Search arXiv⌕ Search

arXiv subjects

Qian Zhang

Publications and source records attributed to Qian Zhang.

At least 37 records · Page 2Linked to original sources
arXiv2026

Higher-Order Action Supervision Makes A Strong Policy Class

Modern data-driven decision-making methods, such as imitation learning (IL) and reinforcement learning (RL), have achieved great success in solving many complex tasks. However, these methods often suffer from serious control instability and robustness issues when applied in real-world applications such as robotics and autonomous driving, posing notable challenges for their practical deployment. We argue that this instability issue stems largely from their limitations in solely supervising and optimizing zeroth-order actions (i.e., the action labels), failing to account for higher-order action dynamics and temporal consistency. In this paper, we show that simultaneously supervising both zeroth- and first-order actions can dramatically enhance policies' performance and control robustness. To achieve this, we introduce a novel and elegant loss scheme supported by formal theoretical guarantees that can equip any off-the-shelf policy model (e.g., deterministic, stochastic, or flow policies) with the capability for higher-order action supervision, without requiring any structural modifications. Moreover, our proposed method can serve as a lightweight plug-and-play module that seamlessly integrates with a broad spectrum of existing offline RL frameworks. Extensive evaluations on OGBench and D4RL demonstrate that our approach yields substantial performance and robustness improvements across a wide range of continuous control environments. Notably, our method can also enhance policies' out-of-distribution (OOD) generalization capability in the challenging low-data regime, making it an ideal tool in tackling many real-world control problems.

cs.RO↗
arXiv2026

Large-Scale Data Center Integration in Power Systems: Uncertainty and Multi-Scale Variation

Hyperscale artificial intelligence (AI) data centers are emerging as a structurally new class of electricity demand. Unlike conventional loads, they materialize as spatially concentrated, transmission-level point loads with rapid deployment timelines and converter-dominated dynamics. Their integration is governed by two defining properties: forecast uncertainty in load realization and multi-scale temporal variation spanning sub-seconds to planning horizons. We develop a unified framework that links reliability and affordability to these dimensions through a four-quadrant structure: (reliability, affordability) $\times$ (uncertainty, variation), which integrates probabilistic resource adequacy, generation and transmission expansion, operational security, and market design. Measured traces from a public generative-AI workload dataset show strongly tonal GPU power spectra rather than smooth broadband behavior: harmonic combs at the training-step cadence, and a distinct sub-second periodicity in inference. Across these traces the dominant variance band shifts with workload type (seconds for training and offline inference; tens of seconds and longer for online inference). We report this as a characterization of the measured workloads rather than a universal signature, and take it to indicate that such loads warrant a spectral description rather than a peak-demand one. These signatures directly affect reserve requirements, ramping products, voltage stability, ride-through performance, and harmonic interactions in converter-rich grids. Taken together, the analytical framework and empirical results establish a system-level basis for assessing the reliability and cost implications of large AI data center integration across planning and operational horizons.

eess.SY↗
arXiv2026

Interactive Power Flow in the Browser

This paper introduces tellegen, an open source framework for interactive power flow (PF) and optimal power flow (OPF) studies that run in the browser. This provides intuitive and democratized access to power system analysis tools compiled to WebAssembly. A user can drag and drop a case file, click and drag to change a nodal demand or line rating, preview the impacts via sensitivity analysis, and obtain an exact re-solve on release. User case files and results stay entirely on the device: tellegen transmits zero Critical Energy/Electric Infrastructure Information (CEII). The framework comprises a core numerical engine for PF and OPF, reusable browser components, saved studies, and structured WebMCP tools for agentic interaction. We evaluate the transmission OPF solver by comparing objectives with PGLib baselines; the distribution PF solver by comparing voltages and currents with OpenDSS; and the WebAssembly execution times by comparing with PowerModels.jl. On realistic synthetic grids, WebAssembly OPF solves take only 25-43% longer than native binary solves. The implementation shows how an engineer can distribute an executable numerical study as a URL, reducing installation and hosting requirements while keeping case data local.

