arXiv subjects

Yu Zhang

Publications and source records attributed to Yu Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2026

LLM-based User-Product Relevance Evaluation for Dynamic Product Advertising

Dynamic Product Advertising (DPA) retrieval systems are a core component of modern e-commerce advertising; however, their evaluation remains challenging. Conventional offline engagement metrics are limited by sparse, biased feedback, while online evaluation is costly and time-consuming. In this work, we propose a user--product relevance metric for offline evaluation of DPA retrieval systems. The metric first compresses the engagement history into a compact set of intent representatives via Semantic-ID-grouped, event-stratified segmentation, then assesses the relevance of a recommended product to each individual intent and aggregates them as a user-level relevance score, yielding a stable and interpretable measure of retrieval quality. To compute this metric at scale, we leverage large language models (LLMs) as semantic relevance judges, capturing nuanced functional and semantic relationships that heuristic methods often miss. We propose an agentic, human-aligned prompting framework that generates multi-category relevance guidelines and distills teacher-model judgments into an efficient student model for scalable evaluation. The resulting metric strongly correlates with offline and online business metrics, enabling faster and more reliable DPA retrieval iteration before A/B testing.

cs.IR↗

arXiv2026

Two Birds One Stone: Effective Static Detection of Resource and Communication Deadlocks in Rust Programs

Although Rust claims to enable fearless concurrency, concurrency errors remain prevalent in practical applications, with deadlocks particularly prominent and harmful. Current static deadlock detection techniques either do not cater to Rust programs without incorporating Rust semantics or solely concentrate on resource deadlocks, disregarding communication deadlocks. In this paper, we present RcChecker, the first static detection method that simultaneously targets resource and communication deadlocks for Rust. At its core, RcChecker introduces the signal-lock graph to characterize the interactions between threads through lock variables and condition variables. The construction of the signal-lock graph involves utilizing flow-sensitive and context-sensitive analyses to track variable lifetime details and abstracting actions associated with condition variables into signal resource holdings and requests. By examining cycles within the signal-lock graph, we can effectively identify resource and communication deadlocks in a unified way. Compared to the existing Rust deadlock detection tool, RcChecker effectively eliminates eight resource deadlock false positives and detects seventeen errors that the existing tool fails to identify. Furthermore, RcChecker reports seven previously undiscovered issues in real-world Rust applications, including two resource deadlocks and five communication deadlocks.

cs.PL↗

arXiv2026

Heterogeneous-Modal Unsupervised Domain Adaptation via Latent Space Bridging

Unsupervised domain adaptation (UDA) effectively bridges the domain gap between a labeled source domain and an unlabeled target domain, but assumes that the two domains share the same modality. Heterogeneous domain adaptation (HDA) instead handles different feature spaces across domains, yet requires labeled target samples or paired data linking the source and target domains. Neither applies when a labeled source domain and a fully unlabeled target domain each hold an entirely distinct modality (e.g., 2D images and 3D point clouds). To address this limitation, we introduce a new setting termed Heterogeneous-Modal Unsupervised Domain Adaptation (HMUDA), which transfers knowledge across modalities via an unlabeled bridge domain containing paired observations from both modalities, whose distribution may deviate from those of the source and target domains. To learn under the HMUDA setting, we propose Latent Space Bridging (LSB), a dual-branch framework where a feature consistency loss on paired bridge samples closes the modality gap and a class-centroid alignment loss reduces the source-target discrepancy. Extensive experiments on eight benchmark settings covering both 2D-to-3D and 3D-to-2D transfer demonstrate that LSB achieves state-of-the-art performance.

