Search arXiv⌕ Search

arXiv subjects

Zhi Chen

Publications and source records attributed to Zhi Chen.

At least 19 recordsLinked to original sources
arXiv2026

Movable Antenna Empowered Near-Field Sensing via Antenna Position Optimization

Movable antenna (MA) technology exhibits great promise for enhancing the sensing capabilities of future sixth-generation (6G) networks due to its capability to alter antenna array geometry. With the growing prevalence of near-field propagation at ultra-high frequencies, this paper focuses on the application of one-dimensional (1D) and two-dimensional (2D) MA arrays for near-field sensing to jointly estimate the angle and distance information about a target. First, for the 1D MA array scenario, to gain insights into MA-enhanced near-field sensing, we investigate two simplified cases with only angle-of-arrival (AoA) or distance estimation, respectively, assuming that the other information is already known. The worst-case Cramer Rao bounds (CRBs) on the mean square errors (MSEs) of the AoA estimation and the distance estimation are derived in these two cases. Then, we jointly optimize the positions of the MAs within the 1D array to minimize these CRBs and derive their closed-form solutions, which yield an identical array geometry to MA-enhanced far-field sensing. For the more challenging joint AoA and distance estimation, since the associated worst-case CRB is a highly complex and non-convex function with respect to the MA positions, a discrete sampling-based approach is proposed to sequentially update the MA positions and obtain an efficient suboptimal solution. Furthermore, we investigate the worst-case CRB minimization problems for a 2D MA array under various conditions and extend our proposed algorithms to solve them efficiently. Numerical results demonstrate that the proposed MA-enhanced near-field sensing scheme dramatically outperforms conventional fixed-position antennas (FPAs). Moreover, the joint angle and distance estimation results in a different array geometry from that in the individual estimation of angle/distance or far-field sensing.

cs.IT↗
arXiv2026

Speculative Forking: Turning Idle Wait into Parallel Exploration for Repository Environment Setup

Before developers can use a software project, they must first get it to run. This often requires installing the right language runtime, system packages, build tools, and test commands. Recent LLM-based agents automate environment setup by inspecting a repository, writing setup scripts, running them, and repairing the resulting errors. However, these agents still follow a sequential trial-and-error loop: they try one setup route, wait for slow commands to finish, observe the failure, and only then decide what to try next. Because environment commands often take long to run, this sequential workflow makes setup slow and limits exploration to one route at a time. We present SpecBuild, an LLM-based environment setup system designed to be both faster and more successful through speculative forking. SpecBuild explores candidate setup branches in parallel, returns the first committed environment, and discards the rest. It applies this design at two granularities: strategy-level forking explores alternative setup routes, such as different base images and dependency policies, while command-level forking predicts failures of running commands and prepares repair branches before those failures are observed. We evaluate SpecBuild on Multi-Docker-Eval, covering 334 tasks from 40 repositories and 9 programming languages. Across three backbone models, SpecBuild improves the success rate by 6.4 to 12.0 percentage points over the strongest baseline, while reducing average setup time by 22.4% to 41.6%. These results show that LLM-based environment setup need not trade speed for reliability: parallel speculative exploration can make agents both faster and more successful.

cs.SE↗
arXiv2026

Visual Memory and Textual Alignment for Cross-Modal Few-Shot Segmentation

Few-shot segmentation (FSS) aims to segment target objects with limited annotated examples. Recent studies have begun to explore large foundation models to improve generalization for this task. In particular, SAM 3 provides strong visual representations and supports text-guided segmentation. However, its performance remains limited in specialized domains, where semantic prompts and visual representations are often poorly aligned. To address this challenge, we propose ViTA-SAM, a framework built upon SAM 3 that integrates visual memory and textual features through cross-modal alignment. Specifically, we construct a visual memory module that encodes support features together with their corresponding masks, providing support-aware visual guidance for query prediction. In parallel, we leverage the text encoder of SAM 3 to extract semantic features as complementary priors. To bridge the gap between semantic and visual representations, we introduce a cross-modal alignment module that conditions textual features on memory-enhanced visual representations, yielding more consistent and visually grounded predictions. In addition, we propose a pseudo-label refinement strategy that updates the memory with predicted query masks, enabling query-adaptive representation learning. Extensive experiments on multiple benchmarks show that ViTA-SAM achieves the best overall performance among the compared methods, outperforming the strongest competing method by over 5% in average mIoU.

