arXiv subjects

Di Liu

Publications and source records attributed to Di Liu.

At least 55 records · Page 3Linked to original sources

arXiv2025

WorldGen: From Text to Traversable and Interactive 3D Worlds

We introduce WorldGen, a system that enables the automatic creation of large-scale, interactive 3D worlds directly from text prompts. Our approach transforms natural language descriptions into traversable, fully textured environments that can be immediately explored or edited within standard game engines. By combining LLM-driven scene layout reasoning, procedural generation, diffusion-based 3D generation, and object-aware scene decomposition, WorldGen bridges the gap between creative intent and functional virtual spaces, allowing creators to design coherent, navigable worlds without manual modeling or specialized 3D expertise. The system is fully modular and supports fine-grained control over layout, scale, and style, producing worlds that are geometrically consistent, visually rich, and efficient to render in real time. This work represents a step towards accessible, generative world-building at scale, advancing the frontier of 3D generative AI for applications in gaming, simulation, and immersive social environments.

cs.CV↗

arXiv2025

DICE: Discrete Inversion Enabling Controllable Editing for Multinomial Diffusion and Masked Generative Models

Discrete diffusion models have achieved success in tasks like image generation and masked language modeling but face limitations in controlled content editing. We introduce DICE (Discrete Inversion for Controllable Editing), the first approach to enable precise inversion for discrete diffusion models, including multinomial diffusion and masked generative models. By recording noise sequences and masking patterns during the reverse diffusion process, DICE enables accurate reconstruction and flexible editing of discrete data without the need for predefined masks or attention manipulation. We demonstrate the effectiveness of DICE across both image and text domains, evaluating it on models such as VQ-Diffusion, Paella, and RoBERTa. Our results show that DICE preserves high data fidelity while enhancing editing capabilities, offering new opportunities for fine-grained content manipulation in discrete spaces.

cs.CV↗

arXiv2025

Large Sign Language Models: Toward 3D American Sign Language Translation

We present Large Sign Language Models (LSLM), a novel framework for translating 3D American Sign Language (ASL) by leveraging Large Language Models (LLMs) as the backbone, which can benefit hearing-impaired individuals' virtual communication. Unlike existing sign language recognition methods that rely on 2D video, our approach directly utilizes 3D sign language data to capture rich spatial, gestural, and depth information in 3D scenes. This enables more accurate and resilient translation, enhancing digital communication accessibility for the hearing-impaired community. Beyond the task of ASL translation, our work explores the integration of complex, embodied multimodal languages into the processing capabilities of LLMs, moving beyond purely text-based inputs to broaden their understanding of human communication. We investigate both direct translation from 3D gesture features to text and an instruction-guided setting where translations can be modulated by external prompts, offering greater flexibility. This work provides a foundational step toward inclusive, multimodal intelligent systems capable of understanding diverse forms of language.

cs.CV↗

arXiv2025

Assessing the Human-Likeness of LLM-Driven Digital Twins in Simulating Health Care System Trust

Serving as an emerging and powerful tool, Large Language Model (LLM)-driven Human Digital Twins are showing great potential in healthcare system research. However, its actual simulation ability for complex human psychological traits, such as distrust in the healthcare system, remains unclear. This research gap particularly impacts health professionals' trust and usage of LLM-based Artificial Intelligence (AI) systems in assisting their routine work. In this study, based on the Twin-2K-500 dataset, we systematically evaluated the simulation results of the LLM-driven human digital twin using the Health Care System Distrust Scale (HCSDS) with an established human-subject sample, analyzing item-level distributions, summary statistics, and demographic subgroup patterns. Results showed that the simulated responses by the digital twin were significantly more centralized with lower variance and had fewer selections of extreme options (all p<0.001). While the digital twin broadly reproduces human results in major demographic patterns, such as age and gender, it exhibits relatively low sensitivity in capturing minor differences in education levels. The LLM-based digital twin simulation has the potential to simulate population trends, but it also presents challenges in making detailed, specific distinctions in subgroups of human beings. This study suggests that the current LLM-driven Digital Twins have limitations in modeling complex human attitudes, which require careful calibration and validation before applying them in inferential analyses or policy simulations in health systems engineering. Future studies are necessary to examine the emotional reasoning mechanism of LLMs before their use, particularly for studies that involve simulations sensitive to social topics, such as human-automation trust.

