arXiv subjects

Yeongmin Kim

Publications and source records attributed to Yeongmin Kim.

18 recordsLinked to original sources

arXiv2026

Multi-Agent Debate and Visual Information Extraction for SeePhys Pro: A 1st-Place Technical Report from ICML 2026 AI4Math Track 3 Challenge

This technical report presents our approach to Challenge Track~3: SeePhys Pro at the 3rd AI for Math Workshop, where the task is to answer college-level physics questions whose statement and figure may be given partly or entirely as an image. Visual physics problems become substantially harder for large language models when the decisive information resides in a figure rather than in the text, and this modality gap widens as more of the problem migrates into the image. We address the task with a two-stage framework: a visual information extraction stage that re-expresses figure content as solver-readable text to close the modality gap, and a reasoning stage that orchestrates three heterogeneous solvers through multi-agent debate. Our analysis yields two findings: the gain from orchestration comes from reliable answer selection rather than from additional debate, and the value of a figure aid scales with how much of the problem is locked inside the image. The resulting pipeline improves overall accuracy over a single-agent baseline from 0.643 to 0.802 on the public split, and won 1st place on both the public and the private leaderboard (private overall 0.743).

cs.LG↗

arXiv2026

Distillation of Large Language Models via Concrete Score Matching

Large language models (LLMs) deliver remarkable performance but are costly to deploy, motivating knowledge distillation (KD) for efficient inference. Existing KD objectives typically match student and teacher probabilities via softmax, which blurs valuable logit information. While direct logit distillation (DLD) mitigates softmax smoothing, it fails to account for logit shift invariance, thereby restricting the solution space. We propose Concrete Score Distillation (CSD), a discrete score-matching objective that overcomes both softmax-induced smoothing and restrictions on the optimal solution set. We resolve the training instability and quadratic complexity of discrete score-matching in autoregressive LLMs, and the resulting CSD objective aligns relative logit differences across all vocabulary pairs between student and teacher with flexible weighting. We provide both mode-seeking and mode-covering instances within our framework and evaluate CSD on task-agnostic instruction-following and task-specific distillation using GPT-2-1.5B, OpenLLaMA-7B, and GEMMA-7B-IT. Experiments show that CSD consistently surpasses recent KD objectives, achieves favorable fidelity-diversity trade-offs, and yields complementary gains when combined with on-policy techniques, demonstrating its scalability and effectiveness for LLM distillation. Code: https://github.com/aailab-kaist/CSD.

cs.LG↗

arXiv2026

Lookahead Sample Reward Guidance for Test-Time Scaling of Diffusion Models

Diffusion models have demonstrated strong generative performance; however, generated samples often fail to fully align with human intent. This paper studies an efficient test-time scaling method for sampling from regions with higher human-aligned reward values. Existing methods for computing the expected future reward (EFR) face important limitations: backward rollout incurs prohibitively high sampling costs, while Tweedie-based approaches, including Sequential Monte Carlo and gradient guidance, suffer from bias and inherent sampling issues. We show that the EFR at any $\mathbf{x}_t$ can be computed using only marginal samples from a pre-trained diffusion model, enabling closed-form reward guidance without neural backpropagation. To further improve efficiency, we introduce a few-step lookahead sampling and an accurate solver that guides particles toward high-reward lookahead samples. We refer to this sampling scheme as LiDAR sampling. LiDAR achieves the same GenEval performance as the latest gradient guidance method for SDXL with a 9.5x speedup. We release the code at https://github.com/aailab-kaist/Diffusion-LiDAR-Sampling.

cs.LG↗

arXiv2026

AMiD: Knowledge Distillation for LLMs with $α$-mixture Assistant Distribution

Autoregressive large language models (LLMs) have achieved remarkable improvement across many tasks but incur high computational and memory costs. Knowledge distillation (KD) mitigates this issue by transferring knowledge from a large teacher to a smaller student through distributional alignment. Previous studies have proposed various discrepancy metrics, but the capacity gap and training instability caused by near-zero probabilities, stemming from the high-dimensional output of LLMs, remain fundamental limitations. To overcome these challenges, several approaches implicitly or explicitly incorporating assistant distribution have recently been proposed. However, the past proposals of assistant distributions have been a fragmented approach without a systematic investigation of the interpolation path and the divergence. This paper proposes $α$-mixture assistant distribution, a novel generalized family of assistant distributions, and $α$-mixture distillation, coined AMiD, a unified framework for KD using the assistant distribution. The $α$-mixture assistant distribution provides a continuous extension of the assistant distribution by introducing a new distribution design variable $α$, which has been fixed in all previous approaches. Furthermore, AMiD generalizes the family of divergences used with the assistant distributions based on optimality, which has also been restricted in previous works. Through extensive experiments, we demonstrate that AMiD offers superior performance and training stability by leveraging a broader and theoretically grounded assistant distribution space. We release the code at https://github.com/aailab-kaist/AMiD.