cs.CV↗
arXiv2026

pynucastro 3: A community library for nuclear astrophysics

We describe the latest release of pynucastro: a community python library for nuclear astrophysics. The goal of the pynucastro project is to build the tools needed to interactively explore nuclear properties, reaction rates, and networks, and to export these networks to a variety of simulation codes. Major changes in pynucastro since the last major release include new rate approximations, a stellar equation of state, support for the StarLib library and rate uncertainties, and new tools for exploring networks.

astro-ph.IM↗
arXiv2026

Sharp decay characterization for the Oldroyd-B system with only velocity dissipation

We study the incompressible Oldroyd-B system on $\mathbb R^d$, $d\ge2$, in the regime in which the velocity is the only dissipated quantity: the stress tensor undergoes neither relaxation nor diffusion. In this regime the operator $\mathbb P\operatorname{div}$ acting on symmetric stresses has an infinite-dimensional kernel consisting of exact stationary states, so no decay estimate can hold for the full stress tensor and the existing sharp-decay theory for dissipative systems does not apply. We identify the active pair $U=(u,Λ^{-1}\mathbb P\operatorname{div}τ)$ as the correct decaying observable and establish, in a critical hybrid Besov framework, a complete characterization of its large-time behavior. For $-d/2<σ_1<σ\le d/2-1$ we prove that $\|U(t)\|_{\mathcal H^σ}=O(t^{-(σ-σ_1)/2})$ holds if and only if the low-frequency part of $U_0$ belongs to $\dot B^{σ_1}_{2,\infty}$, and, for $σ<d/2-1$, that the two-sided estimate $\|U(t)\|_{\mathcal H^σ}\simeq t^{-(σ-σ_1)/2}$ holds if and only if the low-frequency part of $U_0$ belongs to a nondegenerate subclass $\mathfrak B^{σ_1}_{2,\infty}$ of $\dot B^{σ_1}_{2,\infty}$.

math.AP↗
arXiv2026

MSE Minimization for Movable Antenna Enhanced Wireless Sensing via Array Geometry Optimization

This paper develops adaptive movable-antenna (MA) array structures to enhance wireless sensing performance under arbitrary SNR conditions, using the AoA estimation MSE as the sensing metric. Due to the presence of strong sidelobes in the ambiguity function of sparse MA arrays, the classical CRB of AoA estimation MSE fails to characterize the true MSE in the low and medium SNR regimes, rendering CRB-optimized antenna position vector designs suboptimal for MA-enabled sensing. We derive a deterministic MSE approximation that captures the local estimation error within the mainlobe of the ambiguity function and the outlier error induced by sidelobes, providing a tractable and accurate optimization objective. We then propose three adaptive MA structures that are tailored to different hardware and computational requirements. For systems with fully independent motors, a movable free array is optimized by a two-stage greedy algorithm, which approaches the performance of the globally optimal exhaustive search but with lower computational complexity. Halving the required motors, a movable nested array fixes the dense inner subarray and adjusts only the outer-subarray spacing, reducing the optimization to a one-dimensional search. As the most hardware-efficient design, a movable twin array is proposed to adjust the inter-subarray spacing only with a single motor, while still achieving significant MSE reduction over fixed array geometries. Numerical results show that the derived approximation closely matches the true MSE compared with existing performance bounds, and that the proposed structures outperform the CRB-optimized designs by orders of magnitude in MSE across the tested low-to-medium SNR range. Moreover, it reveals that in the low-SNR regime, APV reconfiguration is more effective for improving estimation accuracy than simply increasing the number of fixed antennas.

cs.IT↗
arXiv2026

LiteGUI: Lightweight GUI Agents via Multi-Solution Guided Distillation and Dual-Level Reinforcement Learning

We present LiteGUI, a new framework for building lightweight GUI agents. GUI interaction poses unique challenges due to the long-horizon nature of complex tasks and the existence of multiple valid interaction paths, which are difficult for lightweight GUI agents to handle effectively. To address these challenges, LiteGUI introduces a two-stage post-training framework operating on logged GUI states. First, we propose Guided On-Policy Distillation, which provides training-time privileged teacher guidance at each GUI state by selecting the most-matched valid action from human-verified multi-solution action annotations, while leaving the student's on-policy rollout unchanged. Second, we develop Multi-Solution Dual-Level GRPO, which combines action-level supervision with history-conditioned, per-state planning-quality supervision while accounting for multiple valid actions at each logged GUI state. Together, these stages support multi-step GUI tasks without requiring the student to reproduce fixed demonstration trajectories. We further develop a scalable data generation pipeline and a corresponding multi-solution dataset, Lite-Dataset, to support the training and evaluation of GUI agents, addressing a gap in the existing literature. Extensive experiments across multiple GUI benchmarks demonstrate that LiteGUI substantially improves the performance of lightweight GUI agents over existing training paradigms, including SFT, on-policy distillation and GRPO, and achieves competitive or superior performance compared with substantially larger models.

