arXiv subjects

Yuxuan Chen

Publications and source records attributed to Yuxuan Chen.

At least 19 recordsLinked to original sources

arXiv2026

TV-AudioRemover: Joint Text-Visual Guided Sound Removal with Multi-Task Hard-Mixture Curriculum

Visual object removal can eliminate a target from video frames, yet its acoustic trace persists in the soundtrack, causing obvious audio-visual inconsistency. Existing video inpainting models operate solely on pixels, while audio editing models, especially for the sound removal task, are typically driven by text and therefore rely on limited single-modal control, which is less effective than multimodal guidance that provides stronger semantic grounding and temporal synchronization cues. In this paper, we present Text-Visual Guided Sound Removal (TV-AudioRemover), a target sound removal framework that leverages the visually edited video together with a natural-language instruction to suppress the sound associated with the removed visual object from the original audio mixture. To acquire high-quality training data, we devise a pipeline to construct a million-scale dataset of single-object audio-visual aligned samples, from which we synthesize mixture-target pairs customized for model training. To effectively leverage visual context and follow instruction intent, we augment the model architecture with task tokens, generalizable instruction modeling, and modality-specific global guidance. We further adopt multi-task training to strengthen task-role comprehension, and employ a hard-mixture curriculum that leverages semantically similar acoustic mixtures during fine-tuning to enhance fine-grained source discrimination. To support evaluation, we present AV-Remove-Bench, a comprehensive audio-visual object removal benchmark, along with dedicated objective metrics and an MLLM-based evaluation protocol. Experiments demonstrate that our method achieves state-of-the-art performance on both subjective and objective metrics. Project page: https://yjx-research.github.io/TV-AudioRemover/.

cs.MM↗

arXiv2026

PyRUA-DataFarm: LLM Agent as a Cost-Efficient Teleoperator for Real-Ready Robot Data

Teleoperation remains the default way to collect robot demonstrations, but every episode costs robot and operator time, and every new task starts from scratch. We ask whether a coding agent can take over the teleoperator's job. In our DataFarm, the agent receives a data request and one calibration episode of the robot in the target scene and rebuilds the task in simulation: it writes the scene, an expert controller, and a success judge. The simulator supplies exact actions, and a video model conditioned on real images renders each rollout as photographic video, generating all camera views together consistently. The output is real-ready data: synchronized camera views labelled with the robot's actions, on which a policy can be trained directly and deployed on the real robot. Independent judges certify the expert and every rendered episode before admission. On five real-robot tasks, policies trained only on farm data match policies trained on as many teleoperated episodes (93 vs. 84 successes in 100 trials), and under an unseen tablecloth and coloured light they keep 87 successes where the teleoperation-trained policies fall to 46. Adapting a task is fully automatic and costs \$21 of API usage on average, paid once per task, plus \$5 for a render contract; every further episode costs \$0.80 on average for simulation, rendering, and review, with no robot or operator. One hour of three-view data for a task costs \$107 on average, these costs included, slightly below a quote of \$117 for teleoperation in China and below \$290 in labour alone in North America.

cs.RO↗

arXiv2026

Customizing Wireless Channels via Intelligent Reflecting Surfaces: Feasibility, Fundamental Limits, and Constructive Design

By adjusting their reflection coefficients, intelligent reflecting surfaces (IRSs) can reshape the channels between a base station (BS) and user equipment (UE). Existing studies mainly optimize IRS phase-shifts for communication objectives, leaving the physical attainability of prescribed IRS-reflected channels largely unexplored. This paper investigates channel customization with a phase-only IRS under three progressively relaxed criteria. Observing that the customization mean-squared error (MSE) has the same mathematical form as the signal MSE of a point-to-point multiple-input multiple-output system, we construct a counterpart problem to characterize individual singular-coordinate gain limits and the condition for attaining the amplitude-matching upper bound. To address multi-stream phase conflicts, we analyze principal contribution area (PCA) overlap and derive sufficient array-size conditions for disjoint PCAs under a specified focused-vector construction with parallel uniform linear arrays. We also derive necessary conditions from the two propagation links' singular values and an array-size restriction under the parallel-array Fresnel model. Both the restriction and the construction involve the BS--IRS array-size product. Numerical results show that jointly selecting right singular vectors and IRS phase-shifts reduces mean customization MSE, whereas gains exceeding propagation spectral limits cannot be realized exactly. These results provide design guidance and highlight spectral limits of phase-only IRS channel customization.