cs.CV↗

arXiv2026

Being-M0.7: A Latent World-Action Model for Humanoid Robots

Humanoid loco-manipulation requires coordinated locomotion and manipulation informed by future scene evolution and whole-body motion, yet learning these capabilities is constrained by scarce robot demonstrations. Human video and motion datasets offer scalable supervision, but many contain only video or motion rather than paired video-motion data. Moreover, human motion does not directly specify executable robot actions. We present Being-M0.7, a latent world-action model that transfers visual-motion priors learned from mixed-modality human data to humanoid control through pre-training, robot mid-training, and action post-training. We curate a corpus from more than 10,000 hours of raw human-centric data, integrating video-only, motion-only, and paired video-motion streams to learn complementary visual dynamics and whole-body kinematic structure. Joint prediction of future latent visual states and motion encourages visual representations to encode future kinematics. Robot mid-training adapts this coarse-grained prior to robot viewpoints and body dynamics. During action post-training, an action expert combines visual predictive representations from the frozen, adapted prior with current images and proprioception through gated cross-attention, grounding predictive context in executable whole-body commands. Being-M0.7 achieves the highest aggregate success rate among the compared baselines on SIMPLE and matches the strongest baseline on real-world Unitree G1 loco-manipulation tasks.

cs.RO↗

arXiv2026

YOCO: You Only Calibrate Once! Fast Mocap Calibration for Dexterous Teleoperation

Dexterous teleoperation requires reliable human-hand state estimations. However, common low-cost motion-capture gloves and markerless trackers often exhibit biases that vary across users, glove fit, and recording sessions, degrading retargeting and demonstration quality. We present YOCO, a fast few-shot, fine-tuning-free calibration framework that corrects biased hand-pose streams from a small set of paired raw and target poses. Instead of optimizing a separate model for every operator or session, YOCO conditions a calibration HyperNet on the paired examples and predicts LoRA-style updates for a frozen MANO hand-estimation module, turning per-user calibration into a lightweight feed-forward adaptation step while preserving the geometric prior of MANO and the efficiency of a compact estimator. We train YOCO with synthetic drift augmentations on InterHand2.6M and evaluate on augmented InterHand sequences, offline real glove data, and dexterous teleoperation tasks. Across these settings, YOCO improves calibration efficiency, hand-state estimation quality and teleoperation performance compared with uncalibrated input and standard calibration baselines.

cs.RO↗

arXiv2026

Connected Self Forcing: Beyond Local Learning in Video Autoregression

To stream long videos while maintaining visual quality and temporal consistency, Self Forcing mitigates exposure bias through self-rollout training on self-generated histories with key-value (KV) caching. To keep memory manageable, it detaches historical caches, preserving forward dependencies between chunks but severing the backward gradient paths. We introduce Connected Self Forcing, a training framework that reconnects gradient paths across autoregressive chunks, allowing feedback from later predictions to guide how earlier context is generated. These connections go beyond historical KV-writing: gradients pass through generated latents into the computations that produced them, linking the generation of earlier context to its use in later predictions. To make this connected training memory-efficient, we develop shortcut gradient replay, which recovers cross-chunk gradients without retaining the full rollout computation graph. Integrated with distribution matching distillation, Connected Self Forcing trains historical chunks according to both their direct supervision and their contribution to subsequent generation. Experiments on autoregressive video generation show improvements in long-horizon visual quality and temporal consistency, without changing the inference procedure.

cs.CV↗

arXiv2026

MORPH: Generative Retrieval via Diffusion Transformer with Metric-Ordered Sequence Training and Hybrid-Policy Preference Optimization

