arXiv subjects

Yang Li

Publications and source records attributed to Yang Li.

At least 451 records · Page 25Linked to original sources

arXiv2025

OTCR: Optimal Transmission, Compression and Representation for Multimodal Information Extraction

Multimodal Information Extraction (MIE) requires fusing text and visual cues from visually rich documents. While recent methods have advanced multimodal representation learning, most implicitly assume modality equivalence or treat modalities in a largely uniform manner, still relying on generic fusion paradigms. This often results in indiscriminate incorporation of multimodal signals and insufficient control over task-irrelevant redundancy, which may in turn limit generalization. We revisit MIE from a task-centric view: text should dominate, vision should selectively support. We present OTCR, a two-stage framework. First, Cross-modal Optimal Transport (OT) yields sparse, probabilistic alignments between text tokens and visual patches, with a context-aware gate controlling visual injection. Second, a Variational Information Bottleneck (VIB) compresses fused features, filtering task-irrelevant noise to produce compact, task-adaptive representations. On FUNSD, OTCR achieves 91.95% SER and 91.13% RE, while on XFUND (ZH), it reaches 91.09% SER and 94.20% RE, demonstrating competitive performance across datasets. Feature-level analyses further confirm reduced modality redundancy and strengthened task signals. This work offers an interpretable, information-theoretic paradigm for controllable multimodal fusion in document AI.

cs.IR↗

arXiv2025

Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation

The creation of high-quality 3D assets, a cornerstone of modern game development, has long been characterized by labor-intensive and specialized workflows. This paper presents Hunyuan3D Studio, an end-to-end AI-powered content creation platform designed to revolutionize the game production pipeline by automating and streamlining the generation of game-ready 3D assets. At its core, Hunyuan3D Studio integrates a suite of advanced neural modules (such as Part-level 3D Generation, Polygon Generation, Semantic UV, etc.) into a cohesive and user-friendly system. This unified framework allows for the rapid transformation of a single concept image or textual description into a fully-realized, production-quality 3D model complete with optimized geometry and high-fidelity PBR textures. We demonstrate that assets generated by Hunyuan3D Studio are not only visually compelling but also adhere to the stringent technical requirements of contemporary game engines, significantly reducing iteration time and lowering the barrier to entry for 3D content creation. By providing a seamless bridge from creative intent to technical asset, Hunyuan3D Studio represents a significant leap forward for AI-assisted workflows in game development and interactive media.

cs.CV↗

arXiv2025

Recycling the Web: A Method to Enhance Pre-training Data Quality and Quantity for Language Models

Scaling laws predict that the performance of large language models improves with increasing model size and data size. In practice, pre-training has been relying on massive web crawls, using almost all data sources publicly available on the internet so far. However, this pool of natural data does not grow at the same rate as the compute supply. Furthermore, the availability of high-quality texts is even more limited: data filtering pipelines often remove up to 99% of the initial web scrapes to achieve state-of-the-art. To address the "data wall" of pre-training scaling, our work explores ways to transform and recycle data discarded in existing filtering processes. We propose REWIRE, REcycling the Web with guIded REwrite, a method to enrich low-quality documents so that they could become useful for training. This in turn allows us to increase the representation of synthetic data in the final pre-training set. Experiments at 1B, 3B and 7B scales of the DCLM benchmark show that mixing high-quality raw texts and our rewritten texts lead to 1.0, 1.3 and 2.5 percentage points improvement respectively across 22 diverse tasks, compared to training on only filtered web data. Training on the raw-synthetic data mix is also more effective than having access to 2x web data. Through further analysis, we demonstrate that about 82% of the mixed in texts come from transforming lower-quality documents that would otherwise be discarded. REWIRE also outperforms related approaches of generating synthetic data, including Wikipedia-style paraphrasing, question-answer synthesizing and knowledge extraction. These results suggest that recycling web texts holds the potential for being a simple and effective approach for scaling pre-training data. We make our high-quality synthetic data publicly available at https://huggingface.co/datasets/facebook/recycling_the_web.