eess.SY↗
arXiv2026

Duration-Aware Ramp Adequacy Screening

Ramp products are widely used in regional electricity markets to procure intertemporal flexibility in anticipation of net demand changes. However, the design of such ramp products often lacks a clear specification of ramping duration, potentially leading to infeasible dispatch solutions. This paper develops a duration-aware ramp adequacy screening method that evaluates whether the currently committed and dispatched fleet can meet the anticipated net-demand ramp requirement across different durations. A negative ramp adequacy margin identifies an insufficient-duration set in which the fleet lacks adequate ramp capability. Evaluating this margin across duration supports product-duration selection, while tracking it over time provides a metric for assessing ramp adequacy under different products and dispatch policies. We further formulate rolling-window ramp-reserve procurement with horizon-dependent forecast uncertainty and show that a product can affect ramp capability beyond its designated duration through changes in dispatch positioning. Building on this framework, we develop a forecast-free ramp-reserve scarcity dispatch policy that prioritizes resources according to their remaining ramp-up durations and, in the transmission-unconstrained setting, achieves the same minimum operational security loss as a perfect-foresight benchmark. Studies on a 10-generator system and a 2751-bus synthetic Texas grid demonstrate the value of the proposed framework for early detection of ramp scarcity, product design and evaluation, and screening-guided emergency dispatch.

eess.SY↗
arXiv2026

Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spaces

We present Multimodal Flow, a fully continuous generative model of language and vision. Most unified multimodal models either model both language and quantized images as discrete tokens or combine discrete language prediction with continuous image generation. The former introduces a visual quantization bottleneck. The latter requires modality-dependent objectives and sampling procedures. Fully continuous modeling avoids these trade-offs and enables a shared generative process, but remains underexplored for multimodal pretraining. Multimodal Flow introduces a unified continuous architecture that integrates multimodal continuous representations with a shared chunk-causal flow backbone. It organizes text blocks and images as ordered continuous hyperchunks, preserving textual token order and visual spatial structure. The backbone learns a single vector field over these hyperchunks through Flow Matching. Joint attention enables cross-modal interaction, while modality-specific feed-forward networks process each modality. The model predicts multiple target chunks in parallel during training and generates hyperchunks sequentially at inference. We instantiate MF-1 and pretrain it on multimodal data. Across 0.6B, 1.2B, and 1.6B scales, continued pretraining consistently improves multimodal modeling. With only 150B pretraining tokens, MF-1 achieves an average score of 82.8 across GenEval and DPG-Bench and 75.3 across VQAv2, MMBench, and POPE, remaining competitive with unified models trained on substantially more data. Under matched data, optimization, and parameter budgets, Multimodal Flow further outperforms representative hybrid and discrete models. These results establish continuous chunk-based embedding flow modeling as a new fully continuous paradigm for unified multimodal modeling. The related code and model are publicly released at https://github.com/hustvl/Multimodal-Flow.

cs.CV↗
arXiv2026

RIS-Assisted Multiuser NOMA Networks With Imperfect CSI Under Transceiver Hardware Impairments

The incorporation of non-orthogonal multiple access (NOMA) and reconfigurable intelligent surface (RIS) provides a new solution to improve spectral efficiency. Unfortunately, the channel estimation error of RIS is noteworthy due to the absent active radio frequency link. Meanwhile, the transceivers at base stations (BS) and users also exist hardware impairments (HWI). The imperfect channel state information (CSI) and HWI will degrade the communication performance such as outage probability or data rate. To alleviate such performance deterioration, we propose a robust design scheme to minimize the BS transmit power when the target rate of users is satisfied in RIS-assisted single-beam and multi-beam NOMA networks with transceiver HWI and imperfect CSI. Further, the perfect successive interference cancellation (SIC) condition in single-beam and multi-beam NOMA networks is investigated, and the optimization problem is proposed based on perfect SIC conditions. To tackle the non-convex problem, we provide an effective algorithm combining Bernstein-type inequality and semi-definite relaxation. Numerical results demonstrate that the proposed scheme outperforms non-robust RIS-assisted NOMA scheme that ignores HWI and imperfect CSI. Moreover, the multi-beam NOMA network obtains higher beam gain compared to the single-beam NOMA network, and thus there is a superior performance in multi-beam NOMA networks.

cs.IT↗
arXiv2026

ReDrive: Shaping Representations with World Modeling for End-to-End Driving

Driving policies require capabilities of scene understanding and future evolution prediction. To achieve this goal, current end-to-end models typically construct complex perception-planning pipelines or introduce world models that explicitly predict future states, resulting in a complex system architecture. Inspired by the transferability of general-purpose visual representations, we argue that combining sufficiently strong visual representations with representation world modeling can support effective planning without relying on complex inference-time auxiliary modules. Based on this insight, we present ReDrive, an end-to-end driving framework that strengthens planning-oriented visual features via future representation prediction. To achieve this, ReDrive adopts a three-stage training pipeline consisting of driving video pretraining, joint world-modeling and planning training, and planner adaptation. This yields a strong planning-oriented representation and a high-performance planner, while requiring neither auxiliary perception modules nor future prediction at inference time. Experiments on NAVSIM demonstrate strong performance, achieving 91.0 PDMS on NAVSIM v1 and 90.8 EPDMS on NAVSIM v2. These results show that shaping representations with world modeling is sufficient to enable high-performance end-to-end planning while retaining a simple encoder-planner inference pipeline.