cs.AI↗
arXiv2026

Timer-M1: A Multivariate Time Series Foundation Model via Learning Primitives

We introduce Timer-M1, a pretrained multivariate time series foundation model that learns with primitives for zero-shot forecasting. Across domains, time series share elementary temporal and relational patterns, termed primitives, yet differ in how these primitives manifest and evolve across different contexts. Despite progress in zero-shot and task-general forecasting, existing foundation models may still struggle to generalize to complex real-world scenarios. To this end, we develop a primitive-based data synthesis and pretraining pipeline. The synthesis pipeline generates series with temporal primitives shared across domains and then assembles real and generated series into multivariate samples using relational primitives. Afterwards, samples are organized into episodes by assigning distinct channel roles as target variates, past-only covariates, and known-future covariates, ensuring that the model is optimized on predictable variates using available exogenous information. Technically, Timer-M1 further adapts gated two-dimensional Transformer blocks that dynamically allocate cross-variate attention across layers. Across three large-scale forecasting benchmarks, Timer-M1 ranks first on both FEV and TIME and second on GIFT-Eval among most recent time series foundation models. These results support effective primitive-based pretraining as a route to robust general forecasting technique across domains and task settings.

cs.LG↗
arXiv2026

CARM: Cancellation-Aware Response Masking for LLM Reinforcement Learning

Recent years have witnessed the rapid adoption of reinforcement learning (RL) in large language model (LLM) post-training, with substantial gains in mathematical reasoning and code generation. In practical systems, however, policy updates and differences between rollout and training engines can make sampled responses off-policy. Sequence-level masking addresses this mismatch by deciding whether an entire response should contribute to optimization. A common masking rule uses the length-normalized geometric mean of sampled token probability ratios. Its signed log-ratios can cancel across positions, concealing substantial bidirectional policy drift. We propose \emph{Cancellation-Aware Response Masking} (CARM), a sequence-level mask that takes the absolute value of each token log-ratio before averaging, preventing opposing probability changes from canceling. We prove that accepted responses satisfy a joint bound on the fraction of sampled-token ratios outside a prescribed band and their mean log-distance beyond its boundaries. Experiments on mathematical reasoning and code generation show that CARM improves mean@16 averaged over AIME 2024/2025/2026 and BeyondAIME by up to $3.13$ percentage points over geometric-mean masking, and increases average pass@1 across four code benchmarks by $2.88$ points over the strongest evaluated baseline. These findings support CARM as a theoretically grounded and effective method for response-level off-policy control in LLM reinforcement learning.

cs.LG↗
arXiv2026

Two Heads Are Better Than One: Aggregating Weaker LLMs for Better Forecasts

Large language models (LLMs) are increasingly used to forecast real-world events, but access to the strongest individual forecaster may be costly or otherwise constrained. We study weak-to-strong forecast aggregation: can individually weaker LLM forecasters be aggregated to outperform a stronger forecaster? Using ForecastBench (Karger et al., 2025), we evaluate 70 LLM forecasters across 16 comparison groups, each with more than 1,000 shared subquestions, yielding 1,121 weaker-model pairs. Within each group, we identify the strongest individual by test Brier score and evaluate aggregates composed exclusively of weaker forecasters, with aggregation weights learned on separate training data. We find substantial evidence of weak-to-strong improvement. Learned linear pooling identifies a weaker pair that matches or outperforms the strongest individual in 11 of 16 groups and comes within 5% of its Brier score in all 16 groups. We also find that these improvements do not rely on having a near-best constituent and are generally accompanied by good calibration. Additional analyses show that adding more models does not consistently improve performance, and competitive weaker-model aggregates also remain available under practical constraints.

