arXiv subjects

Xiaohan Li

Publications and source records attributed to Xiaohan Li.

At least 37 records · Page 2Linked to original sources

arXiv2025

Kling-Omni Technical Report

We present Kling-Omni, a generalist generative framework designed to synthesize high-fidelity videos directly from multimodal visual language inputs. Adopting an end-to-end perspective, Kling-Omni bridges the functional separation among diverse video generation, editing, and intelligent reasoning tasks, integrating them into a holistic system. Unlike disjointed pipeline approaches, Kling-Omni supports a diverse range of user inputs, including text instructions, reference images, and video contexts, processing them into a unified multimodal representation to deliver cinematic-quality and highly-intelligent video content creation. To support these capabilities, we constructed a comprehensive data system that serves as the foundation for multimodal video creation. The framework is further empowered by efficient large-scale pre-training strategies and infrastructure optimizations for inference. Comprehensive evaluations reveal that Kling-Omni demonstrates exceptional capabilities in in-context generation, reasoning-based editing, and multimodal instruction following. Moving beyond a content creation tool, we believe Kling-Omni is a pivotal advancement toward multimodal world simulators capable of perceiving, reasoning, generating and interacting with the dynamic and complex worlds.

cs.CV↗

arXiv2025

KlingAvatar 2.0 Technical Report

Avatar video generation models have achieved remarkable progress in recent years. However, prior work exhibits limited efficiency in generating long-duration high-resolution videos, suffering from temporal drifting, quality degradation, and weak prompt following as video length increases. To address these challenges, we propose KlingAvatar 2.0, a spatio-temporal cascade framework that performs upscaling in both spatial resolution and temporal dimension. The framework first generates low-resolution blueprint video keyframes that capture global semantics and motion, and then refines them into high-resolution, temporally coherent sub-clips using a first-last frame strategy, while retaining smooth temporal transitions in long-form videos. To enhance cross-modal instruction fusion and alignment in extended videos, we introduce a Co-Reasoning Director composed of three modality-specific large language model (LLM) experts. These experts reason about modality priorities and infer underlying user intent, converting inputs into detailed storylines through multi-turn dialogue. A Negative Director further refines negative prompts to improve instruction alignment. Building on these components, we extend the framework to support ID-specific multi-character control. Extensive experiments demonstrate that our model effectively addresses the challenges of efficient, multimodally aligned long-form high-resolution video generation, delivering enhanced visual clarity, realistic lip-teeth rendering with accurate lip synchronization, strong identity preservation, and coherent multimodal instruction following.

cs.CV↗

arXiv2025

CG-FedLLM: How to Compress Gradients in Federated Fune-tuning for Large Language Models

The success of current Large-Language Models (LLMs) hinges on extensive training data that is collected and stored centrally, called Centralized Learning (CL). However, such a collection manner poses a privacy threat, and one potential solution is Federated Learning (FL), which transfers gradients, not raw data, among clients. Unlike traditional networks, FL for LLMs incurs significant communication costs due to their tremendous parameters. This study introduces an innovative approach to compress gradients to improve communication efficiency during LLM FL, formulating the new FL pipeline named CG-FedLLM. This approach integrates an encoder on the client side to acquire the compressed gradient features and a decoder on the server side to reconstruct the gradients. We also developed a novel training strategy that comprises Temporal-ensemble Gradient-Aware Pre-training (TGAP) to identify characteristic gradients of the target model and Federated AutoEncoder-Involved Fine-tuning (FAF) to compress gradients adaptively. Extensive experiments confirm that our approach reduces communication costs and improves performance (e.g., average 3 points increment compared with traditional CL- and FL-based fine-tuning with LlaMA on a well-recognized benchmark, C-Eval). This improvement is because our encoder-decoder, trained via TGAP and FAF, can filter gradients while selectively preserving critical features. Furthermore, we present a series of experimental analyses focusing on the signal-to-noise ratio, compression rate, and robustness within this privacy-centric framework, providing insight into developing more efficient and secure LLMs.

cs.LG↗

arXiv2025

LayoutAgent: A Vision-Language Agent Guided Compositional Diffusion for Spatial Layout Planning