cs.CV↗
arXiv2026

G$^2$PTQ: Improving LLM Post-Training Quantization with Generalized Gradient Compensation

Post-training quantization (PTQ) is a practical approach to reducing the memory and computational footprint of large language models (LLMs) without retraining. GPTQ-based methods have become the de facto standard, yet they suffer from two complementary limitations. Methods with local, layer-wise objectives lack global supervision; while methods with global objectives fix their Hessian estimates at the start and ignore first-order gradients, so their guidance grows stale as quantization proceeds. This paper presents G$^2$PTQ, a unified PTQ framework with Generalized Gradient Compensation that integrates both first- and second-order information under a globally supervised, block-wise optimization objective. By refreshing gradient and Hessian estimates before quantizing each Transformer block, G$^2$PTQ avoids the staleness of prior global methods. Furthermore, to stabilize the exact first-order compensation, we introduce a trust-region scaling mechanism that dynamically bounds the gradient step to prevent exploding weight updates. Finally, we derive efficient implementations for block-wise Hessian approximation and exact gradient compensation. Experimental results on various model families and bit-widths demonstrate that G$^2$PTQ enables better alignment with the full-precision model, outperforming state-of-the-art baselines. Code is available at: https://github.com/G2PTQ/G2PTQ.

cs.CL↗
arXiv2026

Optical Mode Sorting with a Programmable Diffractive Neural Network

Programmable diffractive optical processors are particularly attractive for spatial light manipulation because their optical transformations can be dynamically reconfigured and adapted without modifying the physical hardware. However, their practical performance is often limited by the gap between simulation and experiment caused by optical aberrations, alignment errors, and nonideal phase responses. In this paper, we introduce a hybrid optimization framework that combines high-dimensional numerical design with low-dimensional hardware-in-the-loop calibration, enabling programmable diffractive optical networks to compensate experimentally for mismatch without retraining their underlying optical transformations. We demonstrate a programmable optical diffractive neural network (ODNN) designed by back-propagation to spatially sort six linearly polarized modes supported by a multimode fiber. The experimental distortions are represented using a truncated Zernike basis with only 19 correction coefficients per layer. These coefficients are optimized directly on the physical system using stochastic parallel gradient descent, avoiding re-optimization of the full pixelated phase masks. Experimentally, the proposed calibration yields an SNR improvement of approximately 3.26 dB, and a decrease in amplitude error of 0.04. This separation of high-dimensional optical-function design from low-dimensional physical calibration provides a scalable route towards adaptive and reconfigurable spatial-mode processors for optical router on spatial modes and wavelengths, programmable photonic computer systems and quantum information processing.

physics.optics↗
arXiv2026

Rethinking Pairwise Token Interaction in Spiking Transformers

Spiking Transformers inherit token interaction mechanisms from conventional Transformers, yet their sparse binary representations fundamentally alter how token-to-token communication is established. In particular, spike-based query-key matching produces highly sparse and input-dependent interaction patterns, coupling information propagation to the instantaneous availability of matching spike events. This motivates a different interaction paradigm in which long-range communication does not rely solely on pairwise spike coincidence. We therefore propose Gated Spike Axial Propagation (GSAP), a spike-native token interaction mechanism that decouples information propagation from context selection. Instead of directly determining communication through query-key matching, GSAP first propagates spike-based context along the horizontal and vertical axes, allowing information to reach distant tokens through structured sequential propagation. A receiver-conditioned gate then determines how much of the propagated context is incorporated at each token, while a lightweight local pathway preserves fine-grained neighborhood information. In this way, GSAP reformulates token interaction as a propagate-then-select process, enabling structured long-range communication while retaining the sparse event-driven nature of spiking representations. Code is available at https://github.com/Fancyssc/GSAP.

cs.NE↗
arXiv2026

Self-Reference in Large Language Models: The Introspection Threshold for Recursive Self-Improvement

