Chanho Park

Chanho Park, Namyoon Lee

The training efficiency of complex deep learning models can be significantly improved through the use of distributed optimization. However, this process is often hindered by a large amount of communication cost between workers and a parameter server during iterations. To address this bottleneck, in this paper, we present a new communication-efficient algorithm that offers the synergistic benefits of both sparsification and sign quantization, called ${\sf S}^3$GD-MV. The workers in ${\sf S}^3$GD-MV select the top-$K$ magnitude components of their local gradient vector and only send the signs of these components to the server. The server then aggregates the signs and returns the results via a majority vote rule. Our analysis shows that, under certain mild conditions, ${\sf S}^3$GD-MV can converge at the same rate as signSGD while significantly reducing communication costs, if the sparsification parameter $K$ is properly chosen based on the number of workers and the size of the deep learning model. Experimental results using both independent and identically distributed (IID) and non-IID datasets demonstrate that the ${\sf S}^3$GD-MV attains higher accuracy than signSGD, significantly reducing communication costs. These findings highlight the potential of ${\sf S}^3$GD-MV as a promising solution for communication-efficient distributed optimization in deep learning.

Juil Koo, Chanho Park, Minhyuk Sung

We introduce Posterior Distillation Sampling (PDS), a novel optimization method for parametric image editing based on diffusion models. Existing optimization-based methods, which leverage the powerful 2D prior of diffusion models to handle various parametric images, have mainly focused on generation. Unlike generation, editing requires a balance between conforming to the target attribute and preserving the identity of the source content. Recent 2D image editing methods have achieved this balance by leveraging the stochastic latent encoded in the generative process of diffusion models. To extend the editing capabilities of diffusion models shown in pixel space to parameter space, we reformulate the 2D image editing method into an optimization form named PDS. PDS matches the stochastic latents of the source and the target, enabling the sampling of targets in diverse parameter spaces that align with a desired attribute while maintaining the source's identity. We demonstrate that this optimization resembles running a generative process with the target attribute, but aligning this process with the trajectory of the source's generative process. Extensive editing results in Neural Radiance Fields and Scalable Vector Graphics representations demonstrate that PDS is capable of sampling targets to fulfill the aforementioned balance across various parameter spaces.

Chanho Park, Chengsong Lu, Mingjie Chen et al.

Word error rate (WER) estimation aims to evaluate the quality of an automatic speech recognition (ASR) system's output without requiring ground-truth labels. This task has gained increasing attention as advanced ASR systems are trained on large amounts of data. In this context, the computational efficiency of a WER estimator becomes essential in practice. However, previous works have not prioritised this aspect. In this paper, a Fast estimator for WER (Fe-WER) is introduced, utilizing average pooling over self-supervised learning representations for speech and text. Our results demonstrate that Fe-WER outperformed a baseline relatively by 14.10% in root mean square error and 1.22% in Pearson correlation coefficient on Ted-Lium3. Moreover, a comparative analysis of the distributions of target WER and WER estimates was conducted, including an examination of the average values per speaker. Lastly, the inference speed was approximately 3.4 times faster in the real-time factor.

Bumsu Park, Chanho Park, Youngmok Park et al.

For a Gaussian source under mean-squared error (MSE), classical transform coding is rate--distortion (RD) optimal: the Karhunen--Loeve transform (KLT) diagonalizes the covariance, reverse waterfilling allocates the bits, and scalar quantization closes the loop. This elegant story breaks down for multimodal sources, where no single covariance can capture heterogeneous local geometries, and the RD function loses its closed form. We revisit this problem through Gaussian-mixture sources and develop a constructive RD theory for them. Our key finding is that the mixture structure incurs only a component label cost. Conditioned on the active mixture component, each branch is Gaussian; the challenge is allocating bits across heterogeneous branches. We prove that the genie-aided conditional RD function is governed by a single global reverse-waterfilling level shared across all components and eigenmodes. Building on this result, we introduce PrismQuant, which transmits the component label losslessly and encodes the residual using the component-matched KLT, followed by scalar quantization, achieving a rate of H(C)/n bits per source dimension of the converse, with a vanishing asymptotic gap. We further develop a practical implementation based on EM-driven Gaussian-mixture learning, component-adaptive KLTs, and entropy-constrained scalar quantization (ECSQ). Experiments on synthetic Gaussian mixtures show that PrismQuant closely approaches the theoretical RD bound, while experiments on real-world channel-state-information (CSI) data demonstrate competitive or superior performance compared with transformer-based learned codecs at more than one order of magnitude smaller model size.