cs.LG↗
arXiv2026

Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies

Generalist robot policies increasingly benefit from large-scale pretraining, but offline data alone is insufficient for robust real-world deployment. Deployed robots encounter distribution shifts, long-tail failures, task variations, and human correction opportunities that fixed demonstration datasets cannot fully capture. We present Learning While Deploying (LWD), a fleet-scale offline-to-online reinforcement learning framework for continual post-training of generalist Vision-Language-Action (VLA) policies. Starting from a pretrained VLA policy, LWD closes the loop between deployment, shared physical experience, policy improvement, and redeployment by using autonomous rollouts and human interventions collected across a robot fleet. To stabilize learning from heterogeneous, sparse-reward fleet data, LWD combines Distributional Implicit Value Learning (DIVL) for robust value estimation with Q-learning via Adjoint Matching (QAM) for policy extraction in flow-based VLA action generators. We validate LWD on a fleet of 16 dual-arm robots across eight real-world manipulation tasks, including semantic grocery restocking and 3--5 minute long-horizon tasks. A single generalist policy improves as fleet experience accumulates, reaching an average success rate of 95%, with the largest gains on long-horizon tasks.

cs.RO↗
arXiv2026

ReBridge-Flow: Re-Coupling Posterior Bridges in Flow Matching for Image Restoration

Flow Matching provides an efficient generative prior for image restoration by learning continuous transport between source and data distributions. However, existing methods typically incorporate measurement constraints through local corrections. Such corrections may disrupt the source-clean endpoint coupling implicitly encoded by the pretrained flow, making the corrected endpoint pair incompatible with the current state. To address this issue, we propose ReBridge-Flow, a posterior bridge re-coupling method. Specifically, given the current state, ReBridge-Flow first decodes the corresponding local source and clean endpoints. It then incorporates measurement information through clean-side anchoring and synchronously re-couples the source endpoint, yielding a measurement-aware endpoint pair with improved local bridge compatibility. The re-coupled endpoints further define a posterior-informed transport direction for advancing the sampling process. We also introduce the Posterior Bridge Defect, which jointly characterizes measurement error, deviation from the flow prior, and bridge mismatch, and leads to explicit updates for clean-side anchoring and source-side re-coupling. Extensive experiments on multiple natural and medical image restoration tasks demonstrate that ReBridge-Flow effectively alleviates bridge mismatch and improves the structural consistency of restored images.

cs.CV↗
arXiv2026

Channel Gains to Captions: Task-Unified Multi-Level RF Sensing with Vision-Language Models

This letter investigates a task-unified multi-level radio-frequency (RF) sensing framework driven by vision-language models (VLMs). Existing RF sensing methods rely on task-specific designs and provide only partial environmental information, limiting their ability to handle emerging 6G applications. To address this, we propose a generative formulation for RF sensing, where millimeter-wave (mmWave)/terahertz (THz) channel gains are mapped to captions describing multi-level environmental semantics. The framework solves this problem through a complementary design for RF-environment semantic bridging, where a VLM is fine-tuned to leverage its multimodal representations and prompt-conditioned semantic generation capabilities. Hence, different sensing tasks are specified through textual prompts, enabling the framework to handle diverse tasks in a unified manner. For fine-tuning, we introduce prompt-routed low-rank adaptation (LoRA) experts to achieve level-aware adaptation. Simulation results show that, compared with baselines, our framework achieves superior performance with a broader semantic scope, and enables task-unified sensing beyond predefined tasks. Under an unseen sensing requirement, it achieves an average F1-score improvement of 0.17 over the most competitive variant.

eess.SP↗
arXiv2026

Single-Model Adaptive Wireless Image Transmission via Feature Sparsity Regularization

Learned joint source-channel coding (JSCC) enables robust wireless image transmission by jointly optimizing the transmitter and receiver over differentiable channel models. For bandwidth-limited and time-varying visual links, a single model should support user-adjustable transmission rate and adapt to changing wireless channel conditions, while also dynamically allocating resources according to spatial content. Existing content-adaptive or dynamic allocation schemes often rely on entropy coding, context/probability prediction, explicit rate maps or masks, or auxiliary allocation networks, complicating the encoder-decoder pipeline and increasing side-information overhead. We propose TS-JSCC, a single-model adaptive JSCC framework with tail-structured sparsification. First, an L1-based tail-structured sparsification objective encourages each token to retain an active feature-channel prefix while suppressing trailing ones. This enables content-adaptive feature-channel allocation with compact side information through active-prefix transmission. Second, lightweight stage-wise neural regulating modules use a normalized sparsity-control coefficient and the channel signal-to-noise ratio (SNR) to rescale intermediate features for single-model transmission rate and SNR adaptation. Experiments on CIFAR-10, Kodak, and CLIC2021 under additive white Gaussian noise (AWGN) and Rayleigh fading show that TS-JSCC achieves strong rate-distortion performance against the latest learned-JSCC baselines and remains competitive with the considered idealized separation baselines, while retaining a simple one-shot encoder-decoder without extra structures or computations.

