arXiv subjects

Hui Dong

Publications and source records attributed to Hui Dong.

At least 19 recordsLinked to original sources

arXiv2026

Nonorthogonal-state erasure as the resource behind apparent second-law violations

Perfect deterministic distinguishing of nonorthogonal quantum states is forbidden by the linear and unitary structure of quantum mechanics. It has often been assumed that, if such distinguishing were available, it would be the resource enabling work extraction from a single heat bath. We show that this expectation identifies the wrong thermodynamic operation and prove such hypothetical operation increases, rather than decreases, the joint entropy of system and detector. The entropy-decreasing resource is instead the inverse operation, which we call nonorthogonal-state erasure. Reanalyzing a Peres-type Szilard engine, we show that the apparent extracted work $W_{\mathrm{ext}}=0.2766k_{\mathrm{B}}T$ for an equal mixture of an atomic ensemble with spin state $\left|\uparrow\right\rangle $ and $\left|\rightarrow\right\rangle $. Thus the apparent second-law violation is supplied not by nonorthogonal-state distinguishing, but by a nonorthogonal quantum state erasure.

quant-ph↗

arXiv2026

HiFA4: Training-Free 4-bit FlashAttention on Ascend HIF4 NPUs for LLM Inference

We present HiFA4, a post-training operator-level design that executes both QK^T and PV in FlashAttention as 4-bit HIF4 Cube GEMMs for LLM inference on Ascend NPUs, while maintaining the online softmax state in FP16. To our knowledge, HiFA4 is the first Ascend-HIF4-targeted design of this kind evaluated on standard NLP benchmarks. HiFA4 combines two mechanisms. Smooth-QK applies a calibration-static per-channel equivalent rescaling to Q and K after RoPE, transferring quantization difficulty from K to Q without per-tile online reduction at inference. P-Reordering accumulates the softmax normalizer from the same quantized attention weights P_hat used in the PV GEMM, rather than from a higher-precision reconstruction. We show that this inconsistent formulation introduces a coherent output-scaling error, and validate the effect on a Qwen3-8B Layer-0 MMLU trace, where all 3.6M measured attention tiles exhibit net probability-mass loss with median epsilon_bar = -0.064. P-Reordering also allows the normalizer to be fused into the PV Cube GEMM. Across five LLMs, HiFA4 reduces quantization-induced decision drift. On Qwen3-8B, it recovers 37.5% of the accuracy gap introduced by direct HIF4 quantization, narrows the sample-weighted accuracy loss from 1.12 pp to 0.70 pp, reduces BF16-inconsistent MMLU predictions from 16.3% to 8.2%, and cuts MMLU accuracy regressions by 57% (1071 to 465). On Gemma2-9B, mild smoothing keeps HiFA4 within 0.7 pp of BF16 while reducing MMLU regressions by 27%. On LLaMA3.1-8B, Mistral-7B, and Phi-4B, where Smooth-QK is disabled, P-Reordering with the adopted Q-Mean auxiliary still reduces full-set MMLU regressions by 41-52%. A preliminary instruction-scheduling analysis projects a 35.4% critical-path latency reduction relative to BF16 by fusing the softmax normalizer into the PV Cube GEMM; on-hardware validation is left to future work.

cs.LG↗

arXiv2026

Training-free sparse attention based on cumulative energy filtering

Sparse attention accelerates Diffusion Transformers (DiTs) for video generation by computing only the important tokens while skipping the rest. The token selection strategy is key to balancing sparsity and accuracy. We formulate the token filtering process as a dual-goal optimization problem: maximizing sparsity and minimizing accuracy degradation. Existing algorithms cannot fulfill both objectives simultaneously. For example, Top-p only considers the accuracy constraint, while Top-k maintains a fixed computational budget but loosens the accuracy constraint. This paper demonstrates that maintaining a fixed recall rate is sufficient for ensuring accuracy, whereas a fixed threshold is suboptimal for reducing computational cost. Therefore, we propose a dynamic thresholding scheme to improve sparsity while maintaining the same level of accuracy. Furthermore, our algorithm is deeply integrated with Flash Attention (FA), eliminating the need for any additional masking computation overhead. Experimental results on Wan 2.2 validate that, compared to the BLASST algorithm which is also integrated with FA, our dynamic thresholding strategy enhances sparsity from 61.42\% to 82\% with a VBench metric drop of less than 5\%. This results in an approximate 15\% in attention computation and a $1.61\times$ increase in computational efficiency, which is 1.18x higher than that of BLASST.

