arXiv subjects

Yucheng Wang

Publications and source records attributed to Yucheng Wang.

At least 73 records · Page 4Linked to original sources

arXiv2025

FSR-VLN: Fast and Slow Reasoning for Vision-Language Navigation with Hierarchical Multi-modal Scene Graph

Visual-Language Navigation (VLN) is a fundamental challenge in robotic systems, with broad applications for the deployment of embodied agents in real-world environments. Despite recent advances, existing approaches are limited in long-range spatial reasoning, often exhibiting low success rates and high inference latency, particularly in long-range navigation tasks. To address these limitations, we propose FSR-VLN, a vision-language navigation system that combines a Hierarchical Multi-modal Scene Graph (HMSG) with Fast-to-Slow Navigation Reasoning (FSR). The HMSG provides a multi-modal map representation supporting progressive retrieval, from coarse room-level localization to fine-grained goal view and object identification. Building on HMSG, FSR first performs fast matching to efficiently select candidate rooms, views, and objects, then applies VLM-driven refinement for final goal selection. We evaluated FSR-VLN across four comprehensive indoor datasets collected by humanoid robots, utilizing 87 instructions that encompass a diverse range of object categories. FSR-VLN achieves state-of-the-art (SOTA) performance in all datasets, measured by the retrieval success rate (RSR), while reducing the response time by 82% compared to VLM-based methods on tour videos by activating slow reasoning only when fast intuition fails. Furthermore, we integrate FSR-VLN with speech interaction, planning, and control modules on a Unitree-G1 humanoid robot, enabling natural language interaction and real-time navigation.

cs.RO↗

arXiv2025

Addressing Situated Teaching Needs: A Multi-Agent Framework for Automated Slide Adaptation

The adaptation of teaching slides to instructors' situated teaching needs, including pedagogical styles and their students' context, is a critical yet time-consuming task for educators. Through a series of educator interviews, we first identify and systematically categorize the key friction points that impede this adaptation process. Grounded in these findings, we introduce a novel multi-agent framework designed to automate slide adaptation based on high-level instructor specifications. An evaluation involving 16 modification requests across 8 real-world courses validates our approach. The framework's output consistently achieved high scores in intent alignment, content coherence and factual accuracy, and performed on par with baseline methods regarding visual clarity, while also demonstrating appropriate timeliness and a high operational agreement with human experts, achieving an F1 score of 0.89. This work heralds a new paradigm where AI agents handle the logistical burdens of instructional design, liberating educators to focus on the creative and strategic aspects of teaching.

cs.MA↗

arXiv2025

Emergent Dynamical Translational Symmetry Breaking as an Order Principle for Localization and Topological Transitions

Localization transitions represent a fundamental class of continuous phase transitions, yet they occur without any accompanying symmetry breaking. We resolve this by introducing the concept of dynamical translational symmetry (DTS), which is defined not by the Hamiltonian but by the long-time dynamics of local observables. Its order parameter, the time-averaged local translational contrast (TLTC), quantitatively diagnoses whether evolution restores or breaks translational equivalence. We demonstrate that the TLTC universally captures the Anderson localization transition, the many-body localization transition, and topological phase transitions, revealing that these disparate phenomena are unified by the emergent breaking of DTS. This work establishes a unified dynamical-symmetry framework for phases transitions beyond the equilibrium paradigm.

cond-mat.dis-nn↗

arXiv2025

BEE-RAG: Balanced Entropy Engineering for Retrieval-Augmented Generation

With the rapid advancement of large language models (LLMs), retrieval-augmented generation (RAG) has emerged as a critical approach to supplement the inherent knowledge limitations of LLMs. However, due to the typically large volume of retrieved information, RAG tends to operate with long context lengths. From the perspective of entropy engineering, we identify unconstrained entropy growth and attention dilution due to long retrieval context as significant factors affecting RAG performance. In this paper, we propose the balanced entropy-engineered RAG (BEE-RAG) framework, which improves the adaptability of RAG systems to varying context lengths through the principle of entropy invariance. By leveraging balanced context entropy to reformulate attention dynamics, BEE-RAG separates attention sensitivity from context length, ensuring a stable entropy level. Building upon this, we introduce a zero-shot inference strategy for multi-importance estimation and a parameter-efficient adaptive fine-tuning mechanism to obtain the optimal balancing factor for different settings. Extensive experiments across multiple RAG tasks demonstrate the effectiveness of BEE-RAG.

