Chaerin Kong

Julien Abadji, Marah Abdin, Connor Adams et al.

We present Laguna M.1 and Laguna XS.2, two Mixture-of-Experts foundation models built for long-horizon, agentic coding: M.1 has $225.8$B total parameters ($23.4$B activated per token) and XS.2 has $33.4$B total ($3$B activated). Both models were trained from scratch end-to-end inside the same internal system that we refer to as our Model Factory: a tightly-integrated stack of versioned data, training, evaluation, and inference components that turn model development into an industrial process. We describe the principles and design choices of the Model Factory and also detail the end-to-end training process of our models, throughout pre-training data and architecture, post-training stages, evaluation, and quantization. On agentic software engineering and terminal benchmarks (SWE-bench Verified, SWE-bench Multilingual, SWE-Bench Pro, and Terminal-Bench 2.0) M.1 and XS.2 are competitive with state-of-the-art open models in their respective weight classes. Laguna XS.2 weights are released under Apache~2.0 at https://huggingface.co/collections/poolside/laguna-xs2.

Yeji Song, Chaerin Kong, Seoyoung Lee et al.

Neural Radiance Fields (NeRF) achieves photo-realistic image rendering from novel views, and the Neural Scene Graphs (NSG) \cite{ost2021neural} extends it to dynamic scenes (video) with multiple objects. Nevertheless, computationally heavy ray marching for every image frame becomes a huge burden. In this paper, taking advantage of significant redundancy across adjacent frames in videos, we propose a feature-reusing framework. From the first try of naively reusing the NSG features, however, we learn that it is crucial to disentangle object-intrinsic properties consistent across frames from transient ones. Our proposed method, \textit{Consistency-Field-based NSG (CF-NSG)}, reformulates neural radiance fields to additionally consider \textit{consistency fields}. With disentangled representations, CF-NSG takes full advantage of the feature-reusing scheme and performs an extended degree of scene manipulation in a more controllable manner. We empirically verify that CF-NSG greatly improves the inference efficiency by using 85\% less queries than NSG without notable degradation in rendering quality. Code will be available at: https://github.com/ldynx/CF-NSG

Jiho Jang, Chaerin Kong, Donghyeon Jeon et al.

Contrastive learning is a form of distance learning that aims to learn invariant features from two related representations. In this paper, we explore the bold hypothesis that an image and its caption can be simply regarded as two different views of the underlying mutual information, and train a model to learn a unified vision-language representation space that encodes both modalities at once in a modality-agnostic manner. We first identify difficulties in learning a generic one-tower model for vision-language pretraining (VLP), and propose OneR as a simple yet effective framework for our goal. We discover intriguing properties that distinguish OneR from the previous works that learn modality-specific representation spaces such as zero-shot object localization, text-guided visual reasoning and multi-modal retrieval, and present analyses to provide insights into this new form of multi-modal representation learning. Thorough evaluations demonstrate the potential of a unified modality-agnostic VLP framework.

Chaerin Kong, DongHyeon Jeon, Ohjoon Kwon et al.

Fashion attribute editing is a task that aims to convert the semantic attributes of a given fashion image while preserving the irrelevant regions. Previous works typically employ conditional GANs where the generator explicitly learns the target attributes and directly execute the conversion. These approaches, however, are neither scalable nor generic as they operate only with few limited attributes and a separate generator is required for each dataset or attribute set. Inspired by the recent advancement of diffusion models, we explore the classifier-guided diffusion that leverages the off-the-shelf diffusion model pretrained on general visual semantics such as Imagenet. In order to achieve a generic editing pipeline, we pose this as multi-attribute image manipulation task, where the attribute ranges from item category, fabric, pattern to collar and neckline. We empirically show that conventional methods fail in our challenging setting, and study efficient adaptation scheme that involves recently introduced attention-pooling technique to obtain a multi-attribute classifier guidance. Based on this, we present a mask-free fashion attribute editing framework that leverages the classifier logits and the cross-attention map for manipulation. We empirically demonstrate that our framework achieves convincing sample quality and attribute alignments.

Chaerin Kong, Nojun Kwak

Recent years have witnessed astonishing advances in the field of multimodal representation learning, with contrastive learning being the cornerstone for major breakthroughs. Latest works delivered further improvements by incorporating different objectives such as masked modeling and captioning into the frameworks, but our understanding on how these objectives facilitate learning remains vastly incomplete. In this paper, we leverage the fact that classifier-guided diffusion models generate images that reflect the semantic signals provided by the classifier to study the characteristics of multimodal learning objectives. Specifically, we compare contrastive, matching and captioning loss in terms of their semantic signals, and introduce a simple baseline that not only supports our analyses but also improves the quality of generative guidance in a straightforward manner.

Donghoon Han, Seunghyeon Seo, Donghyeon Jeon et al.

Transformers have demonstrated tremendous success not only in the natural language processing (NLP) domain but also the field of computer vision, igniting various creative approaches and applications. Yet, the superior performance and modeling flexibility of transformers came with a severe increase in computation costs, and hence several works have proposed methods to reduce this burden. Inspired by a cost-cutting method originally proposed for language models, Data Multiplexing (DataMUX), we propose a novel approach for efficient visual recognition that employs additional dim1 batching (i.e., concatenation) that greatly improves the throughput with little compromise in the accuracy. We first introduce a naive adaptation of DataMux for vision models, Image Multiplexer, and devise novel components to overcome its weaknesses, rendering our final model, ConcatPlexer, at the sweet spot between inference speed and accuracy. The ConcatPlexer was trained on ImageNet1K and CIFAR100 dataset and it achieved 23.5% less GFLOPs than ViT-B/16 with 69.5% and 83.4% validation accuracy, respectively.

