arXiv subjects

Song Liu

Publications and source records attributed to Song Liu.

At least 19 recordsLinked to original sources

arXiv2026

Evidence for Three-component Interlayer Coherent Exciton Condensation

Increasing the number of internal components in a quantum many-body system can host collective orders inaccessible to simpler settings. Quantum Hall bilayers provide a canonical realization of interlayer exciton condensation, yet extending such coherence across three independently addressable electronic fluids has remained elusive. Here we report evidence for three-component interlayer coherent exciton condensation in triple-layer graphene system. Using Rydberg excitons in an adjacent WSe2 monolayer as a layer-sensitive optical probe, we resolve interaction-induced incompressibility at zeroth-Landau-level crossings for all three pairwise layer combinations, establishing top-middle, middle-bottom and top-bottom exciton condensate channels within the same device. Independent control of displacement field and interlayer bias continuously tunes these pairwise states towards a regime where Landau levels from all three layers approach simultaneous degeneracy. At their convergence, incompressibility persists while the exciton energy and spectral weight evolve smoothly between the pairwise limits, suggesting coherent participation of all three layers in a single three-component state. More broadly, the ability to independently control layer potentials and engineer interlayer interactions establishes multilayer graphene as a programmable synthetic dimension for exploring higher-component quantum Hall order and simulating strongly correlated quantum matter.

cond-mat.mes-hall↗

arXiv2026

Guidance for Prior Change via Density Ratio Estimation

Simulation-Based Inference (SBI) serves as a vital framework for parameter inference in scientific fields where simulators involve intractable likelihoods, yet while amortized generative models offer rapid posterior estimation, they are often restricted by the specific priors used during training, thereby limiting their flexibility as prior knowledge evolves. To address this prior dependency, PriorGuide was introduced as an inference-time guidance method, but due to its intractable formulation, it relies on Gaussian approximations of the reverse transition kernel and Gaussian mixture model fitting for the prior ratio, both of which introduce systematic bias. Motivated by these limitations, we propose an unbiased test-time guidance framework that leverages Density Ratio Estimation (DRE) to learn a score guidance term, effectively decoupling the inference process from the prior training. Moreover, our framework remains agnostic to the specific density ratio estimators, making it a general and flexible framework for handling prior changes. Experimental results across multiple tasks demonstrate that our method matches or outperforms PriorGuide on C2ST and MMD in most tasks while maintaining robustness even under limited overlap between the training and target priors. Furthermore, we apply our method to Bayesian updating for parameter inference from planetary light-curve data, where it also demonstrates strong effectiveness and robustness. Code is available at https://github.com/a-chenchen/dre-based-prior-guidance .

stat.ML↗

arXiv2026

Demonstrating advantages of dynamic quantum circuits on a hybrid superconducting qubit-cavity processor

Dynamic quantum circuits (DQCs) provide a hardware-efficient route to quantum computing by reducing physical-qubit overhead and compressing circuit topology through mid-circuit measurements, qubit reset and reuse, and classical feed-forward control. Here, we demonstrate the advantages of DQCs on a single hybrid superconducting qubit-cavity processor by implementing a hierarchy of algorithms with increasing complexity. This hybrid architecture consists of a high-dimensional cavity qudit serving as the computational register and a dispersively coupled superconducting transmon ancilla that is repeatedly measured, reset, and reused to enable dynamic control. Using this device, we implement a 10-bit Bernstein-Vazirani algorithm with an average success probability of 82%, surpassing state-of-the-art dynamic and static implementations in both scale and performance; an 8-bit quantum phase-estimation protocol with estimation errors below 10-3; and the first dynamic-circuit implementation of Shor's algorithm on a superconducting platform, factoring 15 over all coprime bases with squared statistical overlap values above 99.8%. These results provide concrete benchmarks for future DQC implementations and highlight the versatile advantages of DQCs with the hybrid qubit-qudit architecture, establishing it as a promising route toward scalable, programmable quantum computation.

quant-ph↗

arXiv2026

AngelSpec: Towards Real-World High Performance Inference with Speculative Decoding