Embedding-based retrieval typically returns highest-scoring items, but many production scenarios require items that satisfy a target attribute while preserving a fine-grained pattern expressed by seed examples. We formalize this as pattern-preserving attribute retrieval. Standard approaches fail: averaging seeds preserves the pattern but misses the attribute; global attribute retrieval drifts to unrelated patterns. We approach the task with continuous generative retrieval, where a model reads item-embedding sequences and generates query embeddings for nearest-neighbor search. We propose MORPH: Generative Retrieval via Diffusion Transformer with Metric-Ordered Sequence Training and Hybrid-Policy Preference Optimization, a staged framework with large-scale raw-sequence pretraining, Metric-Ordered Sequence (MOS) training, and final HPPO alignment. MOS construction turns sparse online metric labels into in-pattern trajectories; MOS CPT/SFT then trains the generator through shared multi-domain continuation pretraining and domain-specific tail-centroid supervised fine-tuning. HPPO uses a hybrid pool of static and policy-generated candidate embeddings, labels them with true online intersection metrics, applies iterated preference optimization, and employs a Pareto pair filter to exclude winners that lower pattern purity. Across four large-scale attribute domains under strict item- and pattern-holdout protocols, MOS training improves the primary intersection metric over a strong pretrained generative retriever in every domain-split cell, and the complete Pareto-filtered HPPO procedure improves it further, with paired-bootstrap-significant gains on seven of the eight cells - the exception being the D4 pattern-holdout split. Ablations confirm that the Pareto pair filter improves the attribute-pattern tradeoff on D1-D3, and that hybrid static/policy candidates are complementary.

cs.AI↗

arXiv2026

Benchmarking Time Series Foundation Models for Load Forecasting Under Covariate Uncertainty

Accurate short-term load forecasting (STLF) is essential for the reliable and efficient operation of modern power systems. While time series foundation models (TSFMs) have recently demonstrated remarkable performance across a wide range of forecasting tasks, their effectiveness for STLF under realistic operational conditions remains largely unexplored. In this paper, we present a comprehensive benchmark of four trained-from-scratch (TFS) models and four TSFMs across three real-world load forecasting datasets under operational scenarios that differ in the availability and quality of future covariate information. Our results show that Chronos-2 consistently achieves state-of-the-art performance in both zero-shot and fine-tuned settings when future covariates are available or accurately forecast. However, its performance degrades as covariate forecasts become increasingly noisy, whereas TimesNet exhibits greater robustness under severe covariate uncertainty. These findings demonstrate the effectiveness of covariate-informed TSFMs for STLF while highlighting the critical role of robust covariate modeling in real-world forecasting applications.

cs.LG↗

arXiv2026

Recursive Self-Improvement of Visuomotor Policies through Local Recovery Supervision

Visuomotor policies can execute familiar tasks yet lack the corrective behavior needed after their own mistakes. We present a framework for recursive self-improvement through local recovery supervision. Each round audits the current policy, generates corrective demonstrations at supported failure states, and uses them to update the policy that drives the next round of collection. An offline auditor locates unresolved failures using coarse and dense temporal evidence and specifies observable repair goals. A fixed multimodal agent acts as a tool-using teacher, generating recovery actions through observation, computation, execution, and feedback. The frozen student tests whether each teacher endpoint supports further progress. If continuation fails, the system restores that endpoint and extends the demonstration. Action-level quality assessment then defines continuous training windows with aligned observations, quality weights, and validity masks. Only the student is deployed. In a preliminary LIBERO-Goal study, recovery-augmented post-training achieves 88 successful episodes out of 100 validation scenes, compared with 78 for original-data continuation from the same $π_0$ checkpoint. An earlier BC-RNN study on robomimic Can improves success from 102/130 to 112/130 using 26 local recovery segments. Both comparisons match 2,000 additional optimization steps.

cs.RO↗

arXiv2026

IRSTD-Agent: Agentic Infrared Small Target Detection via Zoom-Guided Interaction Learning