Designing realistic multi-object scenes requires not only generating images, but also planning spatial layouts that respect semantic relations and physical plausibility. On one hand, while recent advances in diffusion models have enabled high-quality image generation, they lack explicit spatial reasoning, leading to unrealistic object layouts. On the other hand, traditional spatial planning methods in robotics emphasize geometric and relational consistency, but they struggle to capture semantic richness in visual scenes. To bridge this gap, in this paper, we propose LayoutAgent, an agentic framework that unifies vision-language reasoning with compositional diffusion for layout generation. Given multiple input images with target objects in them, our method first employs visual-language model to preprocess the inputs through segmentation, object size estimation, scene graph construction, and prompt rewriting. Then we leverage compositional diffusion-a method traditionally used in robotics-to synthesize bounding boxes that respect object relations encoded in the scene graph for spatial layouts. In the end, a foreground-conditioned image generator composes the complete scene by rendering the objects into the planned layout guided by designed prompts. Experiments demonstrate that LayoutAgent outperforms other state-of-the-art layout generation models in layout coherence, spatial realism and aesthetic alignment.

cs.CV↗

arXiv2025

Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis

Recent advances in audio-driven avatar video generation have significantly enhanced audio-visual realism. However, existing methods treat instruction conditioning merely as low-level tracking driven by acoustic or visual cues, without modeling the communicative purpose conveyed by the instructions. This limitation compromises their narrative coherence and character expressiveness. To bridge this gap, we introduce Kling-Avatar, a novel cascaded framework that unifies multimodal instruction understanding with photorealistic portrait generation. Our approach adopts a two-stage pipeline. In the first stage, we design a multimodal large language model (MLLM) director that produces a blueprint video conditioned on diverse instruction signals, thereby governing high-level semantics such as character motion and emotions. In the second stage, guided by blueprint keyframes, we generate multiple sub-clips in parallel using a first-last frame strategy. This global-to-local framework preserves fine-grained details while faithfully encoding the high-level intent behind multimodal instructions. Our parallel architecture also enables fast and stable generation of long-duration videos, making it suitable for real-world applications such as digital human livestreaming and vlogging. To comprehensively evaluate our method, we construct a benchmark of 375 curated samples covering diverse instructions and challenging scenarios. Extensive experiments demonstrate that Kling-Avatar is capable of generating vivid, fluent, long-duration videos at up to 1080p and 48 fps, achieving superior performance in lip synchronization accuracy, emotion and dynamic expressiveness, instruction controllability, identity preservation, and cross-domain generalization. These results establish Kling-Avatar as a new benchmark for semantically grounded, high-fidelity audio-driven avatar synthesis.

cs.CV↗

arXiv2025

HGACNet: Hierarchical Graph Attention Network for Cross-Modal Point Cloud Completion

Point cloud completion is essential for robotic perception, object reconstruction and supporting downstream tasks like grasp planning, obstacle avoidance, and manipulation. However, incomplete geometry caused by self-occlusion and sensor limitations can significantly degrade downstream reasoning and interaction. To address these challenges, we propose HGACNet, a novel framework that reconstructs complete point clouds of individual objects by hierarchically encoding 3D geometric features and fusing them with image-guided priors from a single-view RGB image. At the core of our approach, the Hierarchical Graph Attention (HGA) encoder adaptively selects critical local points through graph attention-based downsampling and progressively refines hierarchical geometric features to better capture structural continuity and spatial relationships. To strengthen cross-modal interaction, we further design a Multi-Scale Cross-Modal Fusion (MSCF) module that performs attention-based feature alignment between hierarchical geometric features and structured visual representations, enabling fine-grained semantic guidance for completion. In addition, we proposed the contrastive loss (C-Loss) to explicitly align the feature distributions across modalities, improving completion fidelity under modality discrepancy. Finally, extensive experiments conducted on both the ShapeNet-ViPC benchmark and the YCB-Complete dataset confirm the effectiveness of HGACNet, demonstrating state-of-the-art performance as well as strong applicability in real-world robotic manipulation tasks.

cs.RO↗

arXiv2025

MIDAS: Multimodal Interactive Digital-humAn Synthesis via Real-time Autoregressive Video Generation

Recently, interactive digital human video generation has attracted widespread attention and achieved remarkable progress. However, building such a practical system that can interact with diverse input signals in real time remains challenging to existing methods, which often struggle with heavy computational cost and limited controllability. In this work, we introduce an autoregressive video generation framework that enables interactive multimodal control and low-latency extrapolation in a streaming manner. With minimal modifications to a standard large language model (LLM), our framework accepts multimodal condition encodings including audio, pose, and text, and outputs spatially and semantically coherent representations to guide the denoising process of a diffusion head. To support this, we construct a large-scale dialogue dataset of approximately 20,000 hours from multiple sources, providing rich conversational scenarios for training. We further introduce a deep compression autoencoder with up to 64$\times$ reduction ratio, which effectively alleviates the long-horizon inference burden of the autoregressive model. Extensive experiments on duplex conversation, multilingual human synthesis, and interactive world model highlight the advantages of our approach in low latency, high efficiency, and fine-grained multimodal controllability.

