Searcharxiv⌕ Search

arXiv subjects

Yu Wu

Publications and source records attributed to Yu Wu.

At least 19 recordsLinked to original sources
arXiv2026

Understanding the superconducting proximity effect in semiconductors through quantum oscillations

Superconductor-semiconductor hybrids host emergent states of matter and offer a platform for new qubits, but the superconducting metal shunts electrical transport, which rules out conventional semiconductor characterization and leaves the hybrid parameters to speculation. Here we determine density, mass, $g$-factor, mobility and subband occupation beneath the superconductor, from Shubnikov-de Haas oscillations of a buried InAs quantum well under Al, Sn, V, Nb, Ta and Re films, with a Dingle analysis that accounts for the shunt. Every metal adds an interface subband whose occupation falls into one of two classes, whereas the mass and $g$-factor of the buried well are unchanged to within 10\%. Within the uncertainty set by the transport mobility, no film shortens the quantum lifetime of the buried well, and Al and Sn lengthen it. Quantum lifetimes bound the hybridization of the interface subband to 2-4~meV. These measurements supply the normal-state parameters that tunnelling spectroscopy renormalizes but cannot measure.

cond-mat.supr-con↗
arXiv2026

Aligning Multi-Trajectory Supervision with Policy Optimization for VLA Driving

Vision-language-action (VLA) driving methods increasingly combine multi-trajectory imitation learning with group-relative policy optimization (GRPO), making trajectory selection critical to final performance. However, some high-scoring trajectories that improve imitation can degrade subsequent GRPO by inducing advantage estimates misaligned with the current policy's feasible behavior distribution, driving updates away from safe and compliant behaviors. To address this, we propose a novel framework that aligns multi-trajectory supervision with policy optimization. To address the policy gradient bias induced by infeasible noisy trajectories outside the feasible region, augmented trajectories are constrained to a neighboring manifold of the ground-truth feasible region, and a Pareto-optimality criterion is adopted in place of the conventional aggregate score, retaining only non-dominated candidates and thereby filtering out conflicting samples at the source. To ensure that expanded trajectory supervision is effectively absorbed during policy optimization, we introduce two complementary mechanisms: feasibility-first advantage assignment and dynamic distillation. The former adapts Pareto credit to the feasibility composition of each rollout group and guides fully infeasible groups toward safe references. The latter updates teacher trajectories across refinement rounds to continually transfer useful supervision. Together, they progressively translate the benefits of expanded supervision into policy improvement. On NAVSIM v1 and v2, our method achieves 91.4 PDMS and 89.1 EPDMS, respectively, under single-trajectory inference, and recovers 440 of 658 initially failed scenes, 11.1\% higher than the original GRPO baseline.

cs.CV↗
arXiv2026

Dimensionality Mismatch Enables Decoupled Heat and Charge Transport

Decoupling heat and charge transport is a key challenge in thermoelectrics. Here, we identify a route to spatially separate phonon and carrier transport in quasi-one-dimensional materials through high-throughput screening of the Materials Project database. Representative Sn$_2$S$_3$ and SbTeI exhibit a strong-intrachain--weak-interchain bonding hierarchy that favors phonon propagation along the chains while suppressing transverse lattice heat transport. In contrast, transverse valence-band states provide effective interchain electronic coupling and relatively light hole transport. This mismatch between lattice and electronic transport dimensionalities produces an inverted thermal--electrical anisotropy. Across the screened candidates, interchain lattice thermal conductivity is strongly suppressed, whereas hole transport remains weakly anisotropic or even favors the interchain direction. For SbTeI, this decoupling yields a maximum $zT$ of approximately 2.1 near 900~K. These results establish dimensionality mismatch as a general strategy for decoupling phonon and carrier transport in thermoelectric materials.

cond-mat.mtrl-sci↗
arXiv2026

RetroMPA: A Molecular Property-Aware Auxiliary Framework for Enhancing Retrosynthesis Prediction

