Searcharxiv⌕ Search

arXiv subjects

Seungki Hong

Publications and source records attributed to Seungki Hong.

8 recordsLinked to original sources

SpinSCI: Mask-Conditioned Spatial-Temporal Spin Transformer for Video Snapshot Compressive Imaging

Video snapshot compressive imaging (SCI) recovers multiple frames from one spatiotemporally coded measurement. This paper proposes SpinSCI, a mask-conditioned Spatial-Temporal Spin Transformer whose Mask-Conditioned Ising Refinement Block (MC-IRB) combines attention logits and sensing information to form signed spin couplings. Finite mean-field updates gate residual feature refinement. Physics-guided initialization and final data consistency incorporate the measurement model. Compared with HiSViT$_9$, SpinSCI achieves average PSNR gains of 0.51 dB, 0.23 dB, and 0.04 dB on small-scale gray, mid-scale color, and large-scale color benchmarks, respectively, with 16.9% fewer parameters, 21.0-21.6% fewer FLOPs, 17.1-49.9% lower latency, and 62.3-63.3% lower peak memory. Relative to DU-9stg, average PSNR differs by at most 0.13 dB across these benchmarks, with 28.2-28.7% fewer FLOPs, 64.6-71.7% lower inference latency, and 30.1-35.0% lower peak memory. Qualitative comparisons on the real benchmark further show recovery of fine details and textures. Code and reference checkpoints are available at https://github.com/skethz/SpinSCI.

cs.CV↗

Graphene: A Lightweight Transformer with Ising Mean-Field Refinement for Image Super-Resolution

This paper proposes Graphene, a lightweight image super-resolution architecture with two complementary feature refinement mechanisms: Ising-model-inspired local feature refinement using an Ising Refinement Block (IRB) and stage-history-based feature refinement using a History Attention (HistAttn) module. The IRB reuses attention output features and pre-softmax attention logits to construct signed pairwise token couplings within each local window, applies unrolled mean-field updates, and refines features through a gated residual correction. These signed couplings allow alignment and opposition between latent spins to modulate local feature refinement. HistAttn attends over the current stage output and earlier representations at the same token position and adaptively blends the current stage output with a history-weighted feature aggregate without adding spatial pairwise attention. On Urban100 at $\times4$, Graphene and Graphene-light improve over IET and IET-light by 0.24 dB and 0.38 dB, respectively, with 34.3%/13.7% fewer parameters, 44.8%/44.4% fewer FLOPs, 78.4%/71.5% lower latency, and 76.0%/85.5% lower peak memory. Real-world SR comparisons further show that Graphene recovers fine details and preserves textures across diverse degradations. Code and reference checkpoints are available at https://github.com/skethz/Graphene

cs.CV↗

Anechoic: Onsager-Corrected Parallel Annealing for Sub-0.1 ms Dense Max-Cut on an FPGA

Ising machines solve combinatorial optimization problems by annealing a network of spins. On dense problems, the least expensive hardware step updates all spins at once: stochastic cellular automata (SCA) decide every spin in parallel and read couplings only for the spins that flip. Such synchronous updates create an echo: the previous state of each spin returns to it through its neighbors. On K2000, a Max-Cut benchmark on a 2,000-node complete graph, two-thirds of all flips undo the same spin's flip one step earlier. This paper presents Anechoic, an FPGA Ising machine that subtracts this echo from every decision. Dynamical mean-field theory identifies the echo as an Onsager reaction; its one-step strength is the number of spins whose flip probability is strictly between 0 and 1, divided by twice the temperature. The decision logic already flags these spins, so the correction costs one population count per step; a temperature-scaled form needs none. An RTL engine executes a dense 2,000-spin step in 18.1 cycles plus 0.14 per flip, so every saved step and flip saves time. Both forms find better K2000 cuts at every step budget than five published binary-spin algorithms at their papers' settings. Twelve engines at 250 MHz on an AMD Alveo V80 reach a cut of at least 33,000 with 99% probability in 0.05 ms, 5.2 times faster than the fastest published hardware, at 5.4 mJ per solution; with 2-bit couplings, the temperature-scaled form is also faster than uncorrected SCA on 49 of 51 G-set graphs. On an NVIDIA GH200 GPU, the same engine is 2.3 times slower and needs 8.0 times more energy per solution, though its 240 concurrent anneals give 2.3 times the throughput. As a GlobalFoundries 22 nm ASIC at 1.25 GHz, twelve engines would reach the target in about 10 microseconds, 26 times faster than the fastest published hardware. The code is available at https://github.com/skethz/anechoic.

cs.AR↗

Augmented James--Stein estimation for leading eigenvectors and eigenspaces in high dimensions

