arXiv subjects

Cheng Gu

Publications and source records attributed to Cheng Gu.

6 recordsLinked to original sources

arXiv2026

Trajectory-Initialized Neural Double Q-Routing for Large-Scale Overhead Hoist Transport Systems

Large-scale industrial robot fleets share constrained physical infrastructure, making vehicle travel times dependent on safety separation, intersection access, downstream blocking, and station contention. We study this problem in overhead hoist transport (OHT) systems, a representative ceiling-mounted material-handling system used in semiconductor fabs. Static shortest-path routing cannot account for these time-varying traffic costs, whereas tabular Q-routing adapts online but learns each destination--node--action value independently, limiting information sharing across sparsely visited routing contexts and making startup behavior sensitive to inaccurate value estimates. We propose Neural Double Q-routing, which replaces destination-indexed tables with a shared state--action value network. The network is warm-started through return-to-go regression on mixed simulator-generated routing trajectories and then refined online using Double-Q updates, local congestion correction, and event-stratified structured replay. Across nine matched fleet-size--arrival-rate settings with 100, 150, and 200 OHTs, the proposed framework reduces mean completion time relative to tabular Double Q-routing by $0.8\%$--$8.8\%$. It achieves the lowest mean completion time among all compared methods in the six 150- and 200-OHT settings, whereas Dijkstra remains best in the three 100-OHT settings. Completed-task counts remain within $1\%$ of tabular Double Q-routing in eight of nine settings, and 95th-percentile completion time decreases in eight settings. In two matched startup scenarios, offline initialization increases the number of completed tasks by up to $23\%$ and reduces tail completion time by up to $15\%$.

cs.LG↗

arXiv2026

Practical FP4 Training for Large-Scale MoE Models on Hopper GPUs

Training large-scale Mixture-of-Experts (MoE) models is bottlenecked by activation memory and expert-parallel communication, yet FP4 training remains impractical on Hopper-class GPUs without native MXFP4 or NVFP4 support. In this work, we present a training recipe that enables MXFP4 efficiency for MoE models on Hopper architectures without native 4-bit computation support. A central challenge is to integrate FP4 into an existing BF16/FP8 hybrid training pipeline without incurring costly precision round-trips (e.g., FP4 $\leftrightarrow$ BF16 $\leftrightarrow$ FP8). We address this challenge by introducing direct FP8-to-FP4 quantization and de-quantization, together with scaling-aware FP4 row-wise to column-wise conversion, enabling FP4 activations and expert-parallel communication with minimal overhead. Core MoE computations are executed in FP8, while activations and expert-parallel communication are compressed using MXFP4, achieving substantial memory and bandwidth savings without degrading convergence. At the 671B parameter scale, our method achieves end-to-end training performance comparable to strong FP8 baselines, while reducing peak activation memory by 14.8\% (11.8 GB) and improving training throughput by 12.5\%, from 1157 to 1302 tokens per GPU per second. These results show that FP4 efficiency can be practically realized for large-scale MoE training through careful software-hardware co-design, even without native FP4 Tensor Core support.

cs.LG↗

arXiv2024

I Know What You Sync: Covert and Side Channel Attacks on File Systems via syncfs

Operating Systems enforce logical isolation using abstractions such as processes, containers, and isolation technologies to protect a system from malicious or buggy code. In this paper, we show new types of side channels through the file system that break this logical isolation. The file system plays a critical role in the operating system, managing all I/O activities between the application layer and the physical storage device. We observe that the file system implementation is shared, leading to timing leakage when using common I/O system calls. Specifically, we found that modern operating systems take advantage of any flush operation (which saves cached blocks in memory to the SSD or disk) to flush all of the I/O buffers, even those used by other isolation domains. Thus, by measuring the delay of syncfs, the attacker can infer the I/O behavior of victim programs. We then demonstrate a syncfs covert channel attack on multiple file systems, including both Linux native file systems and the Windows file system, achieving a maximum bandwidth of 5 Kbps with an error rate of 0.15% on Linux and 7.6 Kbps with an error rate of 1.9% on Windows. In addition, we construct three side-channel attacks targeting both Linux and Android devices. On Linux devices, we implement a website fingerprinting attack and a video fingerprinting attack by tracking the write patterns of temporary buffering files. On Android devices, we design an application fingerprinting attack that leaks application write patterns during boot-up. The attacks achieve over 90% F1 score, precision, and recall. Finally, we demonstrate that these attacks can be exploited across containers implementing a container detection technique and a cross-container covert channel attack.