cs.HC↗

arXiv2025

Modulation of Memristive Characteristics by Dynamic Nanoprecipitation inside Conical Nanopores

Nanofluidic memristors have demonstrated great potential for neuromorphic system applications with the advantages of low energy consumption and excellent biocompatibility. Here, an effective way is developed to regulate the memristive behavior of conical nanopores by leveraging the reversible formation and dissolution of nanoprecipitates induced by ion enrichment and depletion in nanopores under opposite voltages. Through the interplay between precipitation dynamics at the pore tip and the ion enrichment/depletion inside the nanopore, conical nanopores exhibit pronounced current hysteresis loops in the presence of CaHPO4, a slightly soluble inorganic salt. The memristive characteristics are found to be strongly dependent on the concentration of CaHPO4, besides the applied voltage amplitude and scan rate. Under the stimulation of pulse voltages, ionic current demonstrates stable learning and forgetting processes with robust switching stability and effective reset capability, which is similar to the short-term plasticity characteristics of biological synapses. Our research may provide a straightforward and tunable approach for the design of nanofluidic memristors.

physics.chem-ph↗

arXiv2025

Reliability of Large Language Model Generated Clinical Reasoning in Assisted Reproductive Technology: Blinded Comparative Evaluation Study

Creating high-quality clinical Chains-of-Thought (CoTs) is crucial for explainable medical Artificial Intelligence (AI) while constrained by data scarcity. Although Large Language Models (LLMs) can synthesize medical data, their clinical reliability remains unverified. This study evaluates the reliability of LLM-generated CoTs and investigates prompting strategies to enhance their quality. In a blinded comparative study, senior clinicians in Assisted Reproductive Technology (ART) evaluated CoTs generated via three distinct strategies: Zero-shot, Random Few-shot (using shallow examples), and Selective Few-shot (using diverse, high-quality examples). These expert ratings were compared against evaluations from a state-of-the-art AI model (GPT-4o). The Selective Few-shot strategy significantly outperformed other strategies across all human evaluation metrics (p < .001). Critically, the Random Few-shot strategy offered no significant improvement over the Zero-shot baseline, demonstrating that low-quality examples are as ineffective as no examples. The success of the Selective strategy is attributed to two principles: "Gold-Standard Depth" (reasoning quality) and "Representative Diversity" (generalization). Notably, the AI evaluator failed to discern these critical performance differences. The clinical reliability of synthetic CoTs is dictated by strategic prompt curation, not the mere presence of examples. We propose a "Dual Principles" framework as a foundational methodology to generate trustworthy data at scale. This work offers a validated solution to the data bottleneck and confirms the indispensable role of human expertise in evaluating high-stakes clinical AI.

cs.AI↗

arXiv2025

T2Bs: Text-to-Character Blendshapes via Video Generation

We present T2Bs, a framework for generating high-quality, animatable character head morphable models from text by combining static text-to-3D generation with video diffusion. Text-to-3D models produce detailed static geometry but lack motion synthesis, while video diffusion models generate motion with temporal and multi-view geometric inconsistencies. T2Bs bridges this gap by leveraging deformable 3D Gaussian splatting to align static 3D assets with video outputs. By constraining motion with static geometry and employing a view-dependent deformation MLP, T2Bs (i) outperforms existing 4D generation methods in accuracy and expressiveness while reducing video artifacts and view inconsistencies, and (ii) reconstructs smooth, coherent, fully registered 3D geometries designed to scale for building morphable models with diverse, realistic facial motions. This enables synthesizing expressive, animatable character heads that surpass current 4D generation techniques.