Building on the James--Stein approach to leading eigenvector estimation (Goldberg and Kercheval, Proc. Natl. Acad. Sci. USA 120, e2207046120, 2023), we develop a data-adaptive augmented James--Stein shrinkage framework for estimating leading eigenvectors and eigenspaces under a generalized spiked population model, in the high-dimensional regime where the dimension $p$ and sample size $n$ grow proportionally. For each spiked eigenvector, we construct an augmented target subspace that combines auxiliary information, either from domain knowledge or prior information, with the remaining sample spiked eigenvectors. This augmentation allows information shared across the sample spiked components to be exploited while retaining a fully data-driven shrinkage rule. We show that the resulting eigenvector estimator strictly improves upon standard PCA whenever the target subspace contains nonvanishing information about the population eigenvector, while asymptotically reverting to PCA when the target is uninformative. The individual estimators further yield a nested sequence of estimators for all leading spiked eigenspaces, with analogous dominance properties. The proposed estimator also strictly improves upon the existing HDLSS-motivated shrinkage estimator in the proportional high-dimensional regime. Simulation studies demonstrate substantial finite-sample gains and robustness to misspecification of the number of spikes.

math.ST↗

Knowledge Integration Decay in Search-Augmented Reasoning of Large Language Models

Modern Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks by employing search-augmented reasoning to incorporate external knowledge into long chains of thought. However, we identify a critical yet underexplored bottleneck in this paradigm, termed Knowledge Integration Decay (KID). Specifically, we observe that as the length of reasoning generated before search grows, models increasingly fail to integrate retrieved evidence into subsequent reasoning steps, limiting performance even when relevant information is available. To address this, we propose Self-Anchored Knowledge Encoding (SAKE), a training-free inference-time strategy designed to stabilize knowledge utilization. By anchoring retrieved knowledge at both the beginning and end of the reasoning process, SAKE prevents it from being overshadowed by prior context, thereby preserving its semantic integrity. Extensive experiments on multi-hop QA and complex reasoning benchmarks demonstrate that SAKE significantly mitigates KID and improves performance, offering a lightweight yet effective solution for knowledge integration in agentic LLMs.

cs.CL↗

Snowball: A Scalable All-to-All Ising Machine with Dual-Mode Markov Chain Monte Carlo Spin Selection and Asynchronous Spin Updates for Fast Combinatorial Optimization

Ising machines have emerged as accelerators for combinatorial optimization. To enable practical deployment, this work aims to reduce time-to-solution by addressing three challenges: (1) hardware topology, (2) spin selection and update algorithms, and (3) scalable coupling-coefficient precision. Restricted topologies require minor embedding; naive parallel updates can oscillate or stall; and limited precision can preclude feasible mappings or degrade solution quality. This work presents Snowball, a digital, scalable, all-to-all coupled Ising machine that integrates dual-mode Markov chain Monte Carlo spin selection with asynchronous spin updates to promote convergence and reduce time-to-solution. The digital architecture supports wide, configurable coupling precision, unlike many analog realizations at high bit widths. A prototype on an AMD Alveo U250 accelerator card achieves an 8$\times$ reduction in time-to-solution relative to a state-of-the-art Ising machine on the same benchmark instance.

cs.LG↗

DSAC: Low-Cost RowHammer Mitigation Using In-DRAM Stochastic and Approximate Counting Algorithm

This paper provides the fundamental mechanisms of two types of row activation-induced bit flips and proposes in-DRAM protection techniques. RowBleed occurs when a victim row experiences charge leakage due to transistor's threshold voltage lowering induced by long activation of a neighboring aggressor row. Therefore, this paper proposes Time-Weighted Counting for RowBleed mitigation, which assigns greater counter weights to rows that are activated for longer durations. On the other hand, RowHammer occurs when a victim row experiences electron injection due to frequent activation of a neighboring aggressor row. Similarly, Extended RowHammer, the phenomenon where victim rows are two rows beyond aggressor rows, is also caused by electron injection due to frequent activation of a neighboring aggressor row. Consequently, accurate detection of aggressor rows is crucial. Therefore, this paper proposes RowHammer mitigation algorithm named DSAC (in-DRAM Stochastic and Approximate Counting algorithm), which utilizes a replacement probability that adjusts based on the count of the old row. This paper introduces a RowHammer protection index called Maximum Disturbance, which measures the maximum accumulated number of row activations within an observation period. The experimental results demonstrate that DSAC can achieve 133x lower Maximum Disturbance than the state-of-the-art counter-based algorithm.

cs.CR↗

Identification of Collapsed Carbon Nanotubes in High-Strength Fibres Spun from Compositionally Polydisperse Aerogels

Carbon Nanotubes (CNTs) of sufficiently large diameter and a few layers self-collapse into flat ribbons at atmospheric pressure, forming bundles of stacked CNTs that maximize packing and thus CNT interaction. Their improved stress transfer by shear makes collapsed CNTs ideal building blocks in macroscopic fibers of CNTs with high-performance longitudinal properties, particularly high tensile properties as reinforcing fibres. This work introduces cross-sectional transmission electron microscopy of FIB-milled samples as a way to univocally identify collapsed CNTs and to determine the full population of different CNTs in macroscopic fibers produced by spinning from floating catalyst chemical vapour deposition. We show that close proximity in bundles is a major driver for collapse and that CNT stoutness (number of layers/diameter), which dominates the collapse onset, is controlled by the growth promotor. Despite differences in decomposition route, different C precursors lead to similar distributions of the ratio layers/diameter. The synthesis conditions in this study give a maximum fraction of collapsed CNTs of 70$\%$ when using selenium as promotor, corresponding to an average of $0.25 layer/nm$.

physics.app-ph↗