cs.CL↗

arXiv2025

Kimi Linear: An Expressive, Efficient Attention Architecture

We introduce Kimi Linear, a hybrid linear attention architecture that, for the first time, outperforms full attention under fair comparisons across various scenarios -- including short-context, long-context, and reinforcement learning (RL) scaling regimes. At its core lies Kimi Delta Attention (KDA), an expressive linear attention module that extends Gated DeltaNet with a finer-grained gating mechanism, enabling more effective use of limited finite-state RNN memory. Our bespoke chunkwise algorithm achieves high hardware efficiency through a specialized variant of the Diagonal-Plus-Low-Rank (DPLR) transition matrices, which substantially reduces computation compared to the general DPLR formulation while remaining more consistent with the classical delta rule. We pretrain a Kimi Linear model with 3B activated parameters and 48B total parameters, based on a layerwise hybrid of KDA and Multi-Head Latent Attention (MLA). Our experiments show that with an identical training recipe, Kimi Linear outperforms full MLA with a sizeable margin across all evaluated tasks, while reducing KV cache usage by up to 75% and achieving up to 6 times decoding throughput for a 1M context. These results demonstrate that Kimi Linear can be a drop-in replacement for full attention architectures with superior performance and efficiency, including tasks with longer input and output lengths. To support further research, we open-source the KDA kernel and vLLM implementations, and release the pre-trained and instruction-tuned model checkpoints.

cs.CL↗

arXiv2025

C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Models

Low-Rank Adaptation (LoRA) offers a cost-effective solution for fine-tuning large language models (LLMs), but it often produces overconfident predictions in data-scarce few-shot settings. To address this issue, several classical statistical learning approaches have been repurposed for scalable uncertainty-aware LoRA fine-tuning. However, these approaches neglect how input characteristics affect the predictive uncertainty estimates. To address this limitation, we propose Contextual Low-Rank Adaptation (C-LoRA) as a novel uncertainty-aware and parameter efficient fine-tuning approach, by developing new lightweight LoRA modules contextualized to each input data sample to dynamically adapt uncertainty estimates. Incorporating data-driven contexts into the parameter posteriors, C-LoRA mitigates overfitting, achieves well-calibrated uncertainties, and yields robust predictions. Extensive experiments on LLaMA2-7B models demonstrate that C-LoRA consistently outperforms the state-of-the-art uncertainty-aware LoRA methods in both uncertainty quantification and model generalization. Ablation studies further confirm the critical role of our contextual modules in capturing sample-specific uncertainties. C-LoRA sets a new standard for robust, uncertainty-aware LLM fine-tuning in few-shot regimes. Although our experiments are limited to 7B models, our method is architecture-agnostic and, in principle, applies beyond this scale; studying its scaling to larger models remains an open problem. Our code is available at https://github.com/ahra99/c_lora.

cs.LG↗

arXiv2025

From One to More: Contextual Part Latents for 3D Generation

Recent advances in 3D generation have transitioned from multi-view 2D rendering approaches to 3D-native latent diffusion frameworks that exploit geometric priors in ground truth data. Despite progress, three key limitations persist: (1) Single-latent representations fail to capture complex multi-part geometries, causing detail degradation; (2) Holistic latent coding neglects part independence and interrelationships critical for compositional design; (3) Global conditioning mechanisms lack fine-grained controllability. Inspired by human 3D design workflows, we propose CoPart - a part-aware diffusion framework that decomposes 3D objects into contextual part latents for coherent multi-part generation. This paradigm offers three advantages: i) Reduces encoding complexity through part decomposition; ii) Enables explicit part relationship modeling; iii) Supports part-level conditioning. We further develop a mutual guidance strategy to fine-tune pre-trained diffusion models for joint part latent denoising, ensuring both geometric coherence and foundation model priors. To enable large-scale training, we construct Partverse - a novel 3D part dataset derived from Objaverse through automated mesh segmentation and human-verified annotations. Extensive experiments demonstrate CoPart's superior capabilities in part-level editing, articulated object generation, and scene composition with unprecedented controllability.