Eunwon Kim, Chanho Park, Buru Chang

Shared memories between two individuals strengthen their bond and are crucial for facilitating their ongoing conversations. This study aims to make long-term dialogue more engaging by leveraging these shared memories. To this end, we introduce a new long-term dialogue dataset named SHARE, constructed from movie scripts, which are a rich source of shared memories among various relationships. Our dialogue dataset contains the summaries of persona information and events of two individuals, as explicitly revealed in their conversation, along with implicitly extractable shared memories. We also introduce EPISODE, a long-term dialogue framework based on SHARE that utilizes shared experiences between individuals. Through experiments using SHARE, we demonstrate that shared memories between two individuals make long-term dialogues more engaging and sustainable, and that EPISODE effectively manages shared memories during dialogue. Our dataset and code are available at https://github.com/e1kim/SHARE.

Phillip Y. Lee, Chanho Park, Mingue Park et al.

Can warping tokens, rather than pixels, help multimodal large language models (MLLMs) understand how a scene appears from a nearby viewpoint? While MLLMs perform well on visual reasoning, they remain fragile to viewpoint changes, as pixel-wise warping is highly sensitive to small depth errors and often introduces geometric distortions. Drawing on theories of mental imagery that posit part-level structural representations as the basis for human perspective transformation, we examine whether image tokens in ViT-based MLLMs serve as an effective substrate for viewpoint changes. We compare forward and backward warping, finding that backward token warping, which defines a dense grid on the target view and retrieves a corresponding source-view token for each grid point, achieves greater stability and better preserves semantic coherence under viewpoint shifts. Experiments on our proposed ViewBench benchmark demonstrate that token-level warping enables MLLMs to reason reliably from nearby viewpoints, consistently outperforming all baselines including pixel-wise warping approaches, spatially fine-tuned MLLMs, and a generative warping method.

Juil Koo, Wei-Tung Lin, Chanho Park et al.

Human creativity follows a perceptual process, moving from abstract ideas to finer details during creation. While 3D generative models have advanced dramatically, models specifically designed to assist human imagination in 3D creation -- particularly for detailing abstractions from coarse to fine -- have not been explored. We propose a framework that enables intuitive and interactive 3D shape generation by iteratively splitting bounding boxes to refine the set of bounding boxes. The main technical components of our framework are two generative models: the box-splitting generative model and the box-to-shape generative model. The first model, named BoxSplitGen, generates a collection of 3D part bounding boxes with varying granularity by iteratively splitting coarse bounding boxes. It utilizes part bounding boxes created through agglomerative merging and learns the reverse of the merging process -- the splitting sequences. The model consists of two main components: the first learns the categorical distribution of the box to be split, and the second learns the distribution of the two new boxes, given the set of boxes and the indication of which box to split. The second model, the box-to-shape generative model, is trained by leveraging the 3D shape priors learned by an existing 3D diffusion model while adapting the model to incorporate bounding box conditioning. In our experiments, we demonstrate that the box-splitting generative model outperforms token prediction models and the inpainting approach with an unconditional diffusion model. Also, we show that our box-to-shape model, based on a state-of-the-art 3D diffusion model, provides superior results compared to a previous model.

Bumsu Park, Youngmok Park, Chanho Park et al.

We study channel state information (CSI) compression for wideband frequency division duplex massive multiple-input multiple-output (MIMO) when the base station (BS) reconstructs CSI using an imperfect covariance model. Under matched second-order statistics, remote rate--distortion theory yields transform coding with reverse water-filling (RWF) over covariance eigenmodes. With decoder-side covariance mismatch, however, this allocation is no longer end-to-end optimal. We derive an achievable mismatched Gaussian rate--distortion characterization based on a Gaussian test channel and a mismatched minimum mean square error (MMSE) reconstruction rule. In a shared-eigenvector regime (common eigenbasis, mismatched eigenvalues), the problem decouples across modes and leads to a robust reverse water-filling (RRWF) allocation computable via bisection and per-mode root finding. Simulations using wideband massive MIMO covariance models show that RRWF consistently improves reconstruction distortion and end-to-end mean square error relative to conventional RWF under mismatch.