Infrared small-target detection plays an important role in maritime monitoring and aerial surveillance. Although multimodal large language models (MLLMs) offer promising capabilities for visual understanding, existing MLLM-based approaches struggle to precisely localize infrared small targets. In this paper, we propose IRSTD-Agent, an agentic framework for infrared small target detection through dynamic visual search. The framework enables an MLLM to adaptively determine where and at what scale to inspect an image and progressively gather fine-grained visual evidence for precise target localization. Five complementary visual tools (PROPOSAL, ZOOM, DETECT, DROP and REFINE) support object candidate discovery, adaptive observation, target localization, hypothesis rejection, and target extent refinement, together enabling a coordinated search process over original-resolution images. To teach the MLLMs to conduct this search, we introduce Zoom-guided Interaction Learning, which uses annotation-derived interaction trajectories to supervise tool selection and the corresponding arguments. Through extensive experiments on WideIRSTD-Full and IRSTD-1k datasets, we demonstrate that IRSTD-Agent outperforms the evaluated vision-language models and enhances the precise localization capabilities of MLLMs in IRSTD tasks.

cs.CV↗

arXiv2026

ECG-WM: A Physiology-Informed ECG World Model for Clinical Intervention Simulation

Electrocardiogram (ECG)-based models have achieved strong performance in diagnostic tasks, yet they remain limited in modeling how cardiac dynamics evolve under external interventions. In particular, existing approaches focus primarily on static prediction and lack mechanisms to capture ECG variations under different pharmacological conditions. In this work, we propose an ECG World Model for action-conditioned predictive simulation of cardiac electrophysiology. Moving beyond disjoint pipelines, our framework features a principled integration of physiological ordinary differential equation (ODE) priors into latent diffusion dynamics via energy regularization. This structural constraint enables the synthesis of physiologically plausible post-intervention ECG trajectories while effectively mitigating generative hallucinations. Building on this simulation process, we introduce an uncertainty-aware evaluation strategy that leverages the stochasticity of diffusion sampling to characterize both the expected clinical risk and its variability, allowing a more reliable comparative assessment of candidate interventions. We evaluate our method across diverse settings, including controlled drug-response scenarios and real-world clinical records. Beyond standard waveform metrics, experimental results demonstrate improved risk calibration and strong alignment with expert-informed treatment preferences. These results establish our approach as a robust foundation for safe and intervention-aware clinical decision support.

cs.AI↗

arXiv2026

Spectral Rigidity in Toroidal Grothendieck Rings and Multiparameter Quantum Groups

Let $Q$ be a bipartite Dynkin quiver of finite simply-laced type and $\mathscr C_Q$ the corresponding Hernandez--Leclerc category. We study a two-parameter specialization of the Fedele--Hernandez toroidal Grothendieck ring and identify its generic positive part with a Cartan-type multiparameter quantum group. The structural input is the identity \[ 2D^{(2)}-D_0=ω_Q\circ(°_Q,°_Q), \] where $D_0,D^{(2)}$ are the two effective toroidal commutation forms and $ω_Q$ is the antisymmetric Euler form of $Q$. It realizes the specialized character algebra, after an auxiliary scalar extension, as a graded bicharacter twist of the one-parameter algebra at $v=t_0t^{1/2}$. This yields the required root grading and PBW graded dimensions. For every source--sink edge $r\to s$, these dimensions combine with the local $A$--$Y$ commutation formula to give a quadratic annihilator for $\operatorname{Ad}_{Z_r}$. Consequently \[ \operatorname{Spec}_{Z_r}(Z_s)=\{t_0t,t_0^{-1}\}, \] without thinness or type-specific character formulas. The two spectral values yield the oriented multiparameter Serre relations. With \[ q_{ii}=t_0^2t,\qquad q_{ij}=t_0^{-1},\qquad q_{ji}=t_0^{-1}t^{-1}\quad(i\to j), \] and $q_{ij}=1$ on nonedges, we obtain \[ U_{\mathbf q}^{+}(\mathfrak g) \simeq \mathscr K_\infty(\mathscr C_Q)\otimes_RK \] for $\mathfrak g$ of type $A_n,D_n,E_6,E_7,E_8$.

math.QA↗

arXiv2026

MixVLA: Adaptive Mixing of Non-Invariant Information for Generalizable Vision-Language-Action Models