Speculative decoding accelerates large language model inference without changing the target distribution, but no single drafting structure performs best across real-world workloads. Autoregressive multi-token prediction (MTP) is a lightweight, stable proposal mechanism, whereas block-parallel diffusion amortizes drafting latency over much longer candidate sequences; the better choice depends strongly on the output distribution. We present AngelSpec, a unified training framework for MTP and block-parallel speculative decoding that addresses this heterogeneity at three levels. At the training level, rather than fitting one universal drafter to a uniform data mixture, we co-specialize structure and data: the MTP drafter is trained on diverse conversational data for high-entropy open-ended chat, and the block-diffusion drafter on code and mathematics data for longer predictable continuations. At the architecture level, we propose DFly, a block-diffusion framework combining a hybrid target-conditioning backbone with a predecessor-conditioned autoregressive head, improving target-feature utilization and intra-block dependency modeling while keeping generation parallel. At the inference level, both acceptance length and verification cost vary with domain, request, online load, and hardware, so DFly treats verification as a shared batch-level resource: it reallocates compute toward high-confidence prefixes across requests and combines expected utility with a profiled cost model to adapt verification depth online. Across the Hy3 series, DFly raises the average accepted length on Hy3-A21B by roughly 30% and attains the highest average throughput at every tested concurrency from 4 to 64, a 1.98-2.40x speedup over autoregressive decoding and 10.5-11.8% higher throughput than DFlash. We release AngelSpec to support training and extending these methods.

cs.CL↗

arXiv2026

Zero-Flow Two-Sample Tests

We propose a new approach to two-sample testing for deciding whether two sets of samples are drawn from the same distribution. The test is built on a statistical discrepancy based on the zero-flow criterion, termed zero-flow discrepancy (ZFD). We prove the validity of ZFD and propose a practical testing procedure, termed the zero-flow two-sample test (ZF2ST). The key idea is to learn how samples from the two distributions are locally misaligned and use the resulting directional pattern as evidence of distributional difference. By separating witness learning from hypothesis evaluation, ZF2ST can use flexible neural networks while maintaining valid statistical calibration. We develop both regression-based and power-maximized approaches for learning the witness. Experiments on synthetic and image datasets demonstrate that ZF2ST can achieve strong testing power for structured distributional changes while maintaining well-calibrated type-I error.

cs.LG↗

arXiv2026

D-cut: Adaptive Verification Depth Pruning for Batched Speculative Decoding

Speculative decoding accelerates large language model (LLM) inference without compromising output quality. Recent parallel drafting methods further improve single-request performance by decoupling draft length from drafting latency, enabling longer drafts and higher mean accepted tokens (MAT). However, under high request concurrency, long drafts waste substantial computation on rejected tokens, increasing verification cost and potentially making speculative decoding slower than autoregressive decoding. We present D-Cut, an adaptive pruning method that selects draft tokens jointly across the batch and concentrates the verification budget on tokens most likely to be accepted. D-Cut is motivated by two observations. First, acceptance lengths vary considerably across concurrent requests; D-Cut therefore performs cross-request pruning, allocating the verification budget adaptively according to draft confidence. Second, verification cost depends strongly on the deployment environment, including GPU architecture and parallelism strategy; D-Cut incorporates a runtime cost model to adapt its pruning depth to the target environment. Experiments on dense and mixture-of-experts (MoE) models show that, under high concurrency, D-Cut improves the average speedup from $1.26\times$ to $1.65\times$, restores acceleration in dense-model configurations where long-draft baselines are slower than autoregressive decoding, and achieves up to $3.0\times$ speedup over autoregressive decoding on MoE models.

cs.CL↗

arXiv2026

One Demonstration Is Enough for Real-World Robotic Reinforcement Learning

Learning effective robot control policies on physical hardware is challenging due to costly data collection and the difficulty of reward specification. Prior work has incorporated demonstrations into reinforcement learning (RL), yet existing approaches either require large numbers of demonstrations or depend on continuous human intervention during training. To address these limitations, we present AutoSERL, a framework that leverages a single demonstration to fully automate the intervention process in real-world robot RL. The framework includes three complementary mechanisms to accomplish certain tasks: a sliding window intervention mechanism that continuously guides exploration to prevent local optima and unsafe deviations, a safety recovery mechanism that detects and corrects failure states via predefined trajectory recovery points, and an intervention termination criterion that automatically disables guidance once the policy can independently complete the task, preserving its exploration advantage. We evaluate AutoSERL on six contact-intensive manipulation tasks across two robot platforms, spanning insertion, hanging, and hinge-based tasks. AutoSERL consistently outperforms SERL initialized with 20 demonstrations, behavior cloning, and MILES -- a dedicated one-shot imitation learning baseline -- across all tasks while matching HIL-SERL, achieves 100% success rate on insertion tasks, and demonstrates improved robustness to positional variations, all from a single demonstration. Code and videos are available on our project website: https://autoserl.github.io/.