cs.CV↗

arXiv2025

Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation

Vision-Language Navigation (VLN) is a critical task for developing embodied agents that can follow natural language instructions to navigate in complex real-world environments. Recent advances in VLN by large pretrained models have significantly improved generalization and instruction grounding compared to traditional approaches. However, the role of reasoning strategies in navigation-an action-centric, long-horizon task-remains underexplored, despite Chain-of-Thought (CoT) reasoning's demonstrated success in static tasks like visual question answering. To address this gap, we conduct the first systematic evaluation of reasoning strategies for VLN, including No-Think (direct action prediction), Pre-Think (reason before action), and Post-Think (reason after action). Surprisingly, our findings reveal the Inference-time Reasoning Collapse issue, where inference-time reasoning degrades navigation accuracy, highlighting the challenges of integrating reasoning into VLN. Based on this insight, we propose Aux-Think, a framework that trains models to internalize structured reasoning patterns through CoT supervision, while inferring action directly without reasoning in online prediction. To support this framework, we release R2R-CoT-320k, the first Chain-of-Thought annotated dataset for VLN. Extensive experiments show that Aux-Think reduces training effort greatly and achieves the best performance under the same data scale.

cs.RO↗

arXiv2025

Multifractal-enriched mobility edges and emergent quantum phases in Rydberg atomic arrays

Anderson localization describes disorder-induced phase transitions, distinguishing between localized and extended states. In quasiperiodic systems, a third multifractal state emerges, characterized by unique energy and wave functions. However, the corresponding multifractal-enriched mobility edges and three-state-coexisting quantum phases have yet to be experimentally detected. In this work, we propose exactly-solvable one-dimensional quasiperiodic lattice models that simultaneously host three-state-coexisting quantum phases, with their phase boundaries analytically derived via Avila's global theorem. Furthermore, we propose experimental protocols via Rydberg atom arrays to realize these states. Notably, we demonstrate a spectroscopic technique capable of measuring inverse participation ratios across real-space and dual-space domains, enabling simultaneous characterization of localized, extended, and multifractal quantum phases in systems with up to tens of qubits. Our work opens new avenues for the experimental exploration of Anderson localization and multifractal states in artificial quantum systems.

cond-mat.dis-nn↗

arXiv2025

Dissipation-Driven Transition of Particles from Dispersive to Flat Bands

Flat bands (FBs) play a crucial role in condensed matter physics, offering an ideal platform to study strong correlation effects and enabling applications in diffraction-free photonics and quantum devices. However, the study and application of FB properties are susceptible to interference from dispersive bands. Here, we explore the impact of bond dissipation on systems hosting both flat and dispersive bands by calculating the steady-state density matrix. We demonstrate that bond dissipation can drive particles from dispersive bands into FBs and establish the general conditions for this phenomenon to occur. Our results demonstrate that dissipation can facilitate FB preparation, property measurement, and utilization. This opens a new avenue for exploring FB physics in open quantum systems, with potential implications for strongly correlated physics.

quant-ph↗

arXiv2025

Graph Generation Powered with LLMs for Boosting Multivariate Time-Series Representation Learning

Sourced from multiple sensors and organized chronologically, Multivariate Time-Series (MTS) data involves crucial spatial-temporal dependencies. To capture these dependencies, Graph Neural Networks (GNNs) have emerged as powerful tools. As explicit graphs are not inherent to MTS data, graph generation becomes a critical first step in adapting GNNs to this domain. However, existing approaches often rely solely on the data itself for MTS graph generation, leaving them vulnerable to biases from small training datasets. This limitation hampers their ability to construct effective graphs, undermining the accurate modeling of underlying dependencies in MTS data and reducing GNN performance in this field. To address this challenge, we propose a novel framework, K-Link, leveraging the extensive universal knowledge encoded in Large Language Models (LLMs) to reduce biases for powered MTS graph generation. To harness the knowledge within LLMs, such as physical principles, we design and extract a \textit{Knowledge-Link graph} that captures universal knowledge of sensors and their linkage. To empower MTS graph generation with the knowledge-link graph, we further introduce a graph alignment module that transfers universal knowledge from the knowledge-link graph to the graph generated from MTS data. This enhances the MTS graph quality, ensuring effective representation learning for MTS data. Extensive experiments demonstrate the efficacy of K-Link for superior performance on various MTS tasks.

cs.AI↗

arXiv2025

Temporal Source Recovery for Time-Series Source-Free Unsupervised Domain Adaptation

