arXiv subjects

Xun Su

Publications and source records attributed to Xun Su.

11 recordsLinked to original sources

arXiv2026

GVCCTurbo: Rate-Compute Quality Scheduling for Codebook Driven Generative Compression

Codebook-driven generative compression uses a pretrained image or video generator as a zero-shot visual prior and transmits compact codebook indices to guide reconstruction at ultra-low bitrate. Current codecs tie each finite-rate correction to a fresh prior evaluation, so shortening the sampler also removes correction slots that carry target-dependent information. We propose GVCCTurbo, a BPP-driven scheduler that separates expensive prior refreshes from codebook corrections: after calibrating an atom-count operating point and skip-gap ratio once per protocol, it maps a target codebook-payload bitrate to a trajectory length and refresh period, making BPP a schedule input instead of a fixed consequence of sampler length. The same endpoint-prediction and finite-rate steering interface covers GVCC-style rectified-flow video and DDCM-style diffusion image compression, preserving zero-training deployment and compatibility with future distilled priors. Native 1080p curves position the complete zero-shot codec in the ultra-low-bitrate regime. In a controlled 720p Wan-GVCC study, the scheduler cuts prior evaluations from 20 to 9 for a $\sim\!44\%$ measured decoding-time reduction shared across the whole schedule family, at a small shared LPIPS cost on high-motion content; within that family, uniform refresh thinning (pure-skip) is a boundary point, and the BPP-aware interior point trades $2.9\%$ fewer codebook-payload bits for consistently higher PSNR at comparable LPIPS. These results support BPP-to-compute scheduling as a controllable extension of sampler-length tuning, without requiring the allocated point to dominate every boundary point.

cs.CV↗

arXiv2026

GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow

At ultra-low bitrates, high-fidelity reconstruction requires sampling plausible videos from the posterior rather than regressing to oversmoothed conditional means. We propose Generative Video Codebook Codec (GVCC), a zero-shot framework in which a pretrained video generative model serves directly as the decoder, and the transmitted bitstream specifies its generation trajectory. Modern rectified-flow video models are typically sampled with deterministic ODE solvers, which leave no per-step stochastic channel for transmitting compressed information. GVCC addresses this by converting the deterministic flow sampler into an equivalent marginal-preserving stochastic process, so that information can be transmitted by encoding the per-step stochastic innovations. Unlike images, videos introduce longer temporal dependencies and more diverse conditioning modes. We instantiate GVCC in three practical modes: Text-to-Video (T2V) without a reference frame, autoregressive Image-to-Video (I2V) with tail latent correction, and First-Last-Frame-to-Video (FLF2V) with boundary-sharing Group of Pictures (GOP) chaining. On UVG, GVCC achieves the lowest LPIPS among evaluated baselines across three representative bitrate regimes (down to ${\sim}$0.003\,bpp), with 65\% LPIPS reduction over DCVC-RT at matched bitrate.

cs.CV↗

arXiv2026

PTS-SNN: A Prompt-Tuned Temporal Shift Spiking Neural Networks for Efficient Speech Emotion Recognition

Speech Emotion Recognition (SER) is widely deployed in Human-Computer Interaction, yet the high computational cost of conventional models hinders their implementation on resource-constrained edge devices. Spiking Neural Networks (SNNs) offer an energy-efficient alternative due to their event-driven nature; however, their integration with continuous Self-Supervised Learning (SSL) representations is fundamentally challenged by distribution mismatch, where high-dynamic-range embeddings degrade the information coding capacity of threshold-based neurons. To resolve this, we propose Prompt-Tuned Spiking Neural Networks (PTS-SNN), a parameter-efficient neuromorphic adaptation framework that aligns frozen SSL backbones with spiking dynamics. Specifically, we introduce a Temporal Shift Spiking Encoder to capture local temporal dependencies via parameter-free channel shifts, establishing a stable feature basis. To bridge the domain gap, we devise a Context-Aware Membrane Potential Calibration strategy. This mechanism leverages a Spiking Sparse Linear Attention module to aggregate global semantic context into learnable soft prompts, which dynamically regulate the bias voltages of Parametric Leaky Integrate-and-Fire (PLIF) neurons. This regulation effectively centers the heterogeneous input distribution within the responsive firing range, mitigating functional silence or saturation. Extensive experiments on five multilingual datasets (e.g., IEMOCAP, CASIA, EMODB) demonstrate that PTS-SNN achieves 73.34\% accuracy on IEMOCAP, comparable to competitive Artificial Neural Networks (ANNs), while requiring only 1.19M trainable parameters and 0.35 mJ inference energy per sample.