cs.GR↗

arXiv2025

RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learning

Aerial Remote Sensing (ARS) vision tasks present significant challenges due to the unique viewing angle characteristics. Existing research has primarily focused on algorithms for specific tasks, which have limited applicability in a broad range of ARS vision applications. This paper proposes RingMo-Aerial, aiming to fill the gap in foundation model research in the field of ARS vision. A Frequency-Enhanced Multi-Head Self-Attention (FE-MSA) mechanism is introduced to strengthen the model's capacity for small-object representation. Complementarily, an affine transformation-based contrastive learning method improves its adaptability to the tilted viewing angles inherent in ARS tasks. Furthermore, the ARS-Adapter, an efficient parameter fine-tuning method, is proposed to improve the model's adaptability and performance in various ARS vision tasks. Experimental results demonstrate that RingMo-Aerial achieves SOTA performance on multiple downstream tasks. This indicates the practicality and efficacy of RingMo-Aerial in enhancing the performance of ARS vision tasks.

cs.CV↗

arXiv2025

Compressing CNN models for resource-constrained systems by channel and layer pruning

Convolutional Neural Networks (CNNs) have achieved significant breakthroughs in various fields. However, these advancements have led to a substantial increase in the complexity and size of these networks. This poses a challenge when deploying large and complex networks on edge devices. Consequently, model compression has emerged as a research field aimed at reducing the size and complexity of CNNs. One prominent technique in model compression is model pruning. This paper will present a new technique of pruning that combines both channel and layer pruning in what is called a "hybrid pruning framework". Inspired by EfficientNet, a renowned CNN architecture known for scaling up networks from both channel and layer perspectives, this hybrid approach applies the same principles but in reverse, where it scales down the network through pruning. Experiments on the hybrid approach demonstrated a notable decrease in the overall complexity of the model, with only a minimal reduction in accuracy compared to the baseline model. This complexity reduction translates into reduced latency when deploying the pruned models on an NVIDIA JETSON TX2 embedded AI device.

cs.LG↗

arXiv2025

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Large Vision-Language Models (LVLMs) can reason effectively over both textual and visual inputs, but they tend to hallucinate syntactically coherent yet visually ungrounded contents. In this paper, we investigate the internal dynamics of hallucination by examining the tokens logits ranking throughout the generation process, revealing three key patterns in how LVLMs process information: (1) gradual visual information loss - visually grounded tokens gradually become less favored throughout generation, and (2) early excitation - semantically meaningful tokens achieve peak activation in the layers earlier than the final layer. (3) hidden genuine information - visually grounded tokens though not being eventually decoded still retain relatively high rankings at inference. Based on these insights, we propose VISTA (Visual Information Steering with Token-logit Augmentation), a training-free inference-time intervention framework that reduces hallucination while promoting genuine information. VISTA works by combining two complementary approaches: reinforcing visual information in activation space and leveraging early layer activations to promote semantically meaningful decoding. Compared to existing methods, VISTA requires no external supervision and is applicable to various decoding strategies. Extensive experiments show that VISTA on average reduces hallucination by about 40% on evaluated open-ended generation task, and it consistently outperforms existing methods on four benchmarks across four architectures under three decoding strategies. Code is available at https://github.com/LzVv123456/VISTA.

cs.CV↗

arXiv2025

LODAP: On-Device Incremental Learning Via Lightweight Operations and Data Pruning

Incremental learning that learns new classes over time after the model's deployment is becoming increasingly crucial, particularly for industrial edge systems, where it is difficult to communicate with a remote server to conduct computation-intensive learning. As more classes are expected to learn after their execution for edge devices. In this paper, we propose LODAP, a new on-device incremental learning framework for edge systems. The key part of LODAP is a new module, namely Efficient Incremental Module (EIM). EIM is composed of normal convolutions and lightweight operations. During incremental learning, EIM exploits some lightweight operations, called adapters, to effectively and efficiently learn features for new classes so that it can improve the accuracy of incremental learning while reducing model complexity as well as training overhead. The efficiency of LODAP is further enhanced by a data pruning strategy that significantly reduces the training data, thereby lowering the training overhead. We conducted extensive experiments on the CIFAR-100 and Tiny- ImageNet datasets. Experimental results show that LODAP improves the accuracy by up to 4.32\% over existing methods while reducing around 50\% of model complexity. In addition, evaluations on real edge systems demonstrate its applicability for on-device machine learning. The code is available at https://github.com/duanbiqing/LODAP.