The pursuit of self-evolving AI raises a critical question: when is autonomous self-improvement sustainable rather than degenerative? Drawing an analogy to von Neumann's complexity threshold for self-reproducing automata, we argue that sustainable recursive self-improvement in Large Language Models (LLMs) requires a functional analogue: introspection -- the system's capacity to simulate its own operations and target modifications. Grounded in Kleene's Second Recursion Theorem, we demonstrate the theoretical existence of such introspective programs. However, an empirical review reveals that while current LLMs exhibit quasi-introspection (e.g., partial metacognition), they fall short of true introspection due to structural bottlenecks: a lack of complete self-access, the feedforward nature of the Transformer, and computational class constraints that prevent fixed-point iteration. We conclude by outlining architectural paths to cross this complexity threshold and discussing the associated safety implications.

physics.soc-ph↗
arXiv2026

Selective Inference in Growth Curve Models

Growth curve models are widely used in psychological research, and variable selection can help identify baseline characteristics associated with longitudinal heterogeneity. However, conventional inference after data-driven variable selection can be invalid because the same outcome data are used for both selection and inference. We develop a data-fission framework for post-selection inference in growth-curve models that separates the information used for selection and inference while retaining all participants in both stages through the addition and subtraction of Gaussian noise. The framework accommodates flexible variable-selection procedures and targets covariance-weighted linear projection parameters in the selected working model. It provides exact inference when the covariance structure is known, and we establish asymptotic validity under suitable regularity conditions when the covariance structure is estimated. Simulations show that the proposed method provides valid inference and improves efficiency over subject-level data splitting, whereas na\"ıve post-selection inference can be biased. An application to the Longitudinal Study of American Youth illustrates the proposed framework.

stat.ME↗
arXiv2026

FreqDINO++: A Frequency-Guided Multi-Task Routing Vision Foundation Model for Universal Ultrasound Analysis

Ultrasound image analysis plays a crucial role in cancer screening and prenatal diagnosis, yet comprehensive assessment requires jointly addressing tasks such as lesion segmentation and benign-malignant classification. While recent vision foundation models have shown remarkable universal representations, unlocking their potential for ultrasound is bottlenecked by the considerable domain gap from natural images. Existing methods typically fine-tune heavy vision encoders for isolated tasks, incurring substantial computational overhead while overlooking the underlying commonalities across heterogeneous tasks. In this work, we propose FreqDINO++, a frequency-guided multi-task routing vision foundation model for universal ultrasound analysis. We first introduce a Multi-task Routing Adapter (MR-Adapter) to support parameter-efficient integration of task-common and task-specific knowledge, a Frequency-aware Feature Enhancer (F$^2$-Enhancer) is then designed to capture the rich multi-scale frequency characteristics of ultrasound images, and a Task-aligned Collaborative Decoder (TC-Decoder) is devised to promote collaboration between dense and global prediction tasks through global-local token interaction. Extensive experiments on large-scale multi-task and external single-task ultrasound benchmarks demonstrate that FreqDINO++ consistently outperforms strong baselines and recent foundation models across 27 diverse clinical task scenarios, while also showing promising generalization to unseen data. The code is at https://github.com/MingLang-FD/FreqDINO-Plus.

cs.CV↗
arXiv2026

The Unbearable Weight: Scaling Models and Methods for UAV Audio Classification

As unmanned aerial vehicles (UAVs) become increasingly prevalent in consumer and defense settings, classifying them reliably from limited, modality-specific data is an urgent challenge. The dominant approach, large pretrained networks fully fine-tuned on task data, carries a substantial computational and memory weight that is hard to bear in resource-constrained UAV deployments, where edge inference and rapid retraining for emerging platforms are both required. This paper systematically scales across both model architectures and fine-tuning methods for UAV audio classification, asking when that weight is justified and when lighter alternatives prevail. Using a custom dataset of 3,100 audio clips spanning 31 drone classes, we evaluate transformer (ViT, AST) and convolutional (custom CNN, ResNet-18/152, MobileNet-V3-S/L, EfficientNet-B0/B7) backbones under full fine-tuning, classifier-only fine-tuning, and four parameter-efficient fine-tuning (PEFT) methods: SSF, IA3, OFT, and selective batch-norm tuning. All configurations are evaluated with 5-fold cross-validation across accuracy, training time, trainable-parameter share, and inference-time memory footprint. Selective batch-norm fine-tuning of EfficientNet-B7 with three-fold augmentations achieves the highest validation accuracy (97.65% +- 0.30) while updating under 0.5% of model parameters. Across the sweep, lightweight CNNs consistently outperform transformers on both accuracy and efficiency. For UAV audio classification under data scarcity, scaling the method outperforms scaling the model.