Vision-Language-Action (VLA) models have achieved remarkable advances in robotic manipulation, yet their zero-shot generalization under out-of-distribution (OOD) conditions remains limited. These models often entangle task-relevant invariant structure with environment-specific non-invariant factors, causing policies to rely on spurious appearance cues during action prediction. In this work, we propose \textbf{MixVLA}, a model-agnostic training framework that improves the generalization of VLA models without requiring additional OOD data or architectural modifications. The key component of MixVLA is \textbf{Adaptive Mixing of Non-Invariant Information (AMI)}. AMI stochastically mixes non-invariant representations to regularize distribution-specific variability while preserving complementary predictive cues. The mixed non-invariant features are then fused with invariant representations for final action prediction, resulting in improved robustness without sacrificing policy expressiveness. Extensive experiments across challenging manipulation settings, including LIBERO, LIBERO-Plus, the RoboTwin perturbation suite, and real-world tasks, demonstrate that MixVLA improves overall zero-shot robustness while retaining strong in-domain performance.

cs.RO↗

arXiv2026

REDIRECT: A 1% Fix for Bad Robot Habits

Robots can acquire bad habits from a few defective moments in otherwise useful teleoperation. In mixed-quality robot data, normal and problematic demonstrations share most task behavior and differ only at a local action continuation. Full retraining is costly, while fine-tuning on clean data alone offers limited recovery under a small update budget. We ask whether the local difference can instead be fixed with only 1% of the full-training sample-backward budget. Using only episode-level retained/problematic labels, REDIRECT localizes the branch, assigns a coherent retained continuation to the original observations around it, and anchors shared behavior, without frame-level annotations or additional interaction. Across three randomized ManiSkill tasks and three seeds, REDIRECT raises the mean success rate from 68.2% to 90.3%, recovering 88.8% of the clean-retraining gap versus 22.1% for matched-compute fine-tuning. On a PiPER arm, it recovers 86.7-92.9% of the clean-only gap across cup insertion and towel folding. Local robot habits can therefore be repaired by spending the update budget on the behavioral difference rather than relearning shared behavior.

cs.RO↗

arXiv2026

RoXDrive: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving via Action-Faithful Rollouts

End-to-end autonomous driving policies are commonly trained via imitation learning on logged demonstrations without observing the consequences of their own actions, leading to causal confusion in closed-loop real-world deployment. To address this issue, reinforcement learning (RL) post-training offers a promising alternative by leveraging world models as interactive training environments to enable future scene generation for policy improvement. Nevertheless, existing approaches either rely on reconstruction-based simulators, offering limited counterfactual interaction, or adopt synthetic simulators to enable long-horizon closed-loop interaction at the cost of a substantial sim-to-real gap. Recently, video world models have exhibited the ability to generate realistic multi-step future rollouts but may not faithfully reflect action conditions, resulting in action-vision mismatch. In this paper, we introduce RoXDrive, a plug-and-play closed-loop RL framework that enables reliable policy optimization by identifying action-faithful world-model rollouts, consisting of two stages: 1) Model pre-training: In addition to imitation-based policy pre-training, we devise an Action-Vision Faithfulness Evaluator for inverse dynamics estimation with our geometry-aware auxiliary trajectory supervision, enabling long-horizon assessment of whether visual dynamics faithfully reflect the conditioning ego actions. 2) Action-faithful RL post-training: Agents iteratively interact with world models to form long-horizon scene rollouts, retaining only action-faithful ones for dense safety-aware scoring and scene-level closed-loop RL post-training. Extensive experiments on nuScenes and an in-house dataset with over 130K training scenarios demonstrate consistent gains across planners, reducing safety violations by 27.6% with DiffusionDrive on nuScenes and 33.7% with Qwen3-VL on the internal data.