cs.LG↗

arXiv2025

Improved Training Technique for Latent Consistency Models

Consistency models are a new family of generative models capable of producing high-quality samples in either a single step or multiple steps. Recently, consistency models have demonstrated impressive performance, achieving results on par with diffusion models in the pixel space. However, the success of scaling consistency training to large-scale datasets, particularly for text-to-image and video generation tasks, is determined by performance in the latent space. In this work, we analyze the statistical differences between pixel and latent spaces, discovering that latent data often contains highly impulsive outliers, which significantly degrade the performance of iCT in the latent space. To address this, we replace Pseudo-Huber losses with Cauchy losses, effectively mitigating the impact of outliers. Additionally, we introduce a diffusion loss at early timesteps and employ optimal transport (OT) coupling to further enhance performance. Lastly, we introduce the adaptive scaling-$c$ scheduler to manage the robust training process and adopt Non-scaling LayerNorm in the architecture to better capture the statistics of the features and reduce outlier impact. With these strategies, we successfully train latent consistency models capable of high-quality sampling with one or two steps, significantly narrowing the performance gap between latent consistency and diffusion models. The implementation is released here: https://github.com/quandao10/sLCT/

cs.CV↗

arXiv2025

Show and Segment: Universal Medical Image Segmentation via In-Context Learning

Medical image segmentation remains challenging due to the vast diversity of anatomical structures, imaging modalities, and segmentation tasks. While deep learning has made significant advances, current approaches struggle to generalize as they require task-specific training or fine-tuning on unseen classes. We present Iris, a novel In-context Reference Image guided Segmentation framework that enables flexible adaptation to novel tasks through the use of reference examples without fine-tuning. At its core, Iris features a lightweight context task encoding module that distills task-specific information from reference context image-label pairs. This rich context embedding information is used to guide the segmentation of target objects. By decoupling task encoding from inference, Iris supports diverse strategies from one-shot inference and context example ensemble to object-level context example retrieval and in-context tuning. Through comprehensive evaluation across twelve datasets, we demonstrate that Iris performs strongly compared to task-specific models on in-distribution tasks. On seven held-out datasets, Iris shows superior generalization to out-of-distribution data and unseen classes. Further, Iris's task encoding module can automatically discover anatomical relationships across datasets and modalities, offering insights into medical objects without explicit anatomical supervision.

cs.CV↗

arXiv2025

LUCAS: Layered Universal Codec Avatars

Photorealistic 3D head avatar reconstruction faces critical challenges in modeling dynamic face-hair interactions and achieving cross-identity generalization, particularly during expressions and head movements. We present LUCAS, a novel Universal Prior Model (UPM) for codec avatar modeling that disentangles face and hair through a layered representation. Unlike previous UPMs that treat hair as an integral part of the head, our approach separates the modeling of the hairless head and hair into distinct branches. LUCAS is the first to introduce a mesh-based UPM, facilitating real-time rendering on devices. Our layered representation also improves the anchor geometry for precise and visually appealing Gaussian renderings. Experimental results indicate that LUCAS outperforms existing single-mesh and Gaussian-based avatar models in both quantitative and qualitative assessments, including evaluations on held-out subjects in zero-shot driving scenarios. LUCAS demonstrates superior dynamic performance in managing head pose changes, expression transfer, and hairstyle variations, thereby advancing the state-of-the-art in 3D head avatar reconstruction.

cs.CV↗

arXiv2025

Dynamics of a coupled nonlocal PDE-ODE system with spatial memory: well-posedness, stability, and bifurcation analysis