cs.IT↗

arXiv2026

AI Cosmos: An Agentic Infra for Situated Learning

Large language models (LLMs) can improve task performance during learning, yet these gains do not necessarily reflect learners' ability to thereafter apply the knowledge and skills independently. We present AI Cosmos, an agentic infrastructure for situated learning that organizes learning around two complementary principles: scenario-based participation and cumulative assets of practice. AI Cosmos organizes learners and role-specialized agents within learning scenarios that integrate task-relevant knowledge and, when needed, executable workbenches. An asset-memory loop preserves the processes and outcomes of practice as reusable assets with explicit provenance and dependencies. We evaluate scenario-based interaction through two preregistered randomized controlled studies examining the acquisition of legal reasoning and programming competence, holding the same underlying LLM across conditions. AI Cosmos achieves greater learning gains than a conventional LLM in legal reasoning and higher mastery of unseen programming problems than an LLM-as-Teacher baseline.

cs.CL↗

arXiv2026

LociArt: A Unified Paradigm for Free-Style Local Video Stylization

Video stylization typically transforms entire scenes, while local artistic editing requires precise region--style association, spatial control, and temporal consistency. We introduce LociArt, a unified paradigm for free-style local video stylization that explicitly specifies where to stylize and what style to apply while preserving non-target content. At its core, GRNStyle builds on Generative Refinement Networks (GRN) and introduces a polar style-aware mask that embeds style identities as equal-norm directions within selected regions. Complementary representation--geometry conditioning combines encoded mask features with raw-mask spatial support, integrating spatiotemporal context with geometric control. To provide paired supervision, we develop an automated pipeline combining global stylization, video object removal, matting, and compositing, and construct the LociArt-100K Dataset with 100K local stylization pairs. We further establish the LociArt Benchmark, comprising 80 source videos and 84 target masks covering 168 foreground/background stylization cases, with a Style Prototype Similarity (SPS) evaluation scheme for regional style quality and complementary measures of non-target preservation and temporal consistency. Experiments show that GRNStyle outperforms existing methods in regional style quality and spatial control while maintaining strong temporal consistency. Qualitative examples further illustrate joint stylization of multiple regions with the same or different learned styles, despite training only on single-region, single-style pairs. Together, these components provide a unified foundation for learning and evaluating controllable local video stylization. Project page: https://higherhu.github.io/lociart/.

cs.CV↗

arXiv2026

FAMIR: Future-aligned latent dynamics for complex-flow forecasting

Learned flow surrogates are applied recursively, so errors in phase, amplitude and transport accumulate as each prediction feeds the next. During training, however, the realized next state is known. We propose Future-Aligned Motion Inference for Recursive Physical Forecasting (FAMIR), which uses this realized future to shape the signal that drives the update, not only the predicted state. On the latent grid of a frozen autoencoder, a future-conditioned teacher and a history-only student infer motion tensors that condition one shared residual transition. Posterior--Prior Motion Alignment (PPMA) jointly aligns the teacher (posterior) and student (prior) motions, prediction-fed multistep objectives train the student on its own rollouts, and only the student is deployed. On viscoelastic channel flow, Rayleigh--Bénard convection and planetary shallow-water flow, FAMIR achieves lower complete-prefix normalized root-mean-square error than three direct latent predictors of comparable size and a delay-embedded linear reference at ten steps (1.003\%, 1.055%, 0.620%) and twenty steps (1.661%, 1.683%, 1.036%). Its advantage is largest at the first step in the viscoelastic flow and grows with lead time in the other flows. Over forty-step forecasts, FAMIR keeps fluctuation profiles and probability densities closer to the reference than the direct predictors. Without the teacher, the motion-conditioned student already outperforms the direct predictors; in the shallow-water flow, prediction-fed rollouts are decisive and joint alignment is far more effective than distillation toward a fixed teacher (1.036% against 1.874%). Fixed-state interventions show that the trained update relies on the state-specific motion, and the deployed student matches the one-step accuracy of the future-informed teacher.

physics.flu-dyn↗

arXiv2026

Large deviations from a stable steady state for damped dispersive PDEs with vanishing random kicks

We study the behaviour of stationary measures for a class of dispersive PDEs damped by a linear zero-order term and perturbed by a small kick noise. Under some natural assumptions on the law of the noise, we prove that any family of stationary measures satisfies the large deviation principle in the vanishing noise limit. The result highlights the role of nonlinear smoothing and applies to the nonlinear Schrödinger and Korteweg-de Vries equations, and to a variety of random perturbations including Gaussian and exponential variables.

math.PR↗

arXiv2026

Physics-Informed Koopman Learning for Data-Efficient System Identification of Automated Vehicle Dynamics