Time-Series (TS) data has grown in importance with the rise of Internet of Things devices like sensors, but its labeling remains costly and complex. While Unsupervised Domain Adaptation (UDAs) offers an effective solution, growing data privacy concerns have led to the development of Source-Free UDA (SFUDAs), enabling model adaptation to target domains without accessing source data. Despite their potential, applying existing SFUDAs to TS data is challenging due to the difficulty of transferring temporal dependencies, an essential characteristic of TS data, particularly in the absence of source samples. Although prior works attempt to address this by specific source pretraining designs, such requirements are often impractical, as source data owners cannot be expected to adhere to particular pretraining schemes. To address this, we propose Temporal Source Recovery (TemSR), a framework that leverages the intrinsic properties of TS data to generate a source-like domain and recover source temporal dependencies. With this domain, TemSR enables dependency transfer to the target domain without accessing source data or relying on source-specific designs, thereby facilitating effective and practical TS-SFUDA. TemSR features a masking recovery optimization process to generate a source-like distribution with restored temporal dependencies. This distribution is further refined through local context-aware regularization to preserve local dependencies, and anchor-based recovery diversity maximization to promote distributional diversity. Together, these components enable effective temporal dependency recovery and facilitate transfer across domains using standard UDA techniques. Extensive experiments across multiple TS tasks demonstrate the effectiveness of TemSR, which even surpasses existing TS-SFUDA methods that require source-specific designs.

cs.LG↗

arXiv2025

Deep Domain Adaptation for Turbofan Engine Remaining Useful Life Prediction: Methodologies, Evaluation and Future Trends

Remaining Useful Life (RUL) prediction for turbofan engines plays a vital role in predictive maintenance, ensuring operational safety and efficiency in aviation. Although data-driven approaches using machine learning and deep learning have shown potential, they face challenges such as limited data and distribution shifts caused by varying operating conditions. Domain Adaptation (DA) has emerged as a promising solution, enabling knowledge transfer from source domains with abundant data to target domains with scarce data while mitigating distributional shifts. Given the unique properties of turbofan engines, such as complex operating conditions, high-dimensional sensor data, and slower-changing signals, it is essential to conduct a focused review of DA techniques specifically tailored to turbofan engines. To address this need, this paper provides a comprehensive review of DA solutions for turbofan engine RUL prediction, analyzing key methodologies, challenges, and recent advancements. A novel taxonomy tailored to turbofan engines is introduced, organizing approaches into methodology-based (how DA is applied), alignment-based (where distributional shifts occur due to operational variations), and problem-based (why certain adaptations are needed to address specific challenges). This taxonomy offers a multidimensional view that goes beyond traditional classifications by accounting for the distinctive characteristics of turbofan engine data and the standard process of applying DA techniques to this area. Additionally, we evaluate selected DA techniques on turbofan engine datasets, providing practical insights for practitioners and identifying key challenges. Future research directions are identified to guide the development of more effective DA techniques, advancing the state of RUL prediction for turbofan engines.

cs.LG↗

arXiv2025

InfiAgent: Self-Evolving Pyramid Agent Framework for Infinite Scenarios

Large Language Model (LLM) agents have demonstrated remarkable capabilities in organizing and executing complex tasks, and many such agents are now widely used in various application scenarios. However, developing these agents requires carefully designed workflows, carefully crafted prompts, and iterative tuning, which requires LLM techniques and domain-specific expertise. These hand-crafted limitations hinder the scalability and cost-effectiveness of LLM agents across a wide range of industries. To address these challenges, we propose \textbf{InfiAgent}, a Pyramid-like DAG-based Multi-Agent Framework that can be applied to \textbf{infi}nite scenarios, which introduces several key innovations: a generalized "agent-as-a-tool" mechanism that automatically decomposes complex agents into hierarchical multi-agent systems; a dual-audit mechanism that ensures the quality and stability of task completion; an agent routing function that enables efficient task-agent matching; and an agent self-evolution mechanism that autonomously restructures the agent DAG based on new tasks, poor performance, or optimization opportunities. Furthermore, InfiAgent's atomic task design supports agent parallelism, significantly improving execution efficiency. This framework evolves into a versatile pyramid-like multi-agent system capable of solving a wide range of problems. Evaluations on multiple benchmarks demonstrate that InfiAgent achieves 9.9\% higher performance compared to ADAS (similar auto-generated agent framework), while a case study of the AI research assistant InfiHelper shows that it generates scientific papers that have received recognition from human reviewers at top-tier IEEE conferences.

cs.AI↗

arXiv2025

Explaining Fine Tuned LLMs via Counterfactuals A Knowledge Graph Driven Framework