cs.RO↗

arXiv2026

Supermoir\'e Chern mosaic in helical trilayer WSe2

Helically twisted multilayers offer access to moir\'e physics beyond the single-superlattice paradigm, yet their correlated and topological transport properties remain largely unexplored in semiconductor moir\'e materials. Here we report magnetotransport measurements of helical trilayer WSe2, in which two coupled moir\'e patterns relax into a supermoir\'e landscape composed of inequivalent local topological domains with distinct electronic structures and unequal spatial areas. By electrostatic tuning, we identify a trilayer-hybridized regime where interactions and real-space reconstruction combine to generate a plethora of magnetic and topological states absent in the twisted bilayers. At moir\'e filling factor $\nu$ = -1, we observe a ferromagnetic insulating state that is robust against magnetic field and accompanied by a non-quantized anomalous Hall response ~-4 kOhms. This behaviour is consistent with a time-reversal-symmetry-breaking supermoir\'e Chern mosaic, in which the Hall response arises from the non-cancelling contributions of local domains with opposite Chern character arranged by the relaxed structure. Under strong magnetic fields, a symmetry-broken Chern insulating state (C = 1) emerges near $\nu$ = -2/3, displaying a much larger positive Hall response together with strongly enhanced longitudinal resistance, suggestive of field-reconstructed topological minibands and domain-boundary scattering. These results establish relaxed supermoir\'e semiconductor trilayers as a platform for spatially organized magnetism and topology beyond the bilayer limit.

cond-mat.str-el↗

arXiv2026

DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding

Block diffusion speculative decoding accelerates LLM inference by predicting all tokens within a block simultaneously for the target model to verify in parallel. Predicting an entire block at once requires a sufficiently capable draft model and effective utilization of the target model's internal knowledge. However, the state-of-the-art method DFlash constrains all draft layers to share a single fused representation derived from only a few target layers, limiting per-layer expressiveness and hindering further scaling of draft capacity. In this paper, we present \modelname, which flares out the narrow conditioning bottleneck of DFlash through a lightweight layer-wise fusion mechanism: each draft layer attends to its own learnable combination of a broad set of target layers at negligible overhead, simultaneously injecting richer target knowledge and providing every draft layer with a distinct input. This enhanced per-layer expressiveness enables scaling the draft model to deeper architectures with consistent gains. We further scale training data from 800K to 2.4M samples to fully exploit the enlarged capacity. On six benchmarks spanning mathematical reasoning, code generation, and conversation, \modelname attains average wall-clock speedups of 5.52x on Qwen3-4B, 5.46x on Qwen3-8B, and 3.91x on GPT-OSS-20B, improving over DFlash by roughly 11\%, 8\%, and 5\% respectively. Our code is available at https://github.com/Tencent/AngelSlim.

cs.CL↗

arXiv2026

Non-uniqueness for the hyperdissipative Navier-Stokes equations with arbitrarily small subcritical data

In this paper, we consider the hyperdissipative Navier-Stokes equations with fractional dissipation $(-\Delta)^{\beta}$ with $\beta>1$. We prove that smooth solutions of the hyperdissipative Navier-Stokes equations are non-unique with arbitrarily small initial data in ${B}^{-\beta-\alpha}_{\infty,1}(\mathbb{T}^d)$ for any $\alpha>0$. Moreover, we show the existence of a solution with arbitrarily small initial data in ${B}^{-\beta-\alpha}_{\infty,1}(\mathbb{T}^d)$ ($\alpha>0$) that grows arbitrarily large in $\dot{B}^{-s}_{\infty,\infty}(\mathbb{T}^d)$ for all $s\in\mathbb{R}$ in arbitrarily small time. It is worth pointing out that ${B}^{-\beta-\alpha}_{\infty,1}(\mathbb{T}^d)$ lies in the subcritical regime when $0<\alpha<\beta-1$. To the best of our knowledge, this is the first non-uniqueness result of the Navier-Stokes equations with initial data at the subcritical regularity. To show the sharpness of the above results, we establish the local well-posedness of the hyperdissipative Navier-Stokes equations with initial data in $\dot{B}^{-\beta-\alpha}_{\infty,\infty}(\mathbb{T}^d)$ with $\alpha< 0$.