cs.CV↗

arXiv2026

Beyond-Third-Order Quantum Coherence in Two-Dimensional Spectroscopy via Order-Selective Isolation

A central challenge in nonlinear spectroscopy is the order-selective readout of weak higher-order responses that spectrally overlap with dominant lower-order signals. This bottleneck is particularly severe in two-dimensional (2D) spectroscopy, where extending conventional phase-cycling schemes to higher orders rapidly increases measurement and analysis complexity. Here we introduce a computation-assisted strategy that combines rotating-frame acquisition with a frame-shift tracking algorithm to separate signals by their frame-dependent spectral shifts. In a rubidium vapor experiment, we use this approach to isolate a 7th-order nonlinear contribution from coexisting 3rd-order components, enabling direct access to higher-order quantum-coherence dynamics without sacrificing operation at comparatively high pulse intensities. The method is broadly compatible with multidimensional spectroscopy platforms and provides a practical route to probing many-body and collective ultrafast dynamics beyond third order.

quant-ph↗

arXiv2026

Time-optimal Qubit Reset via Environmental Spectral Structure

Fast qubit reset is essential for qubit reuse in the noisy intermediate-scale quantum computing era, yet it conflicts with the weak decoherence required for high-fidelity computation. We solve the time-optimal reset problem for a frequency-tunable qubit coupled to a structural environment under realistic spectral and control constraints. The optimal strategy consists of a switch--restore--switch sequence, where the qubit is moved from a low-decoherence computational configuration to a high-decoherence restoring configuration and then returned for reuse. For superconducting qubits in four representative environments, this strategy reduces the reset time from typically $\gtrsim\SI{100}{\nano\second}$ to $\SI{20}{\nano\second}$, about $40\%$ of a typical two-qubit gate time, while achieving a reset precision of $10^{-5}$. Our results identify environmental spectral structure as a practical resource for rapid, high-fidelity qubit reset and provide a design principle for qubit reuse on qubit-limited processors.

quant-ph↗

arXiv2026

Frequency upconversion of infrared signals via molecular optomechanical cavities

Molecular optomechanical cavities have recently emerged as a promising platform for frequency upconversion, enabling the quantum coherent conversion of infrared signal into the visible range. In a recent work [F. Zou et al., Phys. Rev. Lett. 132, 153602 (2024)], we proposed an amplification mechanism that can enhance the intensity of the upconverted infrared signals by a factor of 1000 or more within such a cavity under the ideal case without any noise. In this work, we employ the power spectrum method to investigate the noise added to the upconverted signal in a molecular optomechanical cavity along with the conversion efficiency from infrared signal into visible range. In the red-detuned regime, the anti-Stokes sideband achieves superior conversion efficiency relative to the Stokes sideband. Conversely, the Stokes sideband dominates under the blue-detuned condition, which amplifies the infrared signal. We further demonstrate the dependence of the added noise on the coupling strength and decay rates of the system. In particular, we find that when the infrared signal is amplified, the added noise approaches the quantum limit of one quantum.

quant-ph↗

arXiv2026

OSC: Hardware Efficient W4A4 Quantization via Outlier Separation in Channel Dimension