The widespread adoption of Low-Rank Adaptation (LoRA) has enabled large language models (LLMs) to acquire domain-specific knowledge with remarkable efficiency. However, understanding how such a fine-tuning mechanism alters a model's structural reasoning and semantic behavior remains an open challenge. This work introduces a novel framework that explains fine-tuned LLMs via counterfactuals grounded in knowledge graphs. Specifically, we construct BioToolKG, a domain-specific heterogeneous knowledge graph in bioinformatics tools and design a counterfactual-based fine-tuned LLMs explainer (CFFTLLMExplainer) that learns soft masks over graph nodes and edges to generate minimal structural perturbations that induce maximum semantic divergence. Our method jointly optimizes structural sparsity and semantic divergence while enforcing interpretability preserving constraints such as entropy regularization and edge smoothness. We apply this framework to a fine-tuned LLaMA-based LLM and reveal that counterfactual masking exposes the model's structural dependencies and aligns with LoRA-induced parameter shifts. This work provides new insights into the internal mechanisms of fine-tuned LLMs and highlights counterfactual graphs as a potential tool for interpretable AI.

cs.LG↗

arXiv2025

Unraveling the Redox Mechanisms Underlying FLASH Radiotherapy: Critical Dose Thresholds and NRF2-Driven Tissue Sparing

FLASH radiotherapy (FLASH-RT) achieves tumor control comparable to conventional dose-rate irradiation (CONV-RT) while significantly reducing radiation damage to normal tissues. However, the physical conditions triggering the FLASH sparing effect remain unclear, and mechanisms related to oxidative stress and redox regulation are poorly understood. This study utilizes a murine acute intestinal toxicity model to investigate how beam parameters influence the FLASH sparing effect and tumor control using innovative FLASH-RT and CONV-RT combined irradiation. Results demonstrate for the first time that a substantially reduced FLASH dose can still elicit sparing effect, provided a total dose threshold is met. Kinetic simulation and experimental validation demonstrate that FLASH-RT enhances peroxyl radical recombination, reducing reactive oxygen species (ROS) and malondialdehyde levels. Antioxidant interventions further confirm the essential role of free radicals. RNA sequencing and molecular analyses reveal that FLASH-RT activates the nuclear factor E2-related factor 2 (NRF2) antioxidant pathway while suppressing extracellular signal-regulated kinases (ERK) signaling, thereby enhancing cellular redox defenses, reducing apoptosis, and mitigating ROS-mediated tissue injury. These findings highlight the feasibility of optimizing the FLASH-RT therapeutic window through redox modulation and provide a foundation for developing free radical-targeted strategies to improve its therapeutic efficacy.

physics.med-ph↗

arXiv2025

Handling Students Dropouts in an LLM-driven Interactive Online Course Using Language Models

Interactive online learning environments, represented by Massive AI-empowered Courses (MAIC), leverage LLM-driven multi-agent systems to transform passive MOOCs into dynamic, text-based platforms, enhancing interactivity through LLMs. This paper conducts an empirical study on a specific MAIC course to explore three research questions about dropouts in these interactive online courses: (1) What factors might lead to dropouts? (2) Can we predict dropouts? (3) Can we reduce dropouts? We analyze interaction logs to define dropouts and identify contributing factors. Our findings reveal strong links between dropout behaviors and textual interaction patterns. We then propose a course-progress-adaptive dropout prediction framework (CPADP) to predict dropouts with at most 95.4% accuracy. Based on this, we design a personalized email recall agent to re-engage at-risk students. Applied in the deployed MAIC system with over 3,000 students, the feasibility and effectiveness of our approach have been validated on students with diverse backgrounds.

cs.CL↗

arXiv2025

Dissipation-induced Half Quantized Conductance in One-dimensional Topological Systems

Quantized conductance from topologically protected edge states is a hallmark of two-dimensional topological phases. In contrast, edge states in one-dimensional (1D) topological systems cannot transmit current across the insulating bulk, rendering their topological nature invisible in transport. In this work, we investigate the transport properties of the Su-Schrieffer-Heeger model with gain and loss, and show that the zero-energy conductance exhibits qualitatively distinct behaviors between the topologically trivial and nontrivial phases, depending on the hybridization and dissipation strengths. Crucially, we analytically demonstrate that the conductance can become half-quantized in the topologically nontrivial phase, a feature absent in the trivial phase. We further show that the half quantization predominantly originates from transport channels involving gain/loss and edge states. Our results uncover a new mechanism for realizing quantized transport in 1D topological systems and highlight the nontrivial role of dissipation in enabling topological signatures in open quantum systems.

cond-mat.mes-hall↗