cs.CL↗

arXiv2025

SQLGovernor: An LLM-powered SQL Toolkit for Real World Application

SQL queries in real world analytical environments, whether written by humans or generated automatically often suffer from syntax errors, inefficiency, or semantic misalignment, especially in complex OLAP scenarios. To address these challenges, we propose SQLGovernor, an LLM powered SQL toolkit that unifies multiple functionalities, including syntax correction, query rewriting, query modification, and consistency verification within a structured framework enhanced by knowledge management. SQLGovernor introduces a fragment wise processing strategy to enable fine grained rewriting and localized error correction, significantly reducing the cognitive load on the LLM. It further incorporates a hybrid self learning mechanism guided by expert feedback, allowing the system to continuously improve through DBMS output analysis and rule validation. Experiments on benchmarks such as BIRD and BIRD CRITIC, as well as industrial datasets, show that SQLGovernor consistently boosts the performance of base models by up to 10%, while minimizing reliance on manual expertise. Deployed in production environments, SQLGovernor demonstrates strong practical utility and effective performance.

cs.DB↗

arXiv2025

CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answering

Users often assume that large language models (LLMs) share their cognitive alignment of context and intent, leading them to omit critical information in question-answering (QA) and produce ambiguous queries. Responses based on misaligned assumptions may be perceived as hallucinations. Therefore, identifying possible implicit assumptions is crucial in QA. To address this fundamental challenge, we propose Conditional Ambiguous Question-Answering (CondAmbigQA), a benchmark comprising 2,000 ambiguous queries and condition-aware evaluation metrics. Our study pioneers "conditions" as explicit contextual constraints that resolve ambiguities in QA tasks through retrieval-based annotation, where retrieved Wikipedia fragments help identify possible interpretations for a given query and annotate answers accordingly. Experiments demonstrate that models considering conditions before answering improve answer accuracy by 11.75%, with an additional 7.15% gain when conditions are explicitly provided. These results highlight that apparent hallucinations may stem from inherent query ambiguity rather than model failure, and demonstrate the effectiveness of condition reasoning in QA, providing researchers with tools for rigorous evaluation.

cs.CL↗

arXiv2025

Unlock giant nonreciprocity via multi-valued behavior of non-Hermitian zero-index materials

Although Einstein's field equations are time-independent, the multivalued feature of the horizon of a blackhole naturally enables the one-way transmission, leading to the strong arrow of time from the time-independent gravitational interaction. Here we experimentally demonstrate a photonic analogue of this principle and reveal the infinite nonreciprocity of the time-reversal-symmetric Maxwell equations. By designing a non-Hermitian zero-index magneto-optical metawaveguide, we introduce multivalued feature to this metawaveguide's complex eigenspace via an exceptional point with non-zero residue, bringing nonlocal, path-dependent historical memory to the system. Hence, a weak magneto-optical response can direct forward and backward waves to two photonic branches with largely distinct momenta and losses, leading to the optical nonreciprocity far beyond the limitation imposed by the magneto-optical material. We fabricated an a-Si/Ce:YIG metawaveguide, achieving nonreciprocal phase shift of 47.78 rad/mm and nonreciprocal loss of 53.9 dB/mm near 1575 nm, exceeding state-of-the-art nonreciprocal devices by an order of magnitude. Our principle universally applies from microwave to visible frequencies, leading to compact isolators, circulators, and sensors. Our principle can also be extended to nonreciprocal acoustic, elastic, and thermal systems. The proposed new paradigm -- geometry-based strong arrow of time in covariant and reversible physical systems -- has broad implications in many disciplines including string theory, cosmology, and astronomy.

physics.optics↗

arXiv2025

Robotic Manipulation Framework Based on Semantic Keypoints for Packing Shoes of Different Sizes, Shapes, and Softness

With the rapid development of the warehousing and logistics industries, the packing of goods has gradually attracted the attention of academia and industry. The packing of footwear products is a typical representative paired-item packing task involving irregular shapes and deformable objects. Although studies on shoe packing have been conducted, different initial states due to the irregular shapes of shoes and standard packing placement poses have not been considered. This study proposes a robotic manipulation framework, including a perception module, reorientation planners, and a packing planner, that can complete the packing of pairs of shoes in any initial state. First, to adapt to the large intraclass variations due to the state, shape, and deformation of the shoe, we propose a vision module based on semantic keypoints, which can also infer more information such as size, state, pose, and manipulation points by combining geometric features. Subsequently, we not only proposed primitive-based reorientation methods for different states of a single deformable shoe but also proposed a fast reorientation method for the top state using box edge contact and gravity, which further improved the efficiency of reorientation. Finally, based on the perception module and reorientation methods, we propose a task planner for shoe pair packing in any initial state to provide an optimal packing strategy. Real-world experiments were conducted to verify the robustness of the reorientation methods and the effectiveness of the packing strategy for various types of shoes. In this study, we highlight the potential of semantic keypoint representation methods, introduce new perspectives on the reorientation of 3D deformable objects and multi-object manipulation, and provide a reference for paired object packing.