Retrosynthesis is a cornerstone of drug discovery and organic synthesis. While data-driven deep learning models have shown remarkable progress, they autonomously learn reaction patterns from extensive datasets with limited integration of established chemical knowledge as priors. To address this limitation, we introduce RetroMPA, a molecular property-aware, post-hoc enhancement module that injects chemical knowledge into the retrosynthesis pipeline. Rather than functioning as an independent SMILES sequence generator, RetroMPA is a broadly applicable, model-agnostic chemical filter designed to recalibrate and optimize the predictive pathways of existing algorithms. This plug-and-play framework integrates seamlessly with a range of data-driven retrosynthesis methods, enhancing outputs without modifying model architecture or requiring resource-intensive retraining. By leveraging a property-aware latent embedding space, RetroMPA consistently improves top-1 accuracy across eight representative retrosynthesis models by an average of 5.50% on USPTO-50K. Furthermore, we validate its scalability on the large-scale USPTO-Full dataset, achieving an average improvement of about 2.03% across both template-based and template-free architectures. Wet-lab experiments provide preliminary support for the practical utility of the framework. These syntheses confirmed viable, previously unreported substrate combinations for classic reaction paradigms---specifically, Suzuki-Miyaura coupling, Bucherer reaction, and Friedel-Crafts acylation---suggesting that RetroMPA can operate beyond mere data fitting. The code is open-sourced at https://github.com/MengzhouLu/RetroMPA.

cs.LG↗
arXiv2026

ReliaGate: Reliability Routing for Low-Stakes Wearable Stress Prediction

We study when a wearable stress system should surface a prediction rather than change it. In low-stakes reflection and summary settings, aggregate accuracy is insufficient because withholding can reduce error while leaving some people with little or no information. We formulate fixed-label reliability routing: after a locked classifier emits a protocol-defined stress/non-stress label, a post-hoc gate surfaces that unchanged label or withholds it as unavailable. ReliaGate assembles established confidence, signal-quality/trust, agreement, train-standardized atypicality, and train-fitted geometry cues into a post-hoc correctness score. We evaluate four wearable datasets using subject-disjoint folds, validation-selected routing, paired held-out-subject intervals, and pooled and per-subject analyses. WESAD point estimates favored ReliaGate, UBFC-Phys primary coverage/risk intervals favored ReliaGate, and E4 checks were mixed. ReliaGate provides an operational framework for studying surfaced-label error, output availability, and accepted-output distribution across subjects, without revising labels or providing clinical or finite-sample risk guarantees.

cs.LG↗
arXiv2026

Exposing SIMD Parallelism in SQIsign: An AVX-512 Implementation

Modern isogeny-based cryptosystems spend much of their running time in finite-field, elliptic-curve, and higher-dimensional isogeny arithmetic. Exploiting SIMD parallelism is nontrivial: routines such as Montgomery ladders contain loop-carried dependencies, while point, pairing, and theta-coordinate formulas expose only irregular fine-grained parallelism. We show that substantial SIMD parallelism can be recovered by reorganizing the arithmetic dependency graphs of higher-level primitives rather than vectorizing field multiplication in isolation. We develop an end-to-end AVX-512IFMA implementation of SQIsign in which data remain in a radix-$2^{51}$ vector representation across most of the curve-side computation. Our redesign includes projective xDBLADD schedules, batched point doubling in several coordinate systems, a vectorized biscalar ladder, fused cubical-arithmetic pairing steps, and batched one- and two-dimensional isogeny evaluation. Relative to the reference C implementation, we achieve end-to-end speedups of $1.76\times$, $1.71\times$, and $3.18\times$ for key generation, signing, and verification at NIST level~I; combined with Qlapoti, key-generation and signing speedups rise to $2.90\times$ and $2.69\times$. We further apply the same backend and methodology to CORAL, a recent isogeny group action for post-quantum non-interactive key exchange based on two-dimensional $2$-isogenies. Across five parameter sets, this yields $1.28$--$1.40\times$ speedups for key generation and $1.92$--$2.46\times$ for shared-key computation. These results provide cross-scheme evidence that algorithm-level SIMD scheduling is a reusable optimization dimension for higher-dimensional isogeny cryptography.

cs.CR↗
arXiv2026

Quantum Incremental Learning with Mixed State Prototypes

Incremental learning models are required to learn new classes sequentially without catastrophic forgetting, while operating under parameter and memory constraints. In the Noisy Intermediate-Scale Quantum (NISQ) era, although quantum neural networks offer advantages in feature mapping, hardware limitations restrict circuit width. Furthermore, traditional quantum classifiers are constrained by the number of orthogonal basis states, limiting their capacity to accommodate a continually growing number of categories. Thus, we introduce a novel quantum incremental learning framework based on trainable mixed-state prototypes. Its original design incorporates new classes by adding class prototypes rather than increasing the circuit width of the shared quantum backbone. The use of mixed-state prototypes is another key contribution, since they have representation capabilities to represent information than a single pure-state prototype. And the decomposable mixed-state calculation provides lower production costs and a convenient Hilbert-Schmidt (HS) distance metric for classification. Simulation results show that our model achieves high-dimensional feature concentration using a minimal number of qubits, while demonstrating lower computational complexity and robust representation in incremental learning tasks compared with classical baselines.

