Source author record

Linze Li

Linze Li appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record

cond-mat.mtrl-sci Computer Vision cond-mat.str-el

Catalog footprint

What is connected

5works

3topics

4close collaborators

Actions

Connect this record

Open graph Browse works

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

The Velocity Deficit: Initial Energy Injection for Flow Matching

While Flow Matching theoretically guarantees constant-velocity trajectories, we identify a critical breakdown in high-dimensional practice: the Velocity Deficit. We show that the MSE objective systematically underestimates velocity magnitude, causing generated samples to fail to reach the data manifold-a phenomenon we term Integration Lag. To rectify this, we propose Initial Energy Injection, instantiated via two complementary methods: the training-based Magnitude-Aware Flow Matching (MAFM) and the training-free Scale Schedule Corrector (SSC). Both are grounded in our discovery of a crucial asymmetry: velocity contraction causes harmful kinetic stagnation at the trajectory's start, yet acts as a beneficial denoising mechanism at its end. Empirically, SSC yields significant efficiency gains with zero retraining and just one line of code. On ImageNet-1k (256x256), it improves FID by 44.6% (from 13.68 to 7.58) and achieves a 5x speedup, enabling a 50-step generator (FID 7.58) to beat a 250-step baseline (FID 8.65). Furthermore, our methods generalize to Text-to-Image tasks and high-resolution generation, improving FID on MS-COCO by ~22%.

preprint2022arXiv

Efficient One Pass Self-distillation with Zipf's Label Smoothing

Self-distillation exploits non-uniform soft supervision from itself during training and improves performance without any runtime cost. However, the overhead during training is often overlooked, and yet reducing time and memory overhead during training is increasingly important in the giant models' era. This paper proposes an efficient self-distillation method named Zipf's Label Smoothing (Zipf's LS), which uses the on-the-fly prediction of a network to generate soft supervision that conforms to Zipf distribution without using any contrastive samples or auxiliary parameters. Our idea comes from an empirical observation that when the network is duly trained the output values of a network's final softmax layer, after sorting by the magnitude and averaged across samples, should follow a distribution reminiscent to Zipf's Law in the word frequency statistics of natural languages. By enforcing this property on the sample level and throughout the whole training period, we find that the prediction accuracy can be greatly improved. Using ResNet50 on the INAT21 fine-grained classification dataset, our technique achieves +3.61% accuracy gain compared to the vanilla baseline, and 0.88% more gain against the previous label smoothing or self-distillation strategies. The implementation is publicly available at https://github.com/megvii-research/zipfls.

preprint2019arXiv

Spontaneous Hall Effect enhanced by local Ir moments in epitaxial Pr$_2$Ir$_2$O$_7$ thin films

Rare earth pyrochlore Iridates (RE2Ir2O7) consist of two interpenetrating cation sublattices, the RE with highly-frustrated magnetic moments, and the Iridium with extended conduction orbitals significantly mixed by spin-orbit interactions. The coexistence and coupling of these two sublattices create a landscape for discovery and manipulation of quantum phenomena such as the topological Hall effect, massless conduction bands, and quantum criticality. Thin films allow extended control of the material system via symmetry-lowering effects such as strain. While bulk Pr2Ir2O7 shows a spontaneous hysteretic Hall effect below 1.5K, we observe the effect at elevated temperatures up to 15K in epitaxial thin films on (111) YSZ substrates synthesized via solid phase epitaxy. Similar to the bulk, the lack of observable long-range magnetic order in the thin films points to a topological origin. We use synchrotron-based element-specific x-ray diffraction (XRD) and x-ray magnetic circular dichroism (XMCD) to compare powders and thin films to attribute the spontaneous Hall effect in the films to localization of the Ir moments. We link the thin film Ir local moments to lattice distortions absent in the bulk-like powders. We conclude that the elevated-temperature spontaneous Hall effect is caused by the topological effect originating either from the Ir or Pr sublattice, with interaction strength enhanced by the Ir local moments. This spontaneous Hall effect with weak net moment highlights the effect of vanishingly small lattice distortions as a means to discover topological phenomena in metallic frustrated magnetic materials.

preprint2014arXiv

Composition-spread Growth and the Robust Topological Surface State of Kondo insulator SmB6 Thin Films

Topological insulators are a class of materials with insulating bulk but protected conducting surfaces due to the combination of spin-orbit interactions and time-reversal symmetry. The surface states are topologically non-trivial and robust against non-magnetic backscattering, leading to interesting physics and potential quantum computing applications1, 2. Recently there has been a fast growing interest in samarium hexboride (SmB6), a Kondo insulator predicted to be the first example of a correlated topological insulator3, 4. Here we fabricated smooth thin films of nanocrystalline SmB6 films. Their transport behavior indeed shows that SmB6 is a bulk insulator with topological surface states. Upon decreasing the temperature, the resistivity \r{ho} of Sm0.14B0.86 (SmB6) films display significant increase below 50 K due to hybridization gap formation, and it shows a saturation behavior below 10 K. The saturated resistance of our textured films is similar to that of the single crystals, suggesting that this conduction is from the surface and robust against grain boundary scatterings. Point contact spectroscopy (PCS) of the film using a superconducting tip displays both a Kondo Fano resonance and Andreev reflection, suggesting the existence of both an insulating Kondo lattice and metallic surface states.

preprint2010arXiv

Functionalized Graphene for High Performance Two-dimensional Spintronics Devices

Using first-principles calculations, we explore the possibility of functionalized graphene as high performance two-dimensional spintronics device. Graphene functionalized with O on one side and H on the other side in the chair conformation is found to be a ferromagnetic metal with a spin-filter efficiency up to 85% at finite bias. The ground state of graphene semi-functionalized with F in the chair conformation is an antiferromagnetic semiconductor, and we construct a magnetoresistive device from it by introducing a magnetic field to stabilize its ferromagnetic metallic state. The resulting room-temperature magnetoresistance is up to 5400%, which is one order of magnitude larger than the available experimental values.