While 4-bit quantization is essential for high-throughput deployment of Large Language Models, activation outliers often lead to significant accuracy degradation due to the restricted dynamic range of low-bit formats. In this paper, we systematically investigate the spatial distribution of outliers and demonstrate a token-persistent structural clustering effect, where high-magnitude outliers consistently occupy fixed channels across tokens. Building on this insight, we propose OSC, a hardware-efficient framework for outlier suppression. During inference, OSC executes a dual-path computation consisting of a low-precision 4-bit General Matrix Multiplication (GEMM) path and a high-precision 16-bit branch GEMM path. Specifically, OSC uses an offline group-wise strategy to identify the channels where outliers are located and then performs structured sub-tensor extraction to coalesce these scattered activation channels into a compact dense tensor online. This mechanism implements outlier protection through regularized and high-throughput GEMM operations, achieving a seamless fit with modern 4-bit micro-scaling hardware. Furthermore, for the inputs of W2 where outlier clustering is less pronounced, we integrate a fallback strategy to FP8. Evaluation on Qwen3-8B and Qwen3-30B restricts the average accuracy drop to 2.19 and 1.12 points, respectively. Notably, OSC is highly hardware-friendly, achieving a peak speedup of 1.78x over the W8A8 GEMM baseline on a modern AI accelerator.

cs.LG↗

arXiv2026

VFA: Relieving Vector Operations in Flash Attention with Global Maximum Pre-computation

FlashAttention-style online softmax enables exact attention computation with linear memory by streaming score tiles through on-chip memory and maintaining a running maximum and normalizer. However, as attention kernels approach peak tensor-core/cube-core throughput on modern accelerators, non-matmul components of online softmax -- especially per-tile rowmax and rowsum reductions and rescale chains -- can become vector or SIMD limited and dominate latency. This paper revisits FlashAttention and proposes Vector Relieved Flash Attention (VFA), a hardware-friendly method that reduces rowmax-driven updates of the running maximum while retaining the online-softmax structure. VFA initializes the running maximum via a cheap approximation from key-block representations, reorders key-block traversal to prioritize high-impact sink and local blocks, and freezes the maximum for remaining blocks to avoid repeated reductions and rescaling. We further integrate VFA with block-sparse skipping methods such as BLASST to form Vector Relieved Sparse Attention (VSA), which reduces both block count and per-block overhead. Notably, VFA and VSA completely avoid the conditional rescale operation in the update stage used in FA4.0. Extensive evaluations on benchmarks including MMLU and MATH500, together with attention statistics, verify our design: (i) sink and local reordering stabilizes the running maximum early; (ii) simple Q and K block summaries fail due to intra-block heterogeneity; (iii) m-initialization is required when maxima appear in middle blocks. Overall, VFA and VSA efficiently alleviate online-softmax reduction bottlenecks without performance loss. Compared to the C16V32 baseline, C8V32, C4V32 and C4V16 achieve nearly two times speedup on modern hardware while hitting the vector bottleneck. With upcoming architecture improvements, C4V16 will deliver six times speedup by enhancing exponent capacity.

cs.LG↗

arXiv2025

Quenching of polarized jets

Jets produced in association with a $Z^{0}$ or $W^{\pm}$ boson in hadronic collisions are automatically polarized due to the parity violation of weak interaction, making these processes ideal for understanding the spin transfer from polarized partons to polarized hadrons. Furthermore, leveraging this feature, we can also employ the weak-boson-tagged process to study the quenching phenomenon of polarized jets, an aspect that has rarely been discussed in the literature. In this work, we compute the polarization of $\Lambda$ hyperons in $pp$ collisions and investigate the nuclear modification due to the jet-medium interaction in $AA$ collisions. Our results highlight this process as a valuable probe of polarized parton hadronization and of spin-dependent medium effects in the QGP.

hep-ph↗

arXiv2025

Finite-Time Thermodynamics Perspective into Nuclear Power Plant Heat Cycle

Nuclear power plants are prominent examples of heat-to-work conversion systems, and optimizing their thermodynamic performance offers significant potential for enhancing energy efficiency. With a development history of less than a century, optimization trends in nuclear power plants indicate that classical thermodynamics alone may be insufficient, particularly when maximizing output power rather than efficiency becomes the primary focus. This paper re-examines nuclear power plant thermodynamic cycles through the lens of finite-time thermodynamics, an approach specifically developed to address the practical requirement of enhancing power output. Beginning with the simpler Brayton cycle without phase transitions, we obtain the famous Curzon-Ahlborn formula for efficiency at maximum power. Subsequently we analyze the more complex Rankine cycle, which incorporates phase transitions. By explicitly considering the working fluid undergoing phase transitions within the cycle, we uncover the inherent trade-off between output power and efficiency. Additionally, we demonstrate that both the maximum attainable power and efficiency increase as latent heat rises. These findings shall provide insights and methodologies for future thermodynamic optimization of nuclear power plants and other Rankine-type cycle systems.