cs.AI↗
arXiv2026

SimWAM: A Simple World Action Model for End-to-End Autonomous Driving

World-Action Models (WAMs) improve end-to-end autonomous driving by transferring video dynamics priors to action prediction, but existing methods incur costly test-time future imagination. We present SimWAM, a simple yet effective WAM that leverages future-video prediction as a training-time supervision signal. It co-trains a pretrained video expert and a lightweight action expert with joint flow matching. An isolated attention mask keeps action prediction independent of future frames, allowing trajectory prediction without explicit future-frame generation at inference. Since the two experts share no parameters and interact only through a unified attention interface, the video backbone could be replaced and the action expert scaled independently without modifying the learning objective or inference pipeline. We further apply reinforcement learning to optimize a compositional driving reward beyond trajectory imitation. Our SimWAM achieves 91.5 PDMS on NAVSIM, surpasses state-of-the-art WAM-based planners with substantially lower latency, and transfers zero-shot to nuScenes. These results position SimWAM as a simple yet solid baseline that could readily benefit from advances in video generation for efficient autonomous driving. The code and model weights are available at https://github.com/H-EmbodVis/SimWAM/.

cs.CV↗
arXiv2026

Outcome-Guided Distillation: A Teacher-Student Framework to Advance VLM Reasoning in Autonomous Driving

End-to-end (E2E) autonomous driving aims to learn a direct mapping from visual observations to control actions. However, these E2E models often act as black boxes and struggle with complex scenarios. To address this, recent works incorporate Vision-Language Models (VLMs) to provide explicit reasoning, enhancing both interpretability and driving robustness. These approaches typically rely on pre-generated annotations, which suffer from potentially flawed labels and require costly human labor. In this work, we propose a new framework that integrates structured reasoning and geometric precision through a teacher-student architecture. The teacher model introduces reflective reasoning, where the VLM generates logical explanations and then reflectively refines the reasoning under the supervision of ground-truth action. This enhances zero-shot generalization without intermediate labels. The student model distills the teacher's reasoning capabilities via supervised fine-tuning. We also design a separate waypoint decoder that interprets textual reasoning into continuous trajectories. Our proposed solution integrates two goals: providing explicit reasoning for interpretability and delivering robust and accurate driving performance. It leverages the synergy between these two objectives within a staged inference engine to enhance driving performance and explicitly uses the reasoning to guide driving prediction. Evaluated on Waymo benchmarks, our framework outperforms classical reasoning-based baselines in zero-shot reasoning, waypoint accuracy, and inference efficiency. Our experiments validate this design, demonstrating that the reasoning text makes a significant contribution to driving inference, resulting in around a 24% improvement in performance compared to an identical model that lacks reasoning. Our work advances reasoning-driven autonomous driving toward interpretable and deployable systems.

cs.RO↗
arXiv2026

Amplitude- and frequency-modulated combs from an actively locked metasurface external-cavity laser

Optical frequency combs are key components of several photonics applications including spectroscopy, communications, and ultrafast photonics. A central challenge in frequency-comb photonics is to develop sources whose operating state can be precisely controlled and adapted to different application needs. We introduce frequency comb functionality to a THz metasurface vertical-external-cavity-surface-emitting laser (VECSEL), combining its characteristic high output power and excellent beam quality with a reconfigurable comb output. The source exhibits reversible switching between actively mode-locked 3.5 ps-long pulses and stable frequency-modulated quantum walk comb states. The flexible control of the intermodal phase relation is achieved through careful dispersion engineering via a Gires-Tournois interferometer (GTI) output-coupler combined with resonant RF bias modulation of the metasurface. These results pave the way for on-demand comb control in the THz range and provide a versatile strategy that could be extended to other semiconductor frequency-comb platforms and wavelength ranges.

physics.optics↗
arXiv2026

DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation

Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification. While recent parallel drafters efficiently propose long token sequences in a single forward pass, they suffer from rapid acceptance decay due to a lack of inter-token dependencies. Furthermore, indiscriminately verifying these extended blocks wastes critical batch capacity on tokens with high rejection risks, severely degrading throughput in high-concurrency serving systems. We introduce DSpark, a speculative decoding framework that unifies high-throughput parallel generation with adaptive, load-aware verification. To maintain draft quality, DSpark utilizes a semi-autoregressive architecture, coupling a parallel backbone with a lightweight sequential module, to introduce intra-block dependency modeling and mitigate suffix decay. To optimize system efficiency, DSpark employs confidence-scheduled verification, dynamically tailoring the verification length for each request based on estimated prefix survival probabilities and engine-specific throughput profiles. On offline benchmarks across diverse domains, DSpark substantially improves the accepted length over state-of-the-art autoregressive and parallel drafters. When deployed within the DeepSeek-V4 serving system under live user traffic, DSpark successfully mitigates verification waste. Compared to the established production baseline (MTP-1), DSpark accelerates per-user generation speeds by 60 to 85 percent at matched throughput levels. More importantly, by preventing severe throughput degradation under strict interactivity constraints, it enables performance tiers that were previously unattainable, shifting the Pareto frontier of our serving system.