Understanding how a particular automated vehicle reacts to nearby traffic can improve motion prediction, control development, traffic simulation, and safety evaluation. However, commercial automated driving systems are proprietary, and single encounters may provide only a few seconds of noisy data. Standard physical models are interpretable but inflexible, whereas neural models are often data-hungry. We propose a physics-informed Koopman framework that combines a calibrated car-following law with a correction learned from the observations. A weak-form estimator learns this correction from velocity measurements integrated over time, avoiding noise-sensitive numerical differentiation. The resulting continuous-time model predicts the follower's response and provides interpretable measures of driving behavior. Experiments on OpenACC and CATS-CF evaluate 5-, 7-, and 11-second histories. Averaged over these histories, the constant-time-headway branch reduces speed prediction error by 16.0% and 15.4% on OpenACC and CATS-CF, respectively, relative to the best neural baselines. The PI-Koopman branches achieve the lowest mean speed and gap errors among the physical and neural comparators. Weak-form estimation reduces acceleration-field reconstruction error by 74.5% in noisy known-law simulations and noise-induced field perturbation by 91.6% in paired real-vehicle measurements. The same PI-Koopman system identification supports following-mode recognition with an approximately eleven-fold difference in median residual variance between human drivers and automated vehicles, and a single residual threshold achieves 85.4% balanced accuracy. The branch informed by the intelligent driver model takes a median 17 to 26 ms for identification and forecasting on the tested central processing units, supporting frequent target adaptation.

eess.SY↗

arXiv2026

Beyond Two Tracks: Speaker-Anchored Full-Duplex Dialogue Recovery

Spoken interaction is moving from alternating turns to full-duplex conversation, where an agent listens while speaking. Learning this coordination requires natural dialogue with persistent speaker-resolved tracks, a data requirement that remains difficult to satisfy at scale. Generative recovery offers a route from ordinary recordings, but recovering two voices is not enough: their track assignments can drift as the conversation unfolds. We address this missing link with speaker-anchored routing before diffusion: a 1.84M-parameter module matches the separator's coarse streams to fixed enrollment identities and orders them before a frozen generator reconstructs the speech, without retraining the generator or altering the reconstructed audio. On 25-minute remote conversations, routing cuts wrong-track time from 43.9% to 4.1%, below the 6.2% of matched-enrollment waveform re-identification, with its largest advantage when one participant holds the floor (17.8% versus 28.6%), and raises fixed-track activity F1 from 0.46 to 0.84 while per-chunk reconstruction quality is unchanged. The same router transfers to unseen face-to-face and telephone recordings, and a margin-gated verification step brings their wrong-track time to 0.9-1.7% while embedding 20-36% of the output, where full re-identification embeds all of it. Recovered voices thus become the participant-consistent tracks that full-duplex dialogue modeling needs. Audio examples: https://elpsykongloo.github.io/beyond-two-tracks/

cs.SD↗

arXiv2026

Knowledge-Guided Construction of Machine Learning Potentials for Reactive Behavior in Energetic Materials

Energetic materials involve multiple interactions, making reliable machine-learning potentials (MLPs) difficult to construct without extensive datasets. Here, we enhance the ability of the neural network interatomic potential (NNAP) to describe molecular systems using sphmulti, a refined spherical-harmonic basis set that combines extra radial basis with element-specific chemical weighting in each radial channel. We further integrate hyperactive learning, farthest-point sampling, and iterative sufficiency criteria with knowledge-guided key events, enabling the NNAP to retain essential information for describing the material system. For 3,3'-diamino-4,4'-azoxyfurazan, the resulting NNAP is trained on only 13,680 configurations yet captures key properties, including the isomerization barrier, pyrolysis activation energy, and shock Hugoniot behavior. NNAP-driven molecular dynamics simulations further reveal that pyrolysis proceeds through furazan-ring opening followed by chain reactions, whereas shock loading induces anisotropic hydrogen transfer driven by interlayer structural deformations. This work enables efficient and reliable MLPs for energetic materials.

cond-mat.mtrl-sci↗

arXiv2026

Directed impulsive molecular dynamics reveal energy-routing pathways of bond cleavage in TATB

Responses of energetic materials to external stimuli involve more than uniform thermalization. Understanding directional energy redistribution is essential for structural and ignition design. Here, we use TATB as an example to construct a vibrationally faithful machine-learning potential from only 4,630 configurations. To resolve the elusive nonequilibrium energy flow, we develop directed impulsive molecular dynamics, a statistically controlled protocol that repeatedly deposits equal kinetic energy along selected vibrational modes. By amplifying mode-specific responses while tracking the ensuing nonequilibrium evolution, this approach turns energy redistribution into a directly traceable routing process. We find that initial bond cleavage depends strongly on the initially excited mode, rather than being determined by bond-cleavage barriers alone. Specifically, modes that readily trigger reaction efficiently channel energy towards a bond cleavage coordinate, whereas modes that are less effective at inducing break divert energy into soft-like modes or trap it in modes from which energy flow is inefficient.