cond-mat.stat-mech↗

arXiv2025

Beyond Constant-Temperature Reservoirs: A Stirling Cycle with Constant Heat-Generation Rate

Conventional heat-engine models typically assume two heat reservoirs at fixed temperatures. In contrast, radioisotope power systems introduce a fundamentally different paradigm in which the hot sources supply heat at a constant generation rate rather than maintaining a constant temperature. We develop a theoretical framework for finite-time heat engines operating between constant heat-generation-rate hot sources and constant-temperature cold reservoirs. A universal proportion between average output power and efficiency is established, independent of the specific cycle configuration or working substance. As a representative case, we analyze a finite-time Stirling cycle employing a tailored control protocol that maintains the working substance at constant temperatures during the quasi-isothermal processes. An intrinsic oscillatory behavior emerges in the temperature dynamics of the hot source, reflecting the interplay between heat accumulation and release. We further quantify the long-term decline in engine performance resulting from radioactive decay and demonstrate its impact over the system's operational lifespan. This work establishes a new theoretical prototype for heat engines and shall provide guidings for the analysis and design of radioisotope power systems.

cond-mat.stat-mech↗

arXiv2025

Note on the noise reduction in spectroscopic detection with compressed sensing

Spectroscopy sampling along delay time is typically performed with uniform delay spacing, which has to be low enough to satisfy the Nyquist-Shannon sampling theorem. The sampling theorem puts the lower bound for the sampling rate to ensure accurate resolution of the spectral features. However, this bound can be relaxed by leveraging prior knowledge of the signals, such as sparsity. Compressed sensing, a under-sampling technique successfully applied to spatial measurements (e.g., single-pixel imaging), has yet to be fully explored for the spectral measurements especially for the temporal sampling. In this work, we investigate the capability of compressed sensing for improving the temporal spectroscopic measurements to mitigate both measurement noise and intrinsic noise. By applying compressed sensing to single-shot pump-probe data, we demonstrate its effectiveness in noise reduction. Additionally, we propose a feasible experimental scheme using a digital mirror device to implement compressed sensing for temporal sampling. This approach provides a promising method for spectroscopy to reduce the signal noise and the number of sample measurements.

physics.chem-ph↗

arXiv2025

Measurement Uncertainty in Infrared Spectroscopy with Entangled Photon Pairs

Spectroscopy with entanglement has shown great potential to break limitations of traditional spectroscopic measurements, yet the role of entanglement in spectroscopic multi-parameter joint measurement, particularly in the infrared optical range, remains elusive. Here, we find an uncertain relation that constrains the precision of infrared spectroscopic multi-parameter measurements using entangled photon pairs. Under such a relation, we demonstrate a trade-off between the measurement precisions of the refractive index and absorption coefficient of the medium in the infrared range, and also illustrate how to balance their respective estimation errors. Our work shall provide guidance towards the future experimental designs and applications in entanglement-assisted spectroscopy.

quant-ph↗

arXiv2024

Frequency-resolved Transient Absorption Spectroscopy for High Pressure System

Dynamics of materials under high-pressure conditions has been an important focus of materials science, especially in the timescale of pico- and femto-second of electronic and vibrational motion, which is typically probed by ultrafast laser pulses. To probe such dynamics, it requires an integration of high-pressure devices with the ultrafast laser system. In this work, we construct a frequency-resolved high-pressure transient absorption spectroscopy system based on a diamond anvil cell (DAC) with transmissive detection. In this setup, we use the narrowband laser as the pump beam and the supercontinuum white light as the probe beam. To effectively eliminate the scattering noise from the pump light, we design a double-chopper operating mode, which allows us to obtain signals in the complete frequency domain including the overlap region with the pump pulse. And we test system with Rhodamine B solution with the probe wavelength range of 450-750 nm and the 550nm pump, and observe that the intensity of the signal peak corresponding to the monomer at 560 nm continuously decreased relative to the signal peak corresponding to the dimer at 530 nm. This indicates that the portion of Rhodamine B molecules in the dimer form increases under increasing pressure. Additionally, we find two dynamic components of the signal peaks for both monomer and dimer, and the short-lifetime component increases as the pressure is increased, and the long-lifetime component decreases.

