arXiv subjects

Dowon Kim

Publications and source records attributed to Dowon Kim.

7 recordsLinked to original sources

arXiv2026

SCOPE: Entanglement Frontier Escape for Source-Free Class Unlearning

Source-free class unlearning erases whole classes using only the forget data, judged at the representation level, where features can leak a class the head no longer predicts. Existing feature-space erasers answer with one fixed projection, yet forget and retain classes share a representation, so deleting one disturbs the other where they overlap. We prove this tension is a frontier. Every fixed projection that deletes pays a retain cost of at least the retain-readout energy along the forget-discriminant subspace, and erasing that subspace alone attains the floor. The leading source-free erasers all instantiate the form it binds, so the frontier limits the whole class. Conditioning the erasure on the input escapes it. Spectral Conditional Projective Erasure (SCOPE) does so with a single gate, suppressing the forget subspace chiefly on inputs its frozen head's weight scores read as a forget class. It is closed form, needs no retain data or gradient training, and costs orders of magnitude less than retraining. Across five object, face, and speaker benchmarks spanning two modalities and both convolutional and transformer backbones, the frontier predicts the measured retain cost. SCOPE leads the source-free erasers on every benchmark and forget-set size, and at the hardest setting it tops every unlearner, trained methods included.

cs.LG↗

arXiv2026

Retain-Neutral Surrogates for Min-Max Unlearning

Machine unlearning seeks to remove the influence of designated training data while preserving performance on the remaining data. Approximate unlearning can be viewed as a local editing problem; in min-max unlearning, the key local object is the surrogate point at which the retain objective is evaluated. When forget and retain gradients are strongly aligned, an unconstrained forget-maximizing perturbation can move to a surrogate point that increases retain loss. We propose Retain-Orthogonal Surrogate Unlearning (ROSU), which constrains the inner surrogate construction by maximizing first-order forget gain subject to zero first-order retain change under a fixed perturbation budget. This yields a closed-form retain-orthogonal perturbation, a lightweight transported outer update, and amplification along the retain-neutral direction. Our analysis establishes (i) a curvature-controlled second-order bound on retain damage, (ii) a positive-alignment regime in which ROSU strictly reduces surrogate retain loss relative to standard min-max perturbations, and (iii) near-equivalence when the two gradients are nearly orthogonal. Across vision and language benchmarks (CIFAR-10/100, Tiny-ImageNet, TOFU, WMDP), the empirical pattern follows this geometry: ROSU gives its clearest gains in high-coupling regimes while remaining competitive elsewhere.

cs.LG↗

arXiv2026

Optimal Power Allocation and Sub-Optimal Channel Assignment for Downlink NOMA Systems Using Deep Reinforcement Learning

In recent years, Non-Orthogonal Multiple Access (NOMA) system has emerged as a promising candidate for multiple access frameworks due to the evolution of deep machine learning, trying to incorporate deep machine learning into the NOMA system. The main motivation for such active studies is the growing need to optimize the utilization of network resources as the expansion of the internet of things (IoT) caused a scarcity of network resources. The NOMA addresses this need by power multiplexing, allowing multiple users to access the network simultaneously. Nevertheless, the NOMA system has few limitations. Several works have proposed to mitigate this, including the optimization of power allocation known as joint resource allocation(JRA) method, and integration of the JRA method and deep reinforcement learning (JRA-DRL). Despite this, the channel assignment problem remains unclear and requires further investigation. In this paper, we propose a deep reinforcement learning framework incorporating replay memory with an on-policy algorithm, allocating network resources in a NOMA system to generalize the learning. Also, we provide extensive simulations to evaluate the effects of varying the learning rate, batch size, type of model, and the number of features in the state.

cs.AI↗

arXiv2025

Scalable Processing-Near-Memory for 1M-Token LLM Inference: CXL-Enabled KV-Cache Management Beyond GPU Limits