cs.AI↗
arXiv2026

NanoBTE: Fast Iterative Solution of the Phonon Boltzmann Transport Equation for Nanoscale Heat Transport

Nanoscale heat dissipation has become a critical challenge in advanced semiconductor devices, where phonon transport can strongly deviate from the classical Fourier description due to the boundary scattering and ballistic effects. In this work, we propose NanoBTE, a deterministic finite-volume solver for the non-gray phonon Boltzmann transport equation under the relaxation-time approximation. The solver supports complex two- and three-dimensional geometries, band-resolved phonon properties, discrete-ordinates angular quadrature, volumetric heat generation, and multiple phonon boundary conditions, including thermalizing, diffuse, and specular reflections. %To improve the efficiency of multiscale simulations, both sequential and synthetic iterative schemes are implemented, where the latter couples the microscopic phonon transport equation with a macroscopic diffusion-type temperature equation to accelerate convergence in near-diffusive regimes. Both sequential and synthetic iterative options are implemented for the steady-state solution. Furthermore, NanoBTE adopts a band-direction task decomposition strategy, enabling efficient MPI-based CPU parallelization and GPU acceleration of the dominant sparse transport operations.

cond-mat.mtrl-sci↗
arXiv2026

PyMETA: A Benchmark Dataset for Hierarchical Student Code Error Classification with Python-Interpreter-Based Labels

With the advancement of Large Language Models (LLMs), code error detection has extended beyond traditional IDE diagnostics to context-sensitive debugging in educational scenarios. However, existing approaches lack large-scale datasets, multi-error analysis, and unified error taxonomies. To address this, we introduce PyMETA, a large-scale Python code error classification dataset of 48,646 student submissions, with single-error labels for all samples and a diagnostic subset of 97 expert-annotated multi-error samples. The dataset uses a three-level hierarchical taxonomy, from a binary error/no-error split down to 14 fine-grained error types grounded in Python's official exception hierarchy. We evaluate multi-level classification tasks on two finetuned models and four LLMs with prompting, comparing their classification performance and runtime cost. For multi-error prompting, the best model, Gemini 2.5 Pro, achieves 81.8% macro F1 under the "contains" criterion. We observe that: 1) prompted LLMs still underperform finetuned smaller models; 2) models exhibit significant disparities across error types; 3) most LLMs over-classify code as Logic Error, with GPT-3.5 showing the highest Logic Error Overprediction Rate and Gemini 2.5 Pro the lowest. Our work establishes a data foundation and provides insights for LLM-based code error research.

cs.SE↗
arXiv2026

SIFT: Self-Imagination Fine-Tuning for Physically Plausible Motion in Video Diffusion Models

Recent advances in video diffusion models have greatly improved visual fidelity, yet their generated motions often violate physical plausibility. We observe a common kinematic failure, "motion entanglement", the unintended coupling of independent motion sources, such as camera movement and object motion. We identify that this issue stems from data bias and the reconstruction-based training design of diffusion models. Training on noisy videos that still retain coarse motion cues inadvertently encourages the model to replicate existing motion without an incentive to learn how to model kinematically-grounded motions. To address this, we propose a Self-Imagination Fine-Tuning (SIFT) paradigm, which enables the model to learn from its own generated videos rather than directly reconstructing real ones, breaking the reconstruction shortcut. We further employ motion-aware discriminative supervision and a progressive hard-case replay strategy to stabilize and accelerate learning. By leveraging freely-generated text prompts, our method can densely cover a broad motion space, including rare or finely-disentangled scenarios that would be costly to collect as video data. Extensive experiments demonstrate that our approach substantially improves the physical realism, motion disentanglement, and controllability of generated videos.