cs.RO↗

arXiv2025

GePUP-ES: High-order Energy-stable Projection Methods for the Incompressible Navier-Stokes Equations with No-slip Conditions

Inspired by the unconstrained PPE (UPPE) formulation [Liu, Liu, & Pego 2007 Comm. Pure Appl. Math., 60 pp. 1443], we previously proposed the GePUP formulation [Zhang 2016 J. Sci. Comput., 67 pp. 1134] for numerically solving the incompressible Navier-Stokes equations (INSE) on no-slip domains. In this paper, we propose GePUP-E and GePUP-ES, variants of GePUP that feature (a) electric boundary conditions with no explicit enforcement of the no-penetration condition, (b) equivalence to the no-slip INSE, (c) exponential decay of the divergence of an initially non-solenoidal velocity, and (d) monotonic decrease of the kinetic energy. Different from UPPE, the GePUP-E and GePUP-ES formulations are of strong forms and are designed for finite volume/difference methods under the framework of method of lines. Furthermore, we develop semi-discrete algorithms that preserve (c) and (d) and fully discrete algorithms that are fourth-order accurate for velocity both in time and in space. These algorithms employ algebraically stable time integrators in a black-box manner and only consist of solving a sequence of linear equations in each time step. Results of numerical tests confirm our analysis.

math.NA↗

arXiv2025

From tropical curves to special Lagrangians

We show that any locally planar tropical curve $Γ\subset \mathbb{R}^n$ (with unit edge weights) can be realized as the limit of the rescaled moment map images of a family of special Lagrangian submanifolds in $T^*T^n$ with respect to the Euclidean structure. This is based on a gluing construction that matches special Lagrangian local models to the combinatorics of $Γ$, thereby establishing a direct link between tropical geometry and special Lagrangian geometry.

math.DG↗

arXiv2025

LLM Enabled Multi-Agent System for 6G Networks: Framework and Method of Dual-Loop Edge-Terminal Collaboration

The ubiquitous computing resources in 6G networks provide ideal environments for the fusion of large language models (LLMs) and intelligent services through the agent framework. With auxiliary modules and planning cores, LLM-enabled agents can autonomously plan and take actions to deal with diverse environment semantics and user intentions. However, the limited resources of individual network devices significantly hinder the efficient operation of LLM-enabled agents with complex tool calls, highlighting the urgent need for efficient multi-level device collaborations. To this end, the framework and method of the LLM-enabled multi-agent system with dual-loop terminal-edge collaborations are proposed in 6G networks. Firstly, the outer loop consists of the iterative collaborations between the global agent and multiple sub-agents deployed on edge servers and terminals, where the planning capability is enhanced through task decomposition and parallel sub-task distribution. Secondly, the inner loop utilizes sub-agents with dedicated roles to circularly reason, execute, and replan the sub-task, and the parallel tool calling generation with offloading strategies is incorporated to improve efficiency. The improved task planning capability and task execution efficiency are validated through the conducted case study in 6G-supported urban safety governance. Finally, the open challenges and future directions are thoroughly analyzed in 6G networks, accelerating the advent of the 6G era.

cs.MA↗

arXiv2025

Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacks

Despite advances in improving large language model (LLM) to refuse to answer malicious instructions, widely used LLMs remain vulnerable to jailbreak attacks where attackers generate instructions with distributions differing from safety alignment corpora. New attacks expose LLMs' inability to recognize unseen malicious instructions, highlighting a critical distributional mismatch between training data and real-world attacks that forces developers into reactive patching cycles. To tackle this challenge, we propose IMAGINE, a synthesis framework that leverages embedding space distribution analysis to generate jailbreak-like instructions. This approach effectively fills the distributional gap between authentic jailbreak patterns and safety alignment corpora. IMAGINE follows an iterative optimization process that dynamically evolves text generation distributions across iterations, thereby augmenting the coverage of safety alignment data distributions through synthesized data examples. Based on the safety-aligned corpus enhanced through IMAGINE, our framework demonstrates significant decreases in attack success rate on Qwen2.5, Llama3.1, and Llama3.2 without compromising their utility.

cs.CL↗

arXiv2025

Unravelling the unique kinetic interactions between N2O and unsaturated hydrocarbons