math.AP↗

arXiv2026

Signatures of quantum chaos in phonon-polariton billiards

We use scanning near-field optical microscopy to image hyperbolic phonon polaritons in hexagonal boron nitride (hBN) billiards with integrable and chaotic geometries. In Sinai billiards, we observe irregular mode patterns consistent with quantum scarring, together with an unexpected sensitivity to weak probe perturbations. These random-wave features coexist with non-chaotic one-dimensional boundary modes arising from nontrivial polariton reflection at the billiard edge. As the billiard boundary becomes increasingly complex, the Fourier transforms of the measured signals evolve toward ring-like structures consistent with Berry's random-wave conjecture. We develop a numerical framework based on the Helmholtz equation with generalized boundary conditions that encode angle-dependent reflection phase shifts. The calculated level statistics exhibit a crossover from Poisson-like behavior in integrable billiards to Wigner-Dyson-like behavior in chaotic geometries, with small deviations from the canonical form arising from nonlinear boundary conditions that require self-consistent bulk-boundary analysis. Theoretical analysis based on dissipative Green's functions qualitatively reproduces the near-field data. These results establish mesoscopic van der Waals billiards as a rich platform for studying generalized chaotic dynamics of hybrid light-matter polaritons.

cond-mat.mes-hall↗

arXiv2026

Destructive interference of second harmonic generation in AA stacked MoTe$_2$/WSe$_2$

The stacking configuration of two-dimensional materials critically governs their optical and electronic responses. Monolayer transition-metal dichalcogenides (TMDC) lack inversion symmetry and exhibit exciton-enhanced second-harmonic generation (SHG). In TMDC bilayers, 60{\deg} (0{\deg}) stacking is conventionally expected to suppress (enhance) SHG owing to destructive (constructive) interference of the layer-resolved nonlinear polarizations. Here, we report an unconventional destructive SHG interference in nearly 0{\deg}-stacked (AA-stacked) MoTe2/WSe2 heterobilayers using two independent probes: atomic-resolution imaging and stacking-sensitive exciton hybridization measurements. Supported by ab initio GW and Bethe-Salpeter equation calculations, we show that distinct two-photon resonances associated with the WSe2 C exciton and the MoTe2 D exciton generate a nearly $\pi$ phase difference ($\Delta\phi$) in their second-order nonlinear susceptibilities $\chi^{(2)}$, leading to the anomalous destructive interference. We further demonstrate that in small-angle twisted MoTe2/WSe2, the SHG polarization state is governed by the interplay between twist angle $\alpha$ and phase difference $\Delta\phi$, and can be mapped onto trajectories on the Poincar\'e sphere. At excitation energies satisfying $\Delta\phi$ + 3$\alpha$ = 180{\deg}, the SHG output becomes nearly circularly polarized (ellipticity ~ 0.91) and undergoes an abrupt 90{\deg} azimuthal rotation, corresponding to a geometric polarization singularity in the parameter space. Our findings open new routes for exciton-resonance engineered nonlinear photonics and stacking-resolved optical functionality in moir\'e materials.

cond-mat.mes-hall↗

arXiv2026

Adaptive KV Cache Reuse for Fast Long-Context LLM Serving

In long-context Large Language Model (LLM) inference, the Time-To-First-Token (TTFT) latency incurred by the prefill stage has become the foremost bottleneck limiting interactive performance and deployment cost. KV Cache reuse offers a direct path to reduce redundant prefill, yet traditional prefix caching applies only to strict-prefix scenarios; directly reusing KV Cache in non-prefix settings breaks the cross-chunk global attention relationships and causes significant degradation in generation quality. When reusable KV Cache is offloaded to GPU-external cache pools, I/O overheads across heterogeneous hardware tiers further emerge as a new TTFT bottleneck. Efficient non-prefix KV Cache reuse therefore requires both semantic-consistency recovery and compute-I/O co-optimization. This paper presents CacheTune, a frequency-guided and hardware-aware KV Cache reuse system for long-context LLM serving. CacheTune first identifies, offline, the KV pairs most critical to cross-attention recovery through frequency-domain analysis, and then selectively recomputes only these semantic-critical tokens online while reusing the remaining KVs. To turn this semantic selection into end-to-end latency reduction, CacheTune further combines sparse KV transfer, multi-stream asynchronous overlap, deferred positional-encoding recovery, and hardware-aware adaptive recomputation-ratio tuning to balance computation and data movement across heterogeneous cache pools. Evaluations on mainstream LLMs and long-context tasks show that CacheTune achieves 3.72x-4.86x TTFT speedup and 3.93x-6.21x higher throughput while maintaining generation quality close to full recompute. Even when caches are offloaded to I/O-bound SSD/HDD storage, CacheTune sustains 2.34x-2.36x TTFT speedup through adaptive recomputation.