Phillip Y. Lee, Jihyeon Je, Chanho Park et al.

We present a framework for perspective-aware reasoning in vision-language models (VLMs) through mental imagery simulation. Perspective-taking, the ability to perceive an environment or situation from an alternative viewpoint, is a key benchmark for human-level visual understanding, essential for environmental interaction and collaboration with autonomous agents. Despite advancements in spatial reasoning within VLMs, recent research has shown that modern VLMs significantly lack perspective-aware reasoning capabilities and exhibit a strong bias toward egocentric interpretations. To bridge the gap between VLMs and human perception, we focus on the role of mental imagery, where humans perceive the world through abstracted representations that facilitate perspective shifts. Motivated by this, we propose a framework for perspective-aware reasoning, named Abstract Perspective Change (APC), that effectively leverages vision foundation models, such as object detection, segmentation, and orientation estimation, to construct scene abstractions and enable perspective transformations. Our experiments on synthetic and real-image benchmarks, compared with various VLMs, demonstrate significant improvements in perspective-aware reasoning with our framework, further outperforming fine-tuned spatial reasoning models and novel-view-synthesis-based approaches.

Chanho Park, Namyoon Lee

Distributed learning is an effective approach to accelerate model training using multiple workers. However, substantial communication delays emerge between workers and a parameter server due to massive costs associated with communicating gradients. SignSGD with majority voting (signSGD-MV) is a simple yet effective optimizer that reduces communication costs through one-bit quantization, yet the convergence rates considerably decrease as adversarial workers increase. In this paper, we show that the convergence rate is invariant as the number of adversarial workers increases, provided that the number of adversarial workers is smaller than that of benign workers. The key idea showing this counter-intuitive result is our novel signSGD with federated defense (signSGD-FD). Unlike the traditional approaches, signSGD-FD exploits the gradient information sent by adversarial workers with the proper weights, which are obtained through gradient sign decoding. Experimental results demonstrate signSGD-FD achieves superior convergence rates over traditional algorithms in various adversarial attack scenarios.

Bumsu Park, Youngmok Park, Chanho Park et al.

Channel state information (CSI) feedback in frequency-division duplex (FDD) massive multiple-input multiple-output (MIMO) systems is fundamentally limited by the high dimensionality of wideband channels. In this paper, we model the stacked wideband CSI vector as a Gaussian-mixture source with a latent geometry state that represents different propagation environments. Each component corresponds to a locally stationary regime characterized by a correlated proper complex Gaussian distribution with its own covariance matrix. This representation captures the multimodal nature of practical CSI datasets while preserving the analytical tractability of Gaussian models. Motivated by this structure, we propose Gaussian-mixture transform coding (GMTC), a practical CSI feedback architecture that combines state inference with state-adaptive TC. The mixture parameters are learned offline from channel samples and stored as a shared statistical dictionary at both the user equipment (UE) and the base station. For each CSI realization, the UE identifies the most likely geometry state, encodes the corresponding label using a lossless source code, and compresses the CSI using the Karhunen-Loeve transform matched to that state. We further characterize the fundamental limits of CSI compression under this model by deriving analytical converse and achievability bounds on the rate-distortion (RD) function. A key structural result is that the optimal bit allocation across all mixture components is governed by a single global reverse-waterfilling level. Simulations on the COST2100 dataset show that GMTC significantly improves the RD tradeoff relative to neural transform coding approaches while requiring substantially smaller model memory and lower inference complexity. These results indicate that near-optimal CSI compression can be achieved through state-adaptive TC without relying on large neural encoders.