cs.AI↗

arXiv2025

Noise is All You Need: Solving Linear Inverse Problems by Noise Combination Sampling with Diffusion Models

Pretrained diffusion models have demonstrated strong capabilities in zero-shot inverse problem solving by incorporating observation information into the generation process of the diffusion models. However, this presents an inherent dilemma: excessive integration can disrupt the generative process, while insufficient integration fails to emphasize the constraints imposed by the inverse problem. To address this, we propose \emph{Noise Combination Sampling}, a novel method that synthesizes an optimal noise vector from a noise subspace to approximate the measurement score, replacing the noise term in the standard Denoising Diffusion Probabilistic Models process. This enables conditional information to be naturally embedded into the generation process without reliance on step-wise hyperparameter tuning. Our method can be applied to a wide range of inverse problem solvers, including image compression, and, particularly when the number of generation steps $T$ is small, achieves superior performance with negligible computational overhead, significantly improving robustness and stability.

cs.LG↗

arXiv2025

Navigating the Exploration-Exploitation Tradeoff in Inference-Time Scaling of Diffusion Models

Inference-time scaling has achieved remarkable success in language models, yet its adaptation to diffusion models remains underexplored. We observe that the efficacy of recent Sequential Monte Carlo (SMC)-based methods largely stems from globally fitting the The reward-tilted distribution, which inherently preserves diversity during multi-modal search. However, current applications of SMC to diffusion models face a fundamental dilemma: early-stage noise samples offer high potential for improvement but are difficult to evaluate accurately, whereas late-stage samples can be reliably assessed but are largely irreversible. To address this exploration-exploitation trade-off, we approach the problem from the perspective of the search algorithm and propose two strategies: Funnel Schedule and Adaptive Temperature. These simple yet effective methods are tailored to the unique generation dynamics and phase-transition behavior of diffusion models. By progressively reducing the number of maintained particles and down-weighting the influence of early-stage rewards, our methods significantly enhance sample quality without increasing the total number of Noise Function Evaluations. Experimental results on multiple benchmarks and state-of-the-art text-to-image diffusion models demonstrate that our approach outperforms previous baselines.

cs.LG↗

arXiv2023

Anchor Space Optimal Transport as a Fast Solution to Multiple Optimal Transport Problems

In machine learning, Optimal Transport (OT) theory is extensively utilized to compare probability distributions across various applications, such as graph data represented by node distributions and image data represented by pixel distributions. In practical scenarios, it is often necessary to solve multiple OT problems. Traditionally, these problems are treated independently, with each OT problem being solved sequentially. However, the computational complexity required to solve a single OT problem is already substantial, making the resolution of multiple OT problems even more challenging. Although many applications of fast solutions to OT are based on the premise of a single OT problem with arbitrary distributions, few efforts handle such multiple OT problems with multiple distributions. Therefore, we propose the anchor space optimal transport (ASOT) problem: an approximate OT problem designed for multiple OT problems. This proposal stems from our finding that in many tasks the mass transport tends to be concentrated in a reduced space from the original feature space. By restricting the mass transport to a learned anchor point space, ASOT avoids pairwise instantiations of cost matrices for multiple OT problems and simplifies the problems by canceling insignificant transports. This simplification greatly reduces its computational costs. We then prove the upper bounds of its $1$-Wasserstein distance error between the proposed ASOT and the original OT problem under different conditions. Building upon this accomplishment, we propose three methods to learn anchor spaces for reducing the approximation error. Furthermore, our proposed methods present great advantages for handling distributions of different sizes with GPU parallelization.