cs.CV↗

arXiv2025

Stereo 3D Gaussian Splatting SLAM for Outdoor Urban Scenes

3D Gaussian Splatting (3DGS) has recently gained popularity in SLAM applications due to its fast rendering and high-fidelity representation. However, existing 3DGS-SLAM systems have predominantly focused on indoor environments and relied on active depth sensors, leaving a gap for large-scale outdoor applications. We present BGS-SLAM, the first binocular 3D Gaussian Splatting SLAM system designed for outdoor scenarios. Our approach uses only RGB stereo pairs without requiring LiDAR or active sensors. BGS-SLAM leverages depth estimates from pre-trained deep stereo networks to guide 3D Gaussian optimization with a multi-loss strategy enhancing both geometric consistency and visual quality. Experiments on multiple datasets demonstrate that BGS-SLAM achieves superior tracking accuracy and mapping performance compared to other 3DGS-based solutions in complex outdoor environments.

cs.RO↗

arXiv2025

Natural Language Generation in Healthcare: A Review of Methods and Applications

Natural language generation (NLG) is the key technology to achieve generative artificial intelligence (AI). With the breakthroughs in large language models (LLMs), NLG has been widely used in various medical applications, demonstrating the potential to enhance clinical workflows, support clinical decision-making, and improve clinical documentation. Heterogeneous and diverse medical data modalities, such as medical text, images, and knowledge bases, are utilized in NLG. Researchers have proposed many generative models and applied them in a number of healthcare applications. There is a need for a comprehensive review of NLG methods and applications in the medical domain. In this study, we systematically reviewed 113 scientific publications from a total of 3,988 NLG-related articles identified using a literature search, focusing on data modality, model architecture, clinical applications, and evaluation methods. Following PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) guidelines, we categorize key methods, identify clinical applications, and assess their capabilities, limitations, and emerging challenges. This timely review covers the key NLG technologies and medical applications and provides valuable insights for future studies to leverage NLG to transform medical discovery and healthcare.

cs.CL↗

arXiv2025

Engineering-Oriented Design of Drift-Resilient MTJ Random Number Generator via Hybrid Control Strategies

Magnetic Tunnel Junctions (MTJs) have shown great promise as hardware sources for true random number generation (TRNG) due to their intrinsic stochastic switching behavior. However, practical deployment remains challenged by drift in switching probability caused by thermal fluctuations, device aging, and environmental instability. This work presents an engineering-oriented, drift-resilient MTJ-based TRNG architecture, enabled by a hybrid control strategy that combines self-stabilizing feedback with pulse width modulation. A key component is the Downcalibration-2 scheme, which updates the control parameter every two steps using only integer-resolution timing, ensuring excellent statistical quality without requiring bit discarding, pre-characterization, or external calibration. Extensive experimental measurements and numerical simulations demonstrate that this approach maintains stable randomness under dynamic temperature drift, using only simple digital logic. The proposed architecture offers high throughput, robustness, and scalability, making it well-suited for secure hardware applications, embedded systems, and edge computing environments.

physics.app-ph↗

arXiv2025

Bayesian Reasoning Enabled by Spin-Orbit Torque Magnetic Tunnel Junctions

Bayesian networks play an increasingly important role in data mining, inference, and reasoning with the rapid development of artificial intelligence. In this paper, we present proof-of-concept experiments demonstrating the use of spin-orbit torque magnetic tunnel junctions (SOT-MTJs) in Bayesian network reasoning. Not only can the target probability distribution function (PDF) of a Bayesian network be precisely formulated by a conditional probability table as usual but also quantitatively parameterized by a probabilistic forward propagating neuron network. Moreover, the parameters of the network can also approach the optimum through a simple point-by point training algorithm, by leveraging which we do not need to memorize all historical data nor statistically summarize conditional probabilities behind them, significantly improving storage efficiency and economizing data pretreatment. Furthermore, we developed a simple medical diagnostic system using the SOT-MTJ as a random number generator and sampler, showcasing the application of SOT-MTJ-based Bayesian reasoning. This SOT-MTJ-based Bayesian reasoning shows great promise in the field of artificial probabilistic neural network, broadening the scope of spintronic device applications and providing an efficient and low-storage solution for complex reasoning tasks.

physics.app-ph↗

arXiv2025

An Efficient and Uncertainty-aware Reinforcement Learning Framework for Quality Assurance in Extrusion Additive Manufacturing