cond-mat.mtrl-sci↗

arXiv2026

Reference-Guided Turn-Taking Style Transfer for Full-Duplex Spoken Language Models

Full-duplex spoken language models decide at every frame whether to take the floor, defining a conversational personality -- yet each set of weights encodes exactly one, which human speakers bracket rather than share. Existing controls mostly act from outside; none identifies the quantity that sets how much the model speaks. We identify it: a single late-layer residual-stream direction, the initiative vector, extracted from the model's own conversations without training or annotation. The same direction reads the decision, anticipating onsets up to 800 ms ahead, and shifts it: scaled during generation, it moves speech ratio from 6-12% to 42-61% (no steering: 21-30%), consistently across conversations, weights, and corpora. A short reference recording suffices to transfer a speaker's turn-taking style to the model, and the transfer is reference-specific: swapping in another speaker's reference worsens the match in 93-98% of cases, whereas the best uniform dose is indistinguishable from no steering. Turn-taking style is not frozen into the weights but a direction that can be read, shifted, and calibrated per person. Audio examples are available at https://elpsykongloo.github.io/initiative-vector/.

cs.CL↗

arXiv2026

RFWeave: Learning Wireless Propagation Across Scenes and Transceiver Configurations

Wireless propagation modeling is foundational to the evaluation and design of modern communication systems. To achieve accurate wireless propagation prediction, recent learning-based approaches leverage scene geometry and materials, demonstrating promising generalization across transceiver locations and unseen scenes. However, these approaches remain largely confined to a fixed configuration of array size, receiver orientation, and transmit beam. In this work, we introduce RFWeave, a learned wireless propagation model designed to generalize across scenes, transceiver locations, and transceiver configurations. To accommodate varying array structures, RFWeave incorporates variable-length transceiver tokens that represent antenna elements individually. Furthermore, to capture the geometry between transmit and receive antenna elements, RFWeave aggregates their pairwise spatial relations into propagation tokens. A configuration-conditioned decoder predicts the spatial spectrum and received power. RFWeave is trained on a large-scale simulated dataset spanning 10,000 indoor scenes and more than 5 million channel records under diverse transceiver configurations. Extensive evaluations show that RFWeave achieves state-of-the-art performance across all evaluated generalization settings, improving spatial spectrum structural similarity (SSIM) by up to 15.7% and reducing received power mean absolute error (MAE) by up to 35.4% over the strongest baselines on unseen scenes. Additional experiments on measured DICHASUS data and in beam management further demonstrate RFWeave's broader applicability to real-world channels and downstream wireless tasks.

eess.SP↗

arXiv2026

Adaptive Role Assignment and Controlled Feature Reconstruction for Federated Image Semantic Communication

Hybrid federated semantic communication enables user equipment (UEs) to contribute model updates or semantic features under a shared training framework. However, heterogeneous role costs and the interaction between model aggregation and feature reconstruction (FR) remain key challenges in practical radio access network (RAN) deployment. To address these issues, we propose ARC-FedSC, a RAN-aware framework that coordinates UE role assignment and server-side controlled FR under a fixed communication budget. Within ARC-FedSC, RAN Aware Role-Bandit learns the historical contribution of UEs in different roles together with current uplink conditions, while Temporal Consistency Alignment (TCA) regulates FR according to recent model aggregation directions. Experiments on CIFAR-10 with time-varying RAN channels show that ARC-FedSC outperforms baselines across all five tested role configurations in the later training stage, with the best configurations achieving about 24.17 dB average PSNR over the last 20 rounds. Component level results further show that Role-Bandit maintains an average rolling UE coverage of 85.3%, compared with about 65.7% for baseline, while TCA reduces the probability of harmful FR events from 0.245 to 0.093, corresponding to a 62.0% reduction. Ablation and sensitivity studies further support the effectiveness and robustness of the proposed design.

cs.LG↗

arXiv2026

MAP4CS: A Multi-dimensional Data Pruning Framework for Efficient Code Retriever Fine-tuning