eess.IV↗
arXiv2026

$τ_0$-WM: A Unified Video-Action World Model for Robotic Manipulation

Robotic manipulation requires models that generate executable actions while anticipating and evaluating their future consequences before physical execution. We present $τ_0$-World Model ($τ_0$-WM), a unified video-action world model that integrates policy learning, video prediction, and action evaluation within a single future-predictive framework. Built on a shared video diffusion backbone, $τ_0$-WM provides two complementary interfaces. First, a video action model jointly predicts future visual latents and continuous action chunks from multi-view observations, language instructions, and robot state. Second, an action-conditioned video simulator rolls out candidate action chunks into multi-view futures and predicts dense task-progress scores. The model is trained on approximately $27{,}300$ hours of real-robot teleoperation, UMI-style interaction, egocentric human videos, and rollout or failure trajectories using modality-specific supervision masks. At inference time, $τ_0$-WM uses test-time computation to sample action candidates, rank them with re-denoising consistency, and invoke simulator-based rectification for low-quality candidates. On challenging long-horizon and fine-grained robotic manipulation tasks, $τ_0$-WM shows superior performance over other relevant baselines.

cs.RO↗
arXiv2026

Human-Centric Intelligence in the Era of Foundation Models: A Survey

Human-centric intelligence is evolving in the foundation-model era, with growing emphasis on scale, transferability, and general-purpose modeling. Yet it has not fully integrated with foundation models to achieve the comparable progress seen in them. More importantly, recent advances across this broad landscape remain fragmented across tasks, modalities, and research communities, leaving their intrinsic conceptual and methodological connections unclear. To bridge these divides and rethink human-centric intelligence in the foundation-model era, we introduce a full-spectrum human context taxonomy that integrates six interconnected levels by viewing humans as observable subjects through visual appearance and spatial geometry, as dynamic actors through kinematic dynamics and interaction modeling, and as situated agents through world simulation and embodied agency. We next present the methodological foundations of the field, covering human-centric data families, computational architecture paradigms, and representative training and inference optimization strategies. We then systematically review representative methods across these levels and organize the associated datasets, benchmarks, and evaluation metrics. We further discuss open challenges and promising research directions toward human-centric intelligence that is scalable, trustworthy, physically grounded, and deployable, aiming to provide a coherent framework and practical reference for advancing the field. Finally, we provide a systematically organized and continuously updated collection of human-centric AI literature and resources on our project page.

cs.CV↗
arXiv2026

$τ_0$-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation

Long-horizon robot manipulation requires a robot to both execute individual skills reliably and sequence them coherently over extended tasks. Most hierarchical vision-language-action (VLA) models make each such decision with a single forward pass, leaving no mechanism to allocate additional computation to difficult or consequential choices. We introduce $τ_0$-VLA, a hierarchical robot foundation model that formulates high-level subtask generation as a compute-scalable inference problem through world-model-guided test-time computation. At each inference step, the high-level policy uses execution memory to generate a subtask and, when needed, searches over alternatives before committing to its output. A low-level policy then executes the generated subtask across multiple robot embodiments. The policy is trained on 40,115 hours of heterogeneous real-world data with multimodal co-training. Across in-domain and distribution-shifted settings, allocating additional test-time computation substantially improves next-subtask prediction accuracy, and these gains translate into higher closed-loop success on long-horizon robot manipulation tasks.

cs.RO↗
arXiv2026

Prandtl-Batchelor flows with a point vortex on a disk

We study steady two-dimensional incompressible Navier-Stokes flow in the unit disk in a high Reynolds number regime, driven by a localized central forcing and a nearly rigid rotating boundary. The forcing models a compact source of circulation that sustains a vortex core in a viscous flow. For sufficiently small viscosity and boundary perturbation, we construct a very weak steady solution on the whole disk and identify its inviscid limit: a point vortex embedded in a constant vorticity background and joined to the boundary motion by a thin boundary layer. The background vorticity is selected by the Batchelor-Wood formula. The singular core introduces non-coercive interactions in the linearized problem that are absent for regular Prandtl-Batchelor flows. To overcome this difficulty, we map the punctured disk to a semi-infinite cylinder by a logarithmic radial transformation and develop a Fourier-mode analysis that isolates the delicate first Fourier mode, yielding uniform stability and vorticity estimates in the presence of the point-vortex singularity.

math.AP↗