Defects in extrusion additive manufacturing remain common despite its prevalent use. While numerous AI-driven approaches have been proposed to improve quality assurance, the inherently dynamic nature of the printing process poses persistent challenges. Regardless of how comprehensive the training dataset is, out-of-distribution data remains inevitable. Consequently, deterministic models often struggle to maintain robustness and, in some cases, fail entirely when deployed in new or slightly altered printing environments. This work introduces an agent that dynamically adjusts flow rate and temperature setpoints in real time, optimizing process control while addressing bottlenecks in training efficiency and uncertainty management. It integrates a vision-based uncertainty quantification module with a reinforcement learning controller, using probabilistic distributions to describe printing segments. While the underlying networks are deterministic, these evolving distributions introduce adaptability into the decision-making process. The vision system classifies material extrusion with a certain level of precision, generating corresponding distributions. A deep Q-learning controller interacts with a simulated environment calibrated to the vision system precision, allowing the agent to learn optimal actions while demonstrating appropriate hesitation when necessary. By executing asynchronous actions and applying progressively tightened elliptical reward shaping, the controller develops robust, adaptive control strategies that account for the coupling effects between process parameters. When deployed with zero-shot learning, the agent effectively bridges the sim-to-real gap, correcting mild and severe under- and over-extrusion reliably. Beyond extrusion additive manufacturing, this scalable framework enables practical AI-driven quality assurance across various additive manufacturing processes.

eess.SY↗

arXiv2025

Triple Modality Fusion: Aligning Visual, Textual, and Graph Data with Large Language Models for Multi-Behavior Recommendations

Integrating diverse data modalities is crucial for enhancing the performance of personalized recommendation systems. Traditional models, which often rely on singular data sources, lack the depth needed to accurately capture the multifaceted nature of item features and user behaviors. This paper introduces a novel framework for multi-behavior recommendations, leveraging the fusion of triple-modality, which is visual, textual, and graph data through alignment with large language models (LLMs). By incorporating visual information, we capture contextual and aesthetic item characteristics; textual data provides insights into user interests and item features in detail; and graph data elucidates relationships within the item-behavior heterogeneous graphs. Our proposed model called Triple Modality Fusion (TMF) utilizes the power of LLMs to align and integrate these three modalities, achieving a comprehensive representation of user behaviors. The LLM models the user's interactions including behaviors and item features in natural languages. Initially, the LLM is warmed up using only natural language-based prompts. We then devise the modality fusion module based on cross-attention and self-attention mechanisms to integrate different modalities from other models into the same embedding space and incorporate them into an LLM. Extensive experiments demonstrate the effectiveness of our approach in improving recommendation accuracy. Further ablation studies validate the effectiveness of our model design and benefits of the TMF.

cs.IR↗

arXiv2025

Probabilistic Greedy Algorithm Solver Using Magnetic Tunneling Junctions for Traveling Salesman Problem

Combinatorial optimization problems are foundational challenges in fields such as artificial intelligence, logistics, and network design. Traditional algorithms, including greedy methods and dynamic programming, often struggle to balance computational efficiency and solution quality, particularly as problem complexity scales. To overcome these limitations, we propose a novel and efficient probabilistic optimization framework that integrates true random number generators (TRNGs) based on spin-transfer torque magnetic tunneling junctions (STT-MTJs). The inherent stochastic switching behavior of STT-MTJs enables dynamic configurability of random number distributions, which we leverage to introduce controlled randomness into a probabilistic greedy algorithm. By tuning a temperature parameter, our algorithm seamlessly transitions between deterministic and stochastic strategies, effectively balancing exploration and exploitation. Furthermore, we apply this framework to the traveling salesman problem (TSP), showcasing its ability to consistently produce high-quality solutions across diverse problem scales. Our algorithm demonstrates superior performance in both solution quality and convergence speed compared to classical approaches, such as simulated annealing and genetic algorithms. Specifically, in larger TSP instances involving up to 70 cities, it retains its performance advantage, achieving near-optimal solutions with fewer iterations and reduced computational costs. This work highlights the potential of integrating MTJ-based TRNGs into optimization algorithms, paving the way for future applications in probabilistic computing and hardware-accelerated optimization.

physics.app-ph↗

arXiv2024

DR-Encoder: Encode Low-rank Gradients with Random Prior for Large Language Models Differentially Privately