cs.CV↗
arXiv2026

Qwen-Image-2.0-RL Technical Report

We present Qwen-Image-2.0-RL, a post-training pipeline that applies reinforcement learning from human feedback (RLHF) and on-policy distillation (OPD) to improve both the visual quality and instruction-following capability of the Qwen-Image-2.0 diffusion model. To provide reliable reward signals, we construct task-specific composite reward models by fine-tuning vision-language models with a pointwise scoring paradigm and chain-of-thought reasoning. For text-to-image generation, the reward models cover alignment, aesthetics, and portrait fidelity dimensions. For image editing tasks, the reward system addresses instruction-following accuracy and face identity preservation. Building on this reward system, we develop a scalable GRPO-based RL training framework, incorporating a hybrid classifier-free guidance (CFG) strategy to preserve pre-trained knowledge, prompt curation via intra-group reward range filtering, and per-category reward weight calibration. To merge the task-specialized RL policies for T2I and editing, we propose on-policy distillation as the final training stage, which consolidates multiple teachers into a single student model through trajectory-level velocity matching. Extensive evaluation shows that Qwen-Image-2.0-RL achieves 57.84 overall score on Qwen-Image-Bench (+2.61 over the base model), Elo ratings of 1193 in text-to-image arena (+78) and 1349 in image edit arena (+93), demonstrating consistent gains in aesthetic quality, prompt adherence, and editing accuracy.

cs.CV↗
arXiv2026

Restoring Initial Noise Sensitivity in Text-to-Image Distillation via Geometric Alignment

Generative distillation significantly accelerates text-to-image (T2I) generation by compressing multi-step trajectories into few-step student models while preserving perceptual quality. However, existing methods primarily optimize efficiency and output fidelity, often neglecting critical properties of the original trajectory. In this work, we identify a key missing property: sensitivity to initial noise, whose degradation impairs downstream control methods relying on noise-based optimization and manipulation. We trace this issue to standard distillation objectives that enforce pointwise output alignment, inadvertently flattening the input-output landscape and suppressing the teacher's local geometric structure. To address this, we propose Geometry-Aware Distillation (GAD), a sensitivity-preserving framework that aligns the local functional behavior of teacher and student models. Specifically, GAD matches Jacobian-vector products with respect to input noise, enabling the student to reproduce the teacher's differential response to perturbations. Extensive experiments across multiple T2I paradigms and noise-driven control tasks demonstrate that GAD significantly restores sensitivity and improves diversity while maintaining high visual fidelity. Code is available at https://github.com/Hannah1102/GAD.

cs.CV↗
arXiv2026

Gate Parameter Lee-Yang Zeros and Dynamical Phases in Quantum Circuits

We propose gate-parameter Lee-Yang zeros of Loschmidt amplitudes as probes of dynamical phases in finite quantum circuits. We study Floquet circuits constructed from two-qubit fSim gates with identical parameters, for which the Loschmidt amplitude becomes a rational function of the gate parameters after a suitable change of variables. At fixed system size and large circuit depth, the zeros in one complexified gate parameter, with the other held fixed, condense onto limiting curves. In contrast to conventional Loschmidt or Fisher zeros in complex time, these zeros live directly in the complex plane of a tunable gate parameter. We show that the limiting set has two origins: a state-dependent component controlled by overlaps with Floquet eigenstates, and a universal component fixed by the Floquet spectrum. As the remaining gate parameter is varied, the universal zero set reorganizes abruptly, providing a finite-qubit diagnostic of a dynamical phase transition. We demonstrate this behavior in a Bethe ansatz solvable brickwork circuit and in longer-range fSim circuits outside this solvable structure. The mechanism follows from the Beraha-Kahane-Weiss theorem together with local unitarity, and is therefore spectral rather than a special consequence of integrability.

quant-ph↗
arXiv2026

Simplified criteria for identifying and designing altermagnetic crystals in real space

Altermagnetism is a compensated magnetic phase characterized by zero net magnetization and exchange-driven spin splitting. However, identifying altermagnets among collinear antiferromagnets usually requires full magnetic-space-group or spin-group analysis, which is not always intuitive. Here we formulate a simple real-space criterion based on how the crystallographic operations of the host nonmagnetic structure permute the two opposite-spin sublattices. We show that altermagnets usually exist on collinear compensated antiferromagnets whose magnetic primitive cell coincides with the host nonmagnetic crystallographic primitive cell. In this case, altermagnetic spin splitting is generally allowed unless an inversion-type operation exists that exchanges the two opposite-spin sublattices. Using chemically ordered Mn2SSe prototypes derived from zinc-blende or rocksalt parent structures, we demonstrate that these criteria can be easily used to construct the three symmetry classes by controlling chemical ordering and magnetic-sublattice permutation. Similar rules can also be applied to low-dimensional crystals or quasicrystals. Our work reduces the identification of altermagnets to a transparent real-space symmetry test and provides a practical route for designing altermagnetic crystals.

cond-mat.mtrl-sci↗