Retrieval-Augmented Generation (RAG) has become a cornerstone in software engineering for enhancing Large Language Models (LLMs) with domain-specific knowledge. However, adapting retrievers to evolving code repositories remains challenging due to the noise and redundancy inherent in massive code corpora. Standard fine-tuning on the full corpus is computationally expensive and often leads to sub-optimal performance due to negative transfer from low-quality samples. Conversely, simple random sampling fails to guarantee data representativeness. To address these challenges, we propose MAP4CS (Multi-dimensional Awareness Pruning for Code Search), an adaptive data pruning framework. MAP4CS identifies a small, high-quality core subset by integrating syntactic structure, semantic diversity, and distributional representation, followed by a rigorous rule-based filtering pipeline. Extensive experiments on two large-scale datasets demonstrate that MAP4CS consistently outperforms random sampling baselines using only 5% of the training data. Remarkably, it achieves performance comparable to, or even superior to, fine-tuning on the full dataset, validating the ''less is more'' hypothesis in data-centric AI. Furthermore, linguistic analysis reveals an adaptive optimization mechanism: MAP4CS automatically functions as a de-duplicator for redundant corpora and a denoiser for chaotic ones, constructing a training corpus that is both lexically diverse and information-dense.

cs.SE↗

arXiv2026

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

Autoregressive generation in large language models (LLMs) conventionally decodes from the final layer, assuming that deeper representations yield more reliable next-token predictions. We revisit this assumption by revealing a recurring Guess-Refine-Perturb dynamic: early layers form coarse guesses, intermediate layers refine reasoning-relevant semantics, and final layers can perturb these refined predictions toward generic or alignment-preferred tokens. We introduce Confident Decoding, a training-free decoding strategy that dynamically selects the most reliable near-final layer through entropy-guided conservative backward search. We further provide a theoretical formulation of layer selection as an optimal stopping problem, showing that under bounded projection noise and dominant late-stage alignment perturbation, our search rule filters perturbation while bounding the loss relative to the oracle refinement layer. Experiments across dense and Mixture-of-Experts LLMs demonstrate consistent gains on challenging reasoning benchmarks, including GPQA-Diamond, Omni-MATH, and HLE, with zero memory overhead and less than 2% latency increase. These results suggest dynamically bypassing final-layer perturbations can unlock stronger reasoning behavior from aligned LLMs.

cs.CL↗

arXiv2026

Adaptive Client Clustering and Coordination for Federated Learning Workflow Management in Edge Networks

Federated learning (FL) is increasingly deployed as a managed learning service rather than as a set of isolated training jobs. In networked edge environments, dependent FL service flows must coordinate heterogeneous clients, non-IID data, fluctuating communication latency, and precedence-constrained tasks under service-level completion requirements. These coupled factors make participant management central to both time-totarget performance and learning stability. This paper proposes A-CoDa, an adaptive clustered coordination framework for managing dependent FL flows. A-CoDa first uses label-distribution divergence (LDD)-based greedy-balanced clustering to construct statistically coherent and size-aware client groups, which serve as a scalable management abstraction. Building on this structure, we design FedMIX, an uncertainty-aware intra-/inter-cluster participation mechanism that ranks clients by a loss-latency-uncertainty utility and adaptively controls cross-cluster probing according to training progress and latency conditions. A dependency-aware DAG scheduler then orchestrates layer-wise task execution so that parallelism and precedence constraints are jointly respected. We further provide a convergence analysis that frames the result as a sufficient loss-domain design bound, explicitly relating the attainable error floor and sufficient communication rounds to LDDinduced sampling mismatch, residual distribution shift, local-SGD drift, stochastic variance, and adaptive probing budgets. Experiments on handwriting, wearable-sensing, product-image, and medical-imaging tasks evaluate A-CoDa under dependent FL workflows and demonstrate its effectiveness in reducing end-toend completion time while maintaining competitive accuracy.

cs.DC↗

arXiv2026

Learner-Centered Design of Educational Tools for Cross-Expertise Technical Communication in Computing Contexts

Cross-expertise technical communication (i.e., communicating about computing topics across levels of computing expertise) is important for workplace collaboration. However, students are underprepared because computing education rarely explicitly teaches communication, and available practice tends to occur among peers with similar expertise. We take a learner-centered design approach to inform technologies for developing these skills. We interviewed 12 industry professionals and conducted focus group and co-design sessions with 14 college students preparing for computing-related roles. Professionals emphasized adapting communication, negotiating expectations, building shared understanding, and using multiple modalities and artifacts. Students anticipated challenges adapting communication, navigating unfamiliar workplace dynamics, and communicating under fear of judgment, and valued rich, realistic practice environments that preserved their psychological safety. Synthesizing professional and learner perspectives with educational theory, we conclude that building self-efficacy through authentic mastery experiences and changing attitudes related to help-seeking are critical elements for educational technology design in this context.

cs.HC↗