Chaerin Kong, Nojun Kwak

The capacity to learn incrementally from an online stream of data is an envied trait of human learners, as deep neural networks typically suffer from catastrophic forgetting and stability-plasticity dilemma. Several works have previously explored incremental few-shot learning, a task with greater challenges due to data constraint, mostly in classification setting with mild success. In this work, we study the underrepresented task of generative incremental few-shot learning. To effectively handle the inherent challenges of incremental learning and few-shot learning, we propose a novel framework named ConPro that leverages the two-player nature of GANs. Specifically, we design a conservative generator that preserves past knowledge in parameter and compute efficient manner, and a progressive discriminator that learns to reason semantic distances between past and present task samples, minimizing overfitting with few data points and pursuing good forward transfer. We present experiments to validate the effectiveness of ConPro.

Jiho Jang, Seonhoon Kim, Kiyoon Yoo et al.

State-of-the-art frameworks in self-supervised learning have recently shown that fully utilizing transformer-based models can lead to performance boost compared to conventional CNN models. Striving to maximize the mutual information of two views of an image, existing works apply a contrastive loss to the final representations. Motivated by self-distillation in the supervised regime, we further exploit this by allowing the intermediate representations to learn from the final layer via the contrastive loss. Through self-distillation, the intermediate layers are better suited for instance discrimination, making the performance of an early-exited sub-network not much degraded from that of the full network. This renders the pretext task easier also for the final layer, leading to better representations. Our method, Self-Distilled Self-Supervised Learning (SDSSL), outperforms competitive baselines (SimCLR, BYOL and MoCo v3) using ViT on various tasks and datasets. In the linear evaluation and k-NN protocol, SDSSL not only leads to superior performance in the final layers, but also in most of the lower layers. Furthermore, qualitative and quantitative analyses show how representations are formed more effectively along the transformer layers. Code is available at https://github.com/hagiss/SDSSL.

Chaerin Kong, Jeesoo Kim, Donghoon Han et al.

Producing diverse and realistic images with generative models such as GANs typically requires large scale training with vast amount of images. GANs trained with limited data can easily memorize few training samples and display undesirable properties like "stairlike" latent space where interpolation in the latent space yields discontinuous transitions in the output space. In this work, we consider a challenging task of pretraining-free few-shot image synthesis, and seek to train existing generative models with minimal overfitting and mode collapse. We propose mixup-based distance regularization on the feature space of both a generator and the counterpart discriminator that encourages the two players to reason not only about the scarce observed data points but the relative distances in the feature space they reside. Qualitative and quantitative evaluation on diverse datasets demonstrates that our method is generally applicable to existing models to enhance both fidelity and diversity under few-shot setting. Code is available.

Chaerin Kong, Jiho Jang, Nojun Kwak

Differential Transformer has recently gained significant attention for its impressive empirical performance, often attributed to its ability to perform noise canceled attention. However, precisely how differential attention achieves its empirical benefits remains poorly understood. Moreover, Differential Transformer architecture demands large-scale training from scratch, hindering utilization of open pretrained weights. In this work, we conduct an in-depth investigation of Differential Transformer, uncovering three key factors behind its success: (1) enhanced expressivity via negative attention, (2) reduced redundancy among attention heads, and (3) improved learning dynamics. Based on these findings, we propose DEX, a novel method to efficiently integrate the advantages of differential attention into pretrained language models. By reusing the softmax attention scores and adding a lightweight differential operation on the output value matrix, DEX effectively incorporates the key advantages of differential attention while remaining lightweight in both training and inference. Evaluations confirm that DEX substantially improves the pretrained LLMs across diverse benchmarks, achieving significant performance gains with minimal adaptation data (< 0.01%).

Chaerin Kong, Seungyong Lee, Soohyeok Im et al.

Image editing has been a long-standing challenge in the research community with its far-reaching impact on numerous applications. Recently, text-driven methods started to deliver promising results in domains like human faces, but their applications to more complex domains have been relatively limited. In this work, we explore the task of fashion style editing, where we aim to manipulate the fashion style of human imagery using text descriptions. Specifically, we leverage a generative human prior and achieve fashion style editing by navigating its learned latent space. We first verify that the existing text-driven editing methods fall short for our problem due to their overly simplified guidance signal, and propose two directions to reinforce the guidance: textual augmentation and visual referencing. Combined with our empirical findings on the latent space structure, our Fashion Style Editing framework (FaSE) successfully projects abstract fashion concepts onto human images and introduces exciting new applications to the field.

Seungwoo Lee, Chaerin Kong, Donghyeon Jeon et al.

Recent advances in diffusion models have showcased promising results in the text-to-video (T2V) synthesis task. However, as these T2V models solely employ text as the guidance, they tend to struggle in modeling detailed temporal dynamics. In this paper, we introduce a novel T2V framework that additionally employ audio signals to control the temporal dynamics, empowering an off-the-shelf T2I diffusion to generate audio-aligned videos. We propose audio-based regional editing and signal smoothing to strike a good balance between the two contradicting desiderata of video synthesis, i.e., temporal flexibility and coherence. We empirically demonstrate the effectiveness of our method through experiments, and further present practical applications for contents creation.