cs.CR↗

arXiv2022

Spin dynamics and continuum spectra of the honeycomb J1-J2 antiferromagnetic Heisenberg model

We employ the spin cluster perturbation theory to investigate the dynamical properties of the antiferromagnetic $J_{1}$-$J_{2}$ Heisenberg model on the honeycomb lattice. We obtain the excitation spectra for all possible phases in the phase diagram, including the N\'{e}el phase, plaquette valence-bond-solid phase, dimer valence-bond-solid phase and stripe antiferromagnetic phase. In the N\'{e}el phase, besides the obvious renormalization of the magnon dispersion, we find that the spectrum exhibits a dome-shaped broad continuum around the second Brillouin zone (BZ) and the additional strong continuum close to the corner of the BZ. In the valence-bond-solid phases, the spectra are dominated by a strong broad continuum all the way down to below $J_1$ coexisting with the lowest-energy triplon modes characterizing the plaquette and dimer phases. We ascribe this strong broad continuum and the additional continuum close to the BZ corner in the N\'{e}el phase to the contributions of fractionalized spinon excitations. In the stripe phase, a clear difference from the linear spin wave approximation is that the spectrum is gapped at the $M$ point while that obtained by the latter is gapless due to the strong quantum fluctuations. We point out that the features observed in the N\'{e}el phase are consistent with the recent neutron scattering experiments on YbCl$_{3}$ and YbBr$_{3}$.

cond-mat.str-el↗

arXiv2021

The Spatio-Temporal Poisson Point Process: A Simple Model for the Alignment of Event Camera Data

Event cameras, inspired by biological vision systems, provide a natural and data efficient representation of visual information. Visual information is acquired in the form of events that are triggered by local brightness changes. Each pixel location of the camera's sensor records events asynchronously and independently with very high temporal resolution. However, because most brightness changes are triggered by relative motion of the camera and the scene, the events recorded at a single sensor location seldom correspond to the same world point. To extract meaningful information from event cameras, it is helpful to register events that were triggered by the same underlying world point. In this work we propose a new model of event data that captures its natural spatio-temporal structure. We start by developing a model for aligned event data. That is, we develop a model for the data as though it has been perfectly registered already. In particular, we model the aligned data as a spatio-temporal Poisson point process. Based on this model, we develop a maximum likelihood approach to registering events that are not yet aligned. That is, we find transformations of the observed events that make them as likely as possible under our model. In particular we extract the camera rotation that leads to the best event alignment. We show new state of the art accuracy for rotational velocity estimation on the DAVIS 240C dataset. In addition, our method is also faster and has lower computational complexity than several competing methods.

cs.CV↗

arXiv2020

Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach

Few-shot learning is a challenging problem that has attracted more and more attention recently since abundant training samples are difficult to obtain in practical applications. Meta-learning has been proposed to address this issue, which focuses on quickly adapting a predictor as a base-learner to new tasks, given limited labeled samples. However, a critical challenge for meta-learning is the representation deficiency since it is hard to discover common information from a small number of training samples or even one, as is the representation of key features from such little information. As a result, a meta-learner cannot be trained well in a high-dimensional parameter space to generalize to new tasks. Existing methods mostly resort to extracting less expressive features so as to avoid the representation deficiency. Aiming at learning better representations, we propose a meta-learning approach with complemented representations network (MCRNet) for few-shot image classification. In particular, we embed a latent space, where latent codes are reconstructed with extra representation information to complement the representation deficiency. Furthermore, the latent space is established with variational inference, collaborating well with different base-learners, and can be extended to other models. Finally, our end-to-end framework achieves the state-of-the-art performance in image classification on three standard few-shot learning datasets.

cs.CV↗