Chanho Park, H. Vincent Poor, Namyoon Lee

Distributed learning is commonly used for accelerating model training by harnessing the computational capabilities of multiple-edge devices. However, in practical applications, the communication delay emerges as a bottleneck due to the substantial information exchange required between workers and a central parameter server. SignSGD with majority voting (signSGD-MV) is an effective distributed learning algorithm that can significantly reduce communication costs by one-bit quantization. However, due to heterogeneous computational capabilities, it fails to converge when the mini-batch sizes differ among workers. To overcome this, we propose a novel signSGD optimizer with \textit{federated voting} (signSGD-FV). The idea of federated voting is to exploit learnable weights to perform weighted majority voting. The server learns the weights assigned to the edge devices in an online fashion based on their computational capabilities. Subsequently, these weights are employed to decode the signs of the aggregated local gradients in such a way to minimize the sign decoding error probability. We provide a unified convergence rate analysis framework applicable to scenarios where the estimated weights are known to the parameter server either perfectly or imperfectly. We demonstrate that the proposed signSGD-FV algorithm has a theoretical convergence guarantee even when edge devices use heterogeneous mini-batch sizes. Experimental results show that signSGD-FV outperforms signSGD-MV, exhibiting a faster convergence rate, especially in heterogeneous mini-batch sizes.

Chanho Park, Mingjie Chen, Thomas Hain

Word error rate (WER) is a metric used to evaluate the quality of transcriptions produced by Automatic Speech Recognition (ASR) systems. In many applications, it is of interest to estimate WER given a pair of a speech utterance and a transcript. Previous work on WER estimation focused on building models that are trained with a specific ASR system in mind (referred to as ASR system-dependent). These are also domain-dependent and inflexible in real-world applications. In this paper, a hypothesis generation method for ASR System-Independent WER estimation (SIWE) is proposed. In contrast to prior work, the WER estimators are trained using data that simulates ASR system output. Hypotheses are generated using phonetically similar or linguistically more likely alternative words. In WER estimation experiments, the proposed method reaches a similar performance to ASR system-dependent WER estimators on in-domain data and achieves state-of-the-art performance on out-of-domain data. On the out-of-domain data, the SIWE model outperformed the baseline estimators in root mean square error and Pearson correlation coefficient by relative 17.58% and 18.21%, respectively, on Switchboard and CALLHOME. The performance was further improved when the WER of the training set was close to the WER of the evaluation dataset.

Chanho Park, Seunghoon Lee, Namyoon Lee

In this paper, we consider the problem of wireless federated learning based on sign stochastic gradient descent (signSGD) algorithm via a multiple access channel. When sending locally computed gradient's sign information, each mobile device requires to apply precoding to circumvent wireless fading effects. In practice, however, acquiring perfect knowledge of channel state information (CSI) at all mobile devices is infeasible. In this paper, we present a simple yet effective precoding method with limited channel knowledge, called sign-alignment precoding. The idea of sign-alignment precoding is to protect sign-flipping errors from wireless fadings. Under the Gaussian prior assumption on the local gradients, we also derive the mean squared error (MSE)-optimal aggregation function called Bayesian over-the-air computation (BayAirComp). Our key finding is that one-bit precoding with BayAirComp aggregation can provide a better learning performance than the existing precoding method even using perfect CSI with AirComp aggregation.

Seunghoon Lee, Chanho Park, Song-Nam Hong et al.

Federated learning is a privacy-preserving and distributed training method using heterogeneous data sets stored at local devices. Federated learning over wireless networks requires aggregating locally computed gradients at a server where the mobile devices send statistically distinct gradient information over heterogenous communication links. This paper proposes a Bayesian federated learning (BFL) algorithm to aggregate the heterogeneous quantized gradient information optimally in the sense of minimizing the mean-squared error (MSE). The idea of BFL is to aggregate the one-bit quantized local gradients at the server by jointly exploiting i) the prior distributions of the local gradients, ii) the gradient quantizer function, and iii) channel distributions. Implementing BFL requires high communication and computational costs as the number of mobile devices increases. To address this challenge, we also present an efficient modified BFL algorithm called scalable-BFL (SBFL). In SBFL, we assume a simplified distribution on the local gradient. Each mobile device sends its one-bit quantized local gradient together with two scalar parameters representing this distribution. The server then aggregates the noisy and faded quantized gradients to minimize the MSE. We provide a convergence analysis of SBFL for a class of non-convex loss functions. Our analysis elucidates how the parameters of communication channels and the gradient priors affect convergence. From simulations, we demonstrate that SBFL considerably outperforms the conventional sign stochastic gradient descent algorithm when training and testing neural networks using MNIST data sets over heterogeneous wireless networks.