physics.optics↗

arXiv2024

Demystifying and Extracting Fault-indicating Information from Logs for Failure Diagnosis

Logs are imperative in the maintenance of online service systems, which often encompass important information for effective failure mitigation. While existing anomaly detection methodologies facilitate the identification of anomalous logs within extensive runtime data, manual investigation of log messages by engineers remains essential to comprehend faults, which is labor-intensive and error-prone. Upon examining the log-based troubleshooting practices at CloudA, we find that engineers typically prioritize two categories of log information for diagnosis. These include fault-indicating descriptions, which record abnormal system events, and fault-indicating parameters, which specify the associated entities. Motivated by this finding, we propose an approach to automatically extract such faultindicating information from logs for fault diagnosis, named LoFI. LoFI comprises two key stages. In the first stage, LoFI performs coarse-grained filtering to collect logs related to the faults based on semantic similarity. In the second stage, LoFI leverages a pre-trained language model with a novel prompt-based tuning method to extract fine-grained information of interest from the collected logs. We evaluate LoFI on logs collected from Apache Spark and an industrial dataset from CloudA. The experimental results demonstrate that LoFI outperforms all baseline methods by a significant margin, achieving an absolute improvement of 25.8~37.9 in F1 over the best baseline method, ChatGPT. This highlights the effectiveness of LoFI in recognizing fault-indicating information. Furthermore, the successful deployment of LoFI at CloudA and user studies validate the utility of our method. The code and data are available at https://github.com/Jun-jie-Huang/LoFI.

cs.SE↗

arXiv2024

Quantum-enhanced weak absorption estimation with correlated photons

Conventional absorption spectroscopy relies on coherent laser sources, and in turn suffers from the inherent limitation of shot noise, especially in estimating weak absorption. Here we propose a measurement strategy with correlated photons to determine the weak absorption by distinguishing the output with and without photons, dubbed as the on-off measurement. We demonstrate that absorption spectroscopy that incorporates quantum correlations is capable of estimating weak absorption down to a single-photon level, even in noisy environments, achieving a precision comparable to that obtained through 1000 photons in conventional absorption spectroscopy. Our strategy provides a new method to probe fragile systems with weak absorption, avoiding the occurrence of light-induced damage.

quant-ph↗

arXiv2024

Dihadron helicity correlation in photon-nucleus collisions

The helicity correlation of two back-to-back hadrons is a powerful tool that makes it possible to probe the longitudinal spin transfer, $G_{1L}$, in unpolarized hadronic collisions. In this work, we investigate the helicity correlation of back-to-back dihadrons produced in photon-nucleus collisions with both space-like and quasireal photons and explore its potential in understanding the flavor dependence of spin-dependent fragmentation functions. We present helicity amplitudes of partonic scatterings with both virtual and real photons and make numerical predictions for the dihadron helicity correlations at the future Electron Ion Collider experiment and the current RHIC/LHC ultra-peripheral collision experiment. Future experimental measurements can also illuminate the fragmentation function of circularly polarized gluons.

hep-ph↗

arXiv2024

Power-Efficiency Constraint for Chemical Motors

Chemical gradients provide the primordial energy for biological functions by driving the mechanical movement of microscopic engines. Their thermodynamic properties remain elusive, especially concerning the dynamic change in energy demand in biological systems. In this article, we derive a constraint relation between the output power and the conversion efficiency for a chemically fueled steady-state rotary motor analogous to the $\mathrm{F}_o$ motor of ATPase. We find that the efficiency at maximum power is half of the maximum quasi static efficiency. These findings shall aid in the understanding of natural chemical engines and inspire the manual design and control of chemically fueled microscale engines.

cond-mat.stat-mech↗