Nonlocal aggregation-diffusion models, when coupled with a spatial map, can capture cognitive and memory-based influences on animal movement and population-level patterns. In this work, we study a one-dimensional reaction-diffusion-aggregation system in which a population's spatiotemporal dynamics are tightly linked to a separate, dynamically updating map. Depending on the local population density, the map amplifies and suppresses certain landscape regions and contributes to directed movement through a nonlocal spatial kernel. After establishing the well-posedness of the coupled PDE-ODE system, we perform a linear stability analysis to identify critical aggregation strengths. We then perform a rigorous bifurcation analysis to determine the precise solution behavior at a steady state near these critical thresholds, deciding whether the bifurcation is sub- or supercritical and the stability of the emergent branch. Based on our analytical findings, we highlight several interesting biological consequences. First, we observe that whether the spatial map functions as attractive or repulsive depends precisely on the map's relative excitation rate versus adaptory rate: when the excitatory effect is larger (smaller) than the adaptatory effect, the map is attractive (repulsive). Second, in the absence of growth dynamics, populations can only form a single aggregate. Therefore, the presence of intraspecific competition is necessary to drive multi-peaked aggregations, reflecting higher-frequency spatial patterns. Finally, we show how subcritical bifurcations can trigger abrupt shifts in average population abundance, suggesting a tipping-point phenomenon in which moderate changes in movement parameters can cause a sudden population decline.

math.AP↗

arXiv2025

Two-Photon Interference of Photons from Remote Tin-Vacancy Centers in Diamond

Scalable quantum networks rely on optical connections between long-lived qubits to distribute entanglement. Tin vacancies in diamond have emerged as promising long-lived qubits, offering extended spin coherence times at liquid helium temperatures and spin-dependent, highly coherent optical transitions for effective photon-based communication. Connecting remote nodes requires quantum interference of indistinguishable photons, which is challenging in an inhomogeneous solid-state environment. Here, we demonstrate a two-node experiment with tin vacancies in diamond, which exhibit a resonant frequency distribution spanning approximately 8 GHz. To overcome the frequency mismatch, we tune the resonant frequencies of one node using the Stark effect. We achieve tunability up to 4 GHz while maintaining optical coherence. As a demonstration, we achieve detuning-dependent remote two-photon interference between separate nodes, obtaining 80(6)% interference visibility without postprocessing when the defects' optical transitions are tuned into resonance, and 63(8)% with detuning up to 20 times their natural linewidths. These results highlight the potential of tin-vacancy centres in diamond for establishing robust optical links between remote quantum registers.

quant-ph↗

arXiv2025

Scalable Multi-Agent Reinforcement Learning for Residential Load Scheduling under Data Governance

As a data-driven approach, multi-agent reinforcement learning (MARL) has made remarkable advances in solving cooperative residential load scheduling problems. However, centralized training, the most common paradigm for MARL, limits large-scale deployment in communication-constrained cloud-edge environments. As a remedy, distributed training shows unparalleled advantages in real-world applications but still faces challenge with system scalability, e.g., the high cost of communication overhead during coordinating individual agents, and needs to comply with data governance in terms of privacy. In this work, we propose a novel MARL solution to address these two practical issues. Our proposed approach is based on actor-critic methods, where the global critic is a learned function of individual critics computed solely based on local observations of households. This scheme preserves household privacy completely and significantly reduces communication cost. Simulation experiments demonstrate that the proposed framework achieves comparable performance to the state-of-the-art actor-critic framework without data governance and communication constraints.

cs.MA↗

arXiv2025

Implicit In-context Learning

In-context Learning (ICL) empowers large language models (LLMs) to swiftly adapt to unseen tasks at inference-time by prefixing a few demonstration examples before queries. Despite its versatility, ICL incurs substantial computational and memory overheads compared to zero-shot learning and is sensitive to the selection and order of demonstration examples. In this work, we introduce Implicit In-context Learning (I2CL), an innovative paradigm that reduces the inference cost of ICL to that of zero-shot learning with minimal information loss. I2CL operates by first generating a condensed vector representation, namely a context vector, extracted from the demonstration examples. It then conducts an inference-time intervention through injecting a linear combination of the context vector and query activations back into the model's residual streams. Empirical evaluation on nine real-world tasks across three model architectures demonstrates that I2CL achieves few-shot level performance at zero-shot inference cost, and it exhibits robustness against variations in demonstration examples. Furthermore, I2CL facilitates a novel representation of task-ids, enhancing task similarity detection and fostering effective transfer learning. We also perform a comprehensive analysis and ablation study on I2CL, offering deeper insights into its internal mechanisms. Code is available at https://github.com/LzVv123456/I2CL.

cs.LG↗