The interaction between unsaturated hydrocarbons and N2O has attracted considerable attention in recent years due to their important roles as potential propellants for advanced propulsion systems e.g. NOFBX, key combustion intermediates in EGR systems, and as major pollutants and precursors in atmospheric chemistry. Although experimental studies and kinetic models have been developed to investigate its fuel chemistry, discrepancies remain between modeled and measured ignition delay times at low temperatures. In this work, we characterize previously unreported direct interaction pathways between N2O and unsaturated hydrocarbons C2H4, C3H6, C2H2, and C3H4 through quantum chemistry calculations, comprehensive kinetic modeling, and experimental validation. These reactions proceed via O-atom addition from N2O to unsaturated hydrocarbons, forming five membered ring intermediates that decompose into N2 and hydrocarbon specific products. Distinct mechanistic differences are identified between alkenes and alkynes, arising from the disparity in N C bond lengths within the intermediates 1.480 A vs. 1.381 A, which governs their decomposition pathways. The corresponding rate coefficients are determined and implemented into multiple kinetic models, with autoignition simulations showing a pronounced promoting effect on model reactivity and improved agreement with experiments, especially at low temperatures. Flux analysis further reveals that the new pathways suppress conventional inhibiting channels while enabling aldehyde and ketone forming pathways that enhance overall reactivity. This work provides a more complete description of N2O hydrocarbon interactions, advancing predictive capability for combustion and atmospheric chemistry.

physics.chem-ph↗

arXiv2025

FinFlowRL: An Imitation-Reinforcement Learning Framework for Adaptive Stochastic Control in Finance

Traditional stochastic control methods in finance struggle in real world markets due to their reliance on simplifying assumptions and stylized frameworks. Such methods typically perform well in specific, well defined environments but yield suboptimal results in changed, non stationary ones. We introduce FinFlowRL, a novel framework for financial optimal stochastic control. The framework pretrains an adaptive meta policy learning from multiple expert strategies, then finetunes through reinforcement learning in the noise space to optimize the generative process. By employing action chunking generating action sequences rather than single decisions, it addresses the non Markovian nature of markets. FinFlowRL consistently outperforms individually optimized experts across diverse market conditions.

q-fin.CP↗

arXiv2025

TacCompress: A Benchmark for Multi-Point Tactile Data Compression in Dexterous Hand

Though robotic dexterous manipulation has progressed substantially recently, challenges like in-hand occlusion still necessitate fine-grained tactile perception, leading to the integration of more tactile sensors into robotic hands. Consequently, the increased data volume imposes substantial bandwidth pressure on signal transmission from the hand's controller. However, the acquisition and compression of multi-point tactile signals based on the dexterous hands' physical structures have not been thoroughly explored. In this paper, our contributions are twofold. First, we introduce a Multi-Point Tactile Dataset for Dexterous Hand Grasping (Dex-MPTD). This dataset captures tactile signals from multiple contact sensors across various objects and grasping poses, offering a comprehensive benchmark for advancing dexterous robotic manipulation research. Second, we investigate both lossless and lossy compression on Dex-MPTD by converting tactile data into images and applying six lossless and five lossy image codecs for efficient compression. Experimental results demonstrate that tactile data can be losslessly compressed to as low as 0.0364 bits per sub-sample (bpss), achieving approximately 200$\times$ compression ratio compared to the raw tactile data. Efficient lossy compressors like HM and VTM can achieve about 1000$\times$ data reductions while preserving acceptable data fidelity. The exploration of lossy compression also reveals that screen-content-targeted coding tools outperform general-purpose codecs in compressing tactile data.

cs.RO↗

arXiv2025

Learning What is Worth Learning: Active and Sequential Domain Adaptation for Multi-modal Gross Tumor Volume Segmentation

Accurate gross tumor volume segmentation on multi-modal medical data is critical for radiotherapy planning in nasopharyngeal carcinoma and glioblastoma. Recent advances in deep neural networks have brought promising results in medical image segmentation, leading to an increasing demand for labeled data. Since labeling medical images is time-consuming and labor-intensive, active learning has emerged as a solution to reduce annotation costs by selecting the most informative samples to label and adapting high-performance models with as few labeled samples as possible. Previous active domain adaptation (ADA) methods seek to minimize sample redundancy by selecting samples that are farthest from the source domain. However, such one-off selection can easily cause negative transfer, and access to source medical data is often limited. Moreover, the query strategy for multi-modal medical data remains unexplored. In this work, we propose an active and sequential domain adaptation framework for dynamic multi-modal sample selection in ADA. We derive a query strategy to prioritize labeling and training on the most valuable samples based on their informativeness and representativeness. Empirical validation on diverse gross tumor volume segmentation tasks demonstrates that our method achieves favorable segmentation performance, significantly outperforming state-of-the-art ADA methods. Code is available at the git repository: \href{https://github.com/Hiyoochan/mmActS}{mmActS}.