The expansion of context windows in large language models (LLMs) to multi-million tokens introduces severe memory and compute bottlenecks, particularly in managing the growing Key-Value (KV) cache. While Compute Express Link (CXL) enables non-eviction frameworks that offload the full KV-cache to scalable external memory, these frameworks still suffer from costly data transfers when recalling non-resident KV tokens to limited GPU memory as context lengths increase. This work proposes scalable Processing-Near-Memory (PNM) for 1M-Token LLM Inference, a CXL-enabled KV-cache management system that coordinates memory and computation beyond GPU limits. Our design offloads token page selection to a PNM accelerator within CXL memory, eliminating costly recalls and enabling larger GPU batch sizes. We further introduce a hybrid parallelization strategy and a steady-token selection mechanism to enhance compute efficiency and scalability. Implemented atop a state-of-the-art CXL-PNM system, our solution delivers consistent performance gains for LLMs with up to 405B parameters and 1M-token contexts. Our PNM-only offloading scheme (PNM-KV) and GPU-PNM hybrid with steady-token execution (PnG-KV) achieve up to 21.9x throughput improvement, up to 60x lower energy per token, and up to 7.3x better total cost efficiency than the baseline, demonstrating that CXL-enabled multi-PNM architectures can serve as a scalable backbone for future long-context LLM inference.

cs.AR↗

arXiv2025

Analysis of a Memcapacitor-Based for Neural Network Accelerator Framework

Data-intensive computing tasks, such as training neural networks, are crucial for artificial intelligence applications but often come with high energy demands. One promising solution is to develop specialized hardware that directly maps neural networks, utilizing arrays of memristive devices to perform parallel multiply-accumulate operations. In our research, we introduce a novel CMOS-based memcapacitor circuit that is validated using the cadence tool. Additionally, we developed the device in Python to facilitate the design of a memcapacitive-based accelerator. Our proposed framework employs a crossbar array of memcapacitor devices to train a neural network capable of digit classification and CIFAR dataset recognition. We tested the non-ideal characteristics of the constructed memcapacitor-based neural network. The system achieved an impressive 98.4% training accuracy in digit recognition and 94.4% training accuracy in CIFAR recognition, highlighting its effectiveness. This study demonstrates the potential of memcapacitor-based neural network systems in handling classification tasks and sets the stage for further advancements in neuromorphic computing.

cs.AR↗

arXiv2024

Swin fMRI Transformer Predicts Early Neurodevelopmental Outcomes from Neonatal fMRI

Brain development in the first few months of human life is a critical phase characterized by rapid structural growth and functional organization. Accurately predicting developmental outcomes during this time is crucial for identifying delays and enabling timely interventions. This study introduces the SwiFT (Swin 4D fMRI Transformer) model, designed to predict Bayley-III composite scores using neonatal fMRI from the Developing Human Connectome Project (dHCP). To enhance predictive accuracy, we apply dimensionality reduction via group independent component analysis (ICA) and pretrain SwiFT on large adult fMRI datasets to address the challenges of limited neonatal data. Our analysis shows that SwiFT significantly outperforms baseline models in predicting cognitive, motor, and language outcomes, leveraging both single-label and multi-label prediction strategies. The model's attention-based architecture processes spatiotemporal data end-to-end, delivering superior predictive performance. Additionally, we use Integrated Gradients with Smoothgrad sQuare (IG-SQ) to interpret predictions, identifying neural spatial representations linked to early cognitive and behavioral development. These findings underscore the potential of Transformer models to advance neurodevelopmental research and clinical practice.

q-bio.NC↗

arXiv2018

Study of the ecological gas for MRPCs

The Multigap Resistive Plate Chamber (MRPC) is a gaseous detector; the performance depends very much on the gas mixture as well as the design. MRPCs are used as a timing device in several collider experiments and cosmic ray experiments thanks to the excellent timing performance. The typical gas mixtures of RPC-type detectors at current experiments are based on the gases $\rm C_2F_4H_2$ and $\rm SF_6$. These gases have very high Global Warming Potential (GWP) values of 1430 and 23900 respectively. The present contribution has been performed as a part of efforts to reduce the amount of greenhouse gases used in high energy experiments. The performance of MRPC has been measured with two different gas mixtures; $\rm C_2F_4H_2$ based gas mixtures and the ecological $\rm C_3F_4H_2$ (HFO-1234ze). A small MRPC was used for the tests. It has an sensitive area of 20 $\times$ 20 $\rm cm^2$; it was been built with 6 gaps of 220 $μ$m. In normal operation, the strong space charge created within the gas avalanche limits the avalanche's growth. $\rm SF_6$ plays an important part in the process due to its high attachment coefficient at low electric fields. It is thus necessary to find another gas that has a similar attachment coefficient. $\rm CF_{3}I$ is a possible candidate. Tests were performed with this gas added to $\rm C_3F_4H_2$.

physics.ins-det↗