cs.CV↗

arXiv2026

Quasinormal Modes of Reissner-Nordström Black Holes in Modified Gravity

In the framework of Scalar-Tensor-Vector Gravity (STVG), this paper investigates the quasinormal modes and time-domain evolution of Reissner-Nordström Modified Gravity (MOG) black holes under massless scalar, electromagnetic, and gravitational perturbations. Quasinormal frequencies are calculated by extending the 3rd- to 6th-order WKB method and combining it with Padé approximation to the 13th order, while complete time-domain waveforms are obtained using a finite-difference method based on light-cone coordinates. The results indicate that increasing the MOG parameter $α$ raises the effective mass of the black holes, leading to a decrease in the damping rate $|ω_I|$ and a slower ringdown decay. An increase in charge $Q$ produces a similar effect, with the damping approaching zero in the near-extremal limit. Regarding the ringdown decay times for the three types of perturbations, the gravitational field has the longest duration, the electromagnetic field is intermediate, and the scalar field is the shortest. The oscillations and decay observed in the time-domain waveforms are qualitatively consistent with the frequency-domain results, and the power-law exponent governing the late-time tail aligns with that of asymptotically flat spacetimes. This study provides a systematic theoretical reference for testing modified gravity theories using black hole spectroscopy.

gr-qc↗

arXiv2026

Windowed and Quantized Group-Based ADMM for Distributed Optimization in Heterogeneous Edge Networks

Distributed optimization in edge networks is constrained by heterogeneous client computing capabilities and limited communication resources. We propose the Windowed and Quantized Group-Based Alternating Direction Method of Multipliers (WQ-GADMM) to coordinate group updates under limited activation capacity and reduce communication costs. Clients are grouped by estimated computation time. Each window activates a limited number of groups per round, and the cloud updates the global model after all groups have updated once. The method quantizes both downlink and uplink model exchanges to reduce communication costs and allows bounded model staleness and inexact proximal local updates. For smooth nonconvex objectives, we establish an average squared Karush-Kuhn-Tucker residual bound under the stated assumptions and parameter conditions. The bound consists of a term that decreases with the iteration count and a quantization-dependent error term. Experiments on MNIST and CIFAR-10 show that 12-bit communication reduces communication volume and simulated wall-clock time while maintaining test accuracy comparable to full precision. The 12-bit configuration also maintains complete group coverage and achieves shorter mean group inter-completion gaps than the evaluated baselines.

cs.DC↗

arXiv2026

Devils in Question Relay: Source-Conditioned Relay Steering to Mitigate Hallucinations in Audio-visual Large Language Models

Audio-visual large language models (AVLLMs) have made remarkable progress in multimodal understanding and reasoning through interactions among visual, auditory, and linguistic information. However, recent studies show that AVLLMs face a critical challenge: $\textbf{source-confused grounding hallucination}$, where cues from the unused modality induce responses that the required modality does not support, undermining reliability in real-world applications. Existing methods have made progress in mitigating this failure, yet how it arises from internal cross-modal interactions remains insufficiently understood. To address this gap, we conduct path-intervention and representation analyses, revealing a $\textbf{question-relay}$ mechanism: question states carry interfering cues alongside required-source evidence, undermining grounding in required-modality evidence. Cutting pathways from interfering modality to question states yields greater correct-answer logit recovery than cutting those to the generation position. Motivated by these findings, we propose $\textbf{SECRET}$ ($\textbf{S}$ourc$\textbf{E}$-$\textbf{C}$onditioned $\textbf{RE}$lay s$\textbf{T}$eering), a training-free method that mitigates cross-modal interference at the question relay. Using contrasting question representations elicited through different modality-pathway interventions, SECRET steers the original question states toward required-source evidence. Experiments on two widely adopted benchmarks CMM and AVHBench across three AVLLMs show that SECRET consistently outperforms prior training-free methods, substantially mitigating source-confused grounding hallucinations (e.g., up to +18.0 and +7.1 percentage points over base models). Modality-specific captioning further demonstrates its generalizability to open-ended generation.

cs.CL↗