical benefits. In this paper, we discover for the first time that the winning tickets can be identified at the very early training stage, which we term as early-bird (EB) tickets, via low-cost training schemes (e.g., early stopping and low-precision training) at large learning rates. Our finding of EB tickets is consistent with recently reported observations that the key connectivity patterns of neural networks emerge early. Furthermore, we propose a mask distance metric that can be used to identify EB tickets with low computational overhead, without needing to know the true winning tickets that emerge after the full training. Finally, we leverage the existence of EB tickets and the proposed mask distance to develop efficient training methods, which are achieved by first identifying EB tickets via low-cost schemes, and then continuing to train merely the EB tickets towards the target accuracy. Experiments based on various deep networks and datasets validate: 1) the existence of EB tickets, and the effectiveness of mask distance in efficiently identifying them; and 2) that the proposed efficient training via EB tickets can achieve up to 4.7x energy savings while maintaining comparable or even better accuracy, demonstrating a promising and easily adopted method for tackling cost-prohibitive deep network training. Code available at https://github.com/RICE-EIC/Early-Bird-Tickets.

cs.LG↗