cs.AR↗

arXiv2026

Fr\"ohlich-type Polarons in Isotopically Enriched Hexagonal Boron Nitride

Exciton-phonon interactions play a central role in defining the optical response of hexagonal boron nitride (hBN), yet their quantitative determination has remained incomplete. Here, we reveal the Fr\"ohlich-type exciton-phonon coupling in boron-10-enriched hBN using low-temperature cathodoluminescence. We resolve the indirect exciton 5.95$\pm$0.02 eV together with its longitudinal optical (LO) phonon replica detuned by 184$\pm$56 meV, enabling the extraction of a Fr\"ohlich coupling constant $\alpha$=0.159 and a larger exciton binding energy of 161 meV, larger than previously reported values for natural-abundance hBN, which is attributed to isotope enrichment. The inferred polaron radius exceeds the lattice constant, indicating large-polaron behavior. We deduced an exciton scattering time ~of 97 fs, corresponding to a homogeneous linewidth of ~6.76 meV. We further obtain a polaron binding energy of ~48 meV and an effective mass of 1.045 $m_0$. These results provide a direct quantitative characterization of exciton-phonon coupling in isotopically engineered hBN and establish a foundation for tailoring its phonon-polaritonic and quantum-optical properties.

cond-mat.mes-hall↗

arXiv2026

Regret Analysis of Guided Diffusion for Black-Box Optimization over Structured Inputs

Guided-diffusion black-box optimization (BO) has shown strong empirical performance on structured design problems such as molecules and crystals, but its regret behavior remains poorly understood. Existing BO regret analyses typically rely on maximum information gain, non-pretrained surrogate models, or exact acquisition maximization -- assumptions that break down in modern diffusion -- BO pipelines, where pretrained diffusion models serve as powerful priors over valid structures and acquisition maximization is replaced by approximate sampling over astronomically large discrete spaces. We develop a first certificate-based expected simple-regret framework for guided-diffusion BO that avoids maximum-information-gain bounds, RKHS assumptions, and exact acquisition maximization. The central quantity in our analysis is mass lift: the increase in probability mass assigned to near-optimal designs relative to the pretrained generator. This view explains how exponential-looking finite-budget convergence and polynomial acceleration can all arise from the same mechanism. We also give practical diagnostics for estimating search exponents from finite candidate pools and a proposal-corrected resampling construction that provides a fully certified sampler instance.

stat.ML↗

arXiv2026

Real-time Surface-Code Error Correction Using an FPGA-based Neural-Network Decoder

Quantum error correction (QEC) is essential for achieving low error rates required for fault-tolerant quantum computation. In stabilizer-based codes such as the surface code, errors are inferred from repeated syndrome measurements and corrected by a classical decoder. To prevent error accumulation, decoding must be performed with both high throughput and low latency to keep pace with the QEC cycle and enable real-time feedback for universal logical operations. Here we report a hardware-integrated control architecture featuring an FPGA-based neural-network (NN) decoder and experimentally demonstrate real-time surface-code (distance-3) QEC on a superconducting quantum processor. The system achieves a deterministic closed-loop latency of 550 ns, including 124 ns for NN decoding, enabling feedback corrections within a 1.25 us QEC cycle. We show that real-time decoding and feedback correction achieve logical performance comparable to offline decoding while maintaining robustness against varying error conditions. We further demonstrate mid-circuit feedback correction in non-Clifford logical circuits, where Pauli-frame updating alone becomes insufficient. Our results establish a low-latency hardware architecture for embedded QEC control and provide a pathway towards scalable fault-tolerant quantum computing systems.

quant-ph↗

arXiv2026

Data-driven Urban Surface Classification Elucidates Global City Heterogeneity

Accurate urban surface characterization is essential for environmental modeling, risk assessment, and climate adaptation. However, existing classifications of urban surfaces lack the global consistency and physical detail to fully represent present-day urban heterogeneity. To address this need, we developed a globally unified, Data-driven Urban Environmental Zone (DUEZ) framework. By applying unsupervised clustering to high-resolution (500-m) datasets of building morphology, vegetation, and surface imperviousness, we classified global urban surfaces into 27 DUEZs, representing the exposure setting for approximately 85% of the global population. Compared to the Local Climate Zone scheme, DUEZ framework provides a more detailed representation of urban form, capturing the fine-scale mixing of built and vegetated surfaces in modern cities. Further aggregation of DUEZ patterns revealed nine predominant urban textures globally with regional differences and socioeconomic relevance. The DUEZ framework enhances physical representation of complex urban surfaces in numerical models and establishes a consistent, data-driven basis for global urban environmental studies.

physics.ao-ph↗

arXiv2026

Blow-up phemomenon for the 3-component Degasperis-Procesi equation

In this paper, we consider the Cauchy problem of the 3-component Degasperis-Procesi equation. Firstly, we discuss a local well-posedness result and a blow-up criterion in the low besov space. Secondly, we study the blow-up phenomenon by using the method which does not require any conservation law. Finally, we investigate some persistence properties.

math.AP↗