cs.CV↗

arXiv2025

Beyond BEV: Optimizing Point-Level Tokens for Collaborative Perception

Collaborative perception allows agents to enhance their perceptual capabilities by exchanging intermediate features. Existing methods typically organize these intermediate features as 2D bird's-eye-view (BEV) representations, which discard critical fine-grained 3D structural cues essential for accurate object recognition and localization. To this end, we first introduce point-level tokens as intermediate representations for collaborative perception. However, point-cloud data are inherently unordered, massive, and position-sensitive, making it challenging to produce compact and aligned point-level token sequences that preserve detailed structural information. Therefore, we present CoPLOT, a novel Collaborative perception framework that utilizes Point-Level Optimized Tokens. It incorporates a point-native processing pipeline, including token reordering, sequence modeling, and multi-agent spatial alignment. A semantic-aware token reordering module generates adaptive 1D reorderings by leveraging scene-level and token-level semantic information. A frequency-enhanced state space model captures long-range sequence dependencies across both spatial and spectral domains, improving the differentiation between foreground tokens and background clutter. Lastly, a neighbor-to-ego alignment module applies a closed-loop process, combining global agent-level correction with local token-level refinement to mitigate localization noise. Extensive experiments on both simulated and real-world datasets show that CoPLOT outperforms state-of-the-art models, with even lower communication and computation overhead. Code will be available at https://github.com/CheeryLeeyy/CoPLOT.

cs.CV↗

arXiv2025

Instant Preference Alignment for Text-to-Image Diffusion Models

Text-to-image (T2I) generation has greatly enhanced creative expression, yet achieving preference-aligned generation in a real-time and training-free manner remains challenging. Previous methods often rely on static, pre-collected preferences or fine-tuning, limiting adaptability to evolving and nuanced user intents. In this paper, we highlight the need for instant preference-aligned T2I generation and propose a training-free framework grounded in multimodal large language model (MLLM) priors. Our framework decouples the task into two components: preference understanding and preference-guided generation. For preference understanding, we leverage MLLMs to automatically extract global preference signals from a reference image and enrich a given prompt using structured instruction design. Our approach supports broader and more fine-grained coverage of user preferences than existing methods. For preference-guided generation, we integrate global keyword-based control and local region-aware cross-attention modulation to steer the diffusion model without additional training, enabling precise alignment across both global attributes and local elements. The entire framework supports multi-round interactive refinement, facilitating real-time and context-aware image generation. Extensive experiments on the Viper dataset and our collected benchmark demonstrate that our method outperforms prior approaches in both quantitative metrics and human evaluations, and opens up new possibilities for dialog-based generation and MLLM-diffusion integration.

cs.CV↗

arXiv2025

ZTFed-MAS2S: A Zero-Trust Federated Learning Framework with Verifiable Privacy and Trust-Aware Aggregation for Wind Power Data Imputation

Wind power data often suffers from missing values due to sensor faults and unstable transmission at edge sites. While federated learning enables privacy-preserving collaboration without sharing raw data, it remains vulnerable to anomalous updates and privacy leakage during parameter exchange. These challenges are amplified in open industrial environments, necessitating zero-trust mechanisms where no participant is inherently trusted. To address these challenges, this work proposes ZTFed-MAS2S, a zero-trust federated learning framework that integrates a multi-head attention-based sequence-to-sequence imputation model. ZTFed integrates verifiable differential privacy with non-interactive zero-knowledge proofs and a confidentiality and integrity verification mechanism to ensure verifiable privacy preservation and secure model parameters transmission. A dynamic trust-aware aggregation mechanism is employed, where trust is propagated over similarity graphs to enhance robustness, and communication overhead is reduced via sparsity- and quantization-based compression. MAS2S captures long-term dependencies in wind power data for accurate imputation. Extensive experiments on real-world wind farm datasets validate the superiority of ZTFed-MAS2S in both federated learning performance and missing data imputation, demonstrating its effectiveness as a secure and efficient solution for practical applications in the energy sector.

cs.LG↗