cs.SD↗
arXiv2026

A Gradient-Based Capacity Accreditation Framework in Resource Adequacy: Formulation, Computation, and Practical Implications

Probabilistic resource adequacy assessment is a cornerstone of modern capacity accreditation. This paper develops a gradient-based framework, in which capacity accreditation is interpreted as the directional derivative of a probabilistic resource adequacy metric with respect to resource capacity, that unifies two widely used accreditation approaches: Effective Load Carrying Capability (ELCC) and Marginal Reliability Impact (MRI). Under mild regularity conditions, we show that marginal ELCC and MRI yield equivalent accreditation factors, while their numerical implementations exhibit markedly different computational characteristics. Building on this framework, we demonstrate how infinitesimal perturbation analysis enables up to a $1000\times$ speedup in gradient estimation for capacity accreditation, and we implement gradient-informed search algorithms that significantly accelerate ELCC computations relative to standard bisection methods. Large-scale Monte Carlo experiments show that MRI achieves substantial runtime reductions compared to ELCC and exhibits greater robustness to perturbation step-size selection. These results provide practical guidance for implementing efficient and scalable capacity accreditation in large-scale power systems.

eess.SY↗
arXiv2026

Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping

Long-horizon online visual mapping requires continuous camera-motion and scene-geometry estimation under bounded computation. Recent feed-forward 3D reconstruction models provide strong geometric priors, but streaming variants often predict poses in a fixed or historically maintained coordinate system, leading to train--test mismatch, early-anchor attention bias, and accumulated drift. We propose \emph{Anchor3R}, a current-centric streaming 3D reconstruction framework that predicts window-relative poses and local geometry in the current-frame coordinate system. Overlapping predictions form a dense relative-pose graph, supporting online pose updates and loop-aware motion averaging for global reconstruction. Experiments on indoor, outdoor, driving, and RGB-D benchmarks demonstrate improved long-horizon pose accuracy and dense reconstruction quality over existing streaming baselines. Despite being trained only on 48-frame sequences, Anchor3R directly generalizes to streams exceeding 10,000 frames while maintaining bounded GPU memory during online inference. Code is available at https://github.com/polar-explorer/Anchor3R.

cs.CV↗
arXiv2026

REAL-Q: E2E LLM Quantization via Dynamic Gradient Descent

Post-training quantization (PTQ) is essential for deploying large language models (LLMs) under strict resource constraints. State-of-the-art PTQ methods quantize each layer with a single closed-form second-order solver: to remain analytically tractable, they heavily approximate the global loss (dropping cross-channel coupling, pooling output rows into groups), and they then freeze the resulting Hessian across the entire layer, with no way to refresh it as the loss landscape shifts column by column--a phenomenon we call information misalignment. We propose REAL-Q (Real-time E2E-loss Aligned LLM Quantization), a novel PTQ paradigm that breaks this compromise: instead of diluting the objective for the sake of analytic tractability, REAL-Q targets an end-to-end-aligned surrogate of the global loss and refines it via fine-grained, dynamic Block-wise Gradient Descent applied after every column block (128 columns). By coupling this fine-grained correction with a sliding window mechanism for smooth cross-layer transitions, REAL-Q effectively mitigates error propagation across the network. On LLaMA-3.1 (8B and 70B) and Qwen3 (0.6B-32B) at W4A16, REAL-Q reduces end-to-end KL divergence by up to ~49% relative to state-of-the-art globally-guided methods.

cs.LG↗
arXiv2026

Generative AI for Analysts

We study how generative artificial intelligence (GenAI) reshapes financial analysts' information production. Using the 2023 integration of GenAI into FACTSET as a plausibly exogenous change in AI access, we find that FACTSET-associated reports become markedly richer--featuring 26% more distinct information sources, 24% broader topical coverage, and 21% more analytical methods--while also improving timeliness. However, these gains do not uniformly improve decision quality: relative forecast accuracy declines when analysts face greater information-processing demands. Yet, a machine-learning benchmark processing the same observable inputs shows no analogous deterioration, pointing to a human processing constraint rather than poorer underlying information. Placebo tests using other data vendors make a common platform-wide technology trend unlikely. Overall, GenAI relaxes information-acquisition constraints while making human attention a more important bottleneck.

q-fin.ST↗