The emergence of the Large Language Model (LLM) has shown their superiority in a wide range of disciplines, including language understanding and translation, relational logic reasoning, and even partial differential equations solving. The transformer is the pervasive backbone architecture for the foundation model construction. It is vital to research how to adjust the Transformer architecture to achieve an end-to-end privacy guarantee in LLM fine-tuning. In this paper, we investigate three potential information leakage during a federated fine-tuning procedure for LLM (FedLLM). Based on the potential information leakage, we provide an end-to-end privacy guarantee solution for FedLLM by inserting two-stage randomness. The first stage is to train a gradient auto-encoder with a Gaussian random prior based on the statistical information of the gradients generated by local clients. The second stage is to fine-tune the overall LLM with a differential privacy guarantee by adopting appropriate Gaussian noises. We show the efficiency and accuracy gains of our proposed method with several foundation models and two popular evaluation benchmarks. Furthermore, we present a comprehensive privacy analysis with Gaussian Differential Privacy (GDP) and Renyi Differential Privacy (RDP).

cs.LG↗

arXiv2024

Improving Sequential Recommender Systems with Online and In-store User Behavior

Online e-commerce platforms have been extending in-store shopping, which allows users to keep the canonical online browsing and checkout experience while exploring in-store shopping. However, the growing transition between online and in-store becomes a challenge to sequential recommender systems for future online interaction prediction due to the lack of holistic modeling of hybrid user behaviors (online and in-store). The challenges are twofold. First, combining online and in-store user behavior data into a single data schema and supporting multiple stages in the model life cycle (pre-training, training, inference, etc.) organically needs a new data pipeline design. Second, online recommender systems, which solely rely on online user behavior sequences, must be redesigned to support online and in-store user data as input under the sequential modeling setting. To overcome the first challenge, we propose a hybrid, omnichannel data pipeline to compile online and in-store user behavior data by caching information from diverse data sources. Later, we introduce a model-agnostic encoder module to the sequential recommender system to interpret the user in-store transaction and augment the modeling capacity for better online interaction prediction given the hybrid user behavior.

cs.IR↗

arXiv2024

Iter-AHMCL: Alleviate Hallucination for Large Language Model via Iterative Model-level Contrastive Learning

The development of Large Language Models (LLMs) has significantly advanced various AI applications in commercial and scientific research fields, such as scientific literature summarization, writing assistance, and knowledge graph construction. However, a significant challenge is the high risk of hallucination during LLM inference, which can lead to security concerns like factual inaccuracies, inconsistent information, and fabricated content. To tackle this issue, it is essential to develop effective methods for reducing hallucination while maintaining the original capabilities of the LLM. This paper introduces a novel approach called Iterative Model-level Contrastive Learning (Iter-AHMCL) to address hallucination. This method modifies the representation layers of pre-trained LLMs by using contrastive `positive' and `negative' models, trained on data with and without hallucinations. By leveraging the differences between these two models, we create a more straightforward pathway to eliminate hallucinations, and the iterative nature of contrastive learning further enhances performance. Experimental validation on four pre-trained foundation LLMs (LLaMA2, Alpaca, LLaMA3, and Qwen) finetuning with a specially designed dataset shows that our approach achieves an average improvement of 10.1 points on the TruthfulQA benchmark. Comprehensive experiments demonstrate the effectiveness of Iter-AHMCL in reducing hallucination while maintaining the general capabilities of LLMs.

cs.CL↗

arXiv2024

LLM-Ensemble: Optimal Large Language Model Ensemble Method for E-commerce Product Attribute Value Extraction

Product attribute value extraction is a pivotal component in Natural Language Processing (NLP) and the contemporary e-commerce industry. The provision of precise product attribute values is fundamental in ensuring high-quality recommendations and enhancing customer satisfaction. The recently emerging Large Language Models (LLMs) have demonstrated state-of-the-art performance in numerous attribute extraction tasks, without the need for domain-specific training data. Nevertheless, varying strengths and weaknesses are exhibited by different LLMs due to the diversity in data, architectures, and hyperparameters. This variation makes them complementary to each other, with no single LLM dominating all others. Considering the diverse strengths and weaknesses of LLMs, it becomes necessary to develop an ensemble method that leverages their complementary potentials. In this paper, we propose a novel algorithm called LLM-ensemble to ensemble different LLMs' outputs for attribute value extraction. We iteratively learn the weights for different LLMs to aggregate the labels with weights to predict the final attribute value. Not only can our proposed method be proven theoretically optimal, but it also ensures efficient computation, fast convergence, and safe deployment. We have also conducted extensive experiments with various state-of-the-art LLMs, including Llama2-13B, Llama2-70B, PaLM-2, GPT-3.5, and GPT-4, on Walmart's internal data. Our offline metrics demonstrate that the LLM-ensemble method outperforms all the state-of-the-art single LLMs on Walmart's internal dataset. This method has been launched in several production models, leading to improved Gross Merchandise Volume (GMV), Click-Through Rate (CTR), Conversion Rate (CVR), and Add-to-Cart Rate (ATC).

cs.IR↗