cs.LG↗

arXiv2023

Safe Screening for Unbalanced Optimal Transport

This paper introduces a framework that utilizes the Safe Screening technique to accelerate the optimization process of the Unbalanced Optimal Transport (UOT) problem by proactively identifying and eliminating zero elements in the sparse solutions. We demonstrate the feasibility of applying Safe Screening to the UOT problem with $\ell_2$-penalty and KL-penalty by conducting an analysis of the solution's bounds and considering the local strong convexity of the dual problem. Considering the specific structural characteristics of the UOT in comparison to general Lasso problems on the index matrix, we specifically propose a novel approximate projection, an elliptical safe region construction, and a two-hyperplane relaxation method. These enhancements significantly improve the screening efficiency for the UOT's without altering the algorithm's complexity.

math.OC↗

arXiv2022

Wasserstein Graph Distance Based on $L_1$-Approximated Tree Edit Distance between Weisfeiler-Lehman Subtrees

The Weisfeiler-Lehman (WL) test is a widely used algorithm in graph machine learning, including graph kernels, graph metrics, and graph neural networks. However, it focuses only on the consistency of the graph, which means that it is unable to detect slight structural differences. Consequently, this limits its ability to capture structural information, which also limits the performance of existing models that rely on the WL test. This limitation is particularly severe for traditional metrics defined by the WL test, which cannot precisely capture slight structural differences. In this paper, we propose a novel graph metric called the Wasserstein WL Subtree (WWLS) distance to address this problem. Our approach leverages the WL subtree as structural information for node neighborhoods and defines node metrics using the $L_1$-approximated tree edit distance ($L_1$-TED) between WL subtrees of nodes. Subsequently, we combine the Wasserstein distance and the $L_1$-TED to define the WWLS distance, which can capture slight structural differences that may be difficult to detect using conventional metrics. We demonstrate that the proposed WWLS distance outperforms baselines in both metric validation and graph classification experiments.

cs.LG↗

arXiv2015

Heterodimer nanostructures induced energy focusing on metal film

As an interesting surface plasmon phenomenon discovered several years ago, electromagnetic field redistribution in nanoparticle dimer on film system provides a novel thought to enhance the light power on a plain film which could been widely used in surface enhanced Raman scattering (SERS), solar cells, photo-catalysis, etc. Homodimers on film are mainly investigated in past years, while the properties of heterodimers on film are still unclear. In this work, size difference induced electromagnetic field redistribution in Ag nanoparticle dimer on Au film system is investigated first. The results obtained from finite element method indicate that the smaller nanoparticle has much greater ability to focus light energy on Au film, which even reached more than 5 time compared to the larger one. Further researches indicate that this energy focusing ability has a strong relationship to the wavelength and diameter ration in dimer. Similar focusing phenomenon is found in the system of thick wire-smaller particle on film. Later, the SERS spectra collected in the small nanoparticle-large nanowire system provide an experimental evidence for this theoretic predication. Our results strengthen the understanding of surface plasmon on plane film and have potential application prospects in the surface plasmon related fields.

cond-mat.mes-hall↗

arXiv2006

The rational parts of one-loop QCD amplitudes II: The five-gluon case

The rational parts of 5-gluon one-loop amplitudes are computed by using the newly developed method for computing the rational parts directly from Feynman integrals. We found complete agreement with the previously well-known results of Bern, Dixon and Kosower obtained by using the string theory method. Intermediate results for some combinations of Feynman diagrams are presented in order to show the efficiency of the method and the local cancellation between different contributions.

hep-ph↗

arXiv2004

Six-Quark Amplitudes from Fermionic MHV Vertices

The fermionic extension of the CSW approach to perturbative gauge theory coupled with fermions is used to compute the six-quark QCD amplitudes. We find complete agreement with the results obtained by using the usual Feynman rules.

hep-th↗