cs.LG↗

arXiv2026

Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment

Large language models (LLMs) are commonly aligned with human preferences using reinforcement learning from human feedback (RLHF). In this method, LLM policies are generally optimized through reward maximization with Kullback-Leibler (KL) divergence regularization of the reference policy. However, KL and its $f$-divergence variants only compare token probabilities at identical indices, failing to capture semantic similarity. We propose Wasserstein Policy Regularization (WPR), a semantic-aware regularization for the RLHF framework based on the entropy-regularized Wasserstein distance, which incorporates the geometry of the token space. The dual formulation of the distance expresses the regularization as penalty terms applied to the reward via optimal dual variables, which yield a tractable objective compatible with standard RL algorithms. Empirically, our method outperforms KL- and $f$-divergence-based baselines, demonstrating the benefits of semantic-aware policy distances for alignment. Our code is available at https://github.com/aailab-kaist/WPR.

cs.LG↗

arXiv2026

A Dataset and Benchmark for Robotic Cloth Unfolding Grasp Selection: The ICRA 2024 Cloth Competition

Robotic cloth manipulation suffers from a lack of standardized benchmarks and shared datasets for evaluating and comparing different approaches. To address this, we created a benchmark and organized the ICRA 2024 Cloth Competition, a unique head-to-head evaluation focused on grasp pose selection for in-air robotic cloth unfolding. Eleven diverse teams participated in the competition, utilizing our publicly released dataset of real-world robotic cloth unfolding attempts and a variety of methods to design their unfolding approaches. Afterwards, we also expanded our dataset with 176 competition evaluation trials, resulting in a dataset of 679 unfolding demonstrations across 34 garments. Analysis of the competition results revealed insights about the trade-off between grasp success and coverage, the surprisingly strong achievements of hand-engineered methods and a significant discrepancy between competition performance and prior work, underscoring the importance of independent, out-of-the-lab evaluation in robotic cloth manipulation. The associated dataset is a valuable resource for developing and evaluating grasp selection methods, particularly for learning-based approaches. We hope that our benchmark, dataset and competition results can serve as a foundation for future benchmarks and drive further progress in data-driven robotic cloth manipulation. The dataset and benchmarking code are available at https://airo.ugent.be/cloth_competition.

cs.RO↗

arXiv2025

Preference Optimization by Estimating the Ratio of the Data Distribution

Direct preference optimization (DPO) is widely used as a simple and stable method for aligning large language models (LLMs) with human preferences. This paper investigates a generalized DPO loss that enables a policy model to match the target policy from a likelihood ratio estimation perspective. The ratio of the target policy provides a unique identification of the policy distribution without relying on reward models or partition functions. This allows the generalized loss to retain both simplicity and theoretical guarantees, which prior work such as $f$-PO fails to achieve simultaneously. We propose Bregman preference optimization (BPO), a generalized framework for ratio matching that provides a family of objective functions achieving target policy optimality. BPO subsumes DPO as a special case and offers tractable forms for all instances, allowing implementation with a few lines of code. We further develop scaled Basu's power divergence (SBA), a gradient scaling method that can be used for BPO instances. The BPO framework complements other DPO variants and is applicable to target policies defined by these variants. In experiments, unlike other probabilistic loss extensions such as $f$-DPO or $f$-PO, which exhibit a trade-off between generation fidelity and diversity, instances of BPO improve both win rate and entropy compared with DPO. When applied to Llama-3-8B-Instruct, BPO achieves state-of-the-art performance among Llama-3-8B backbones, with a 55.9\% length-controlled win rate on AlpacaEval2. Project page: https://github.com/aailab-kaist/BPO.

cs.LG↗

arXiv2025

Disentangling Hyperedges through the Lens of Category Theory

Despite the promising results of disentangled representation learning in discovering latent patterns in graph-structured data, few studies have explored disentanglement for hypergraph-structured data. Integrating hyperedge disentanglement into hypergraph neural networks enables models to leverage hidden hyperedge semantics, such as unannotated relations between nodes, that are associated with labels. This paper presents an analysis of hyperedge disentanglement from a category-theoretical perspective and proposes a novel criterion for disentanglement derived from the naturality condition. Our proof-of-concept model experimentally showed the potential of the proposed criterion by successfully capturing functional relations of genes (nodes) in genetic pathways (hyperedges).

cs.LG↗

arXiv2025

Global Context-aware Representation Learning for Spatially Resolved Transcriptomics

Spatially Resolved Transcriptomics (SRT) is a cutting-edge technique that captures the spatial context of cells within tissues, enabling the study of complex biological networks. Recent graph-based methods leverage both gene expression and spatial information to identify relevant spatial domains. However, these approaches fall short in obtaining meaningful spot representations, especially for spots near spatial domain boundaries, as they heavily emphasize adjacent spots that have minimal feature differences from an anchor node. To address this, we propose Spotscape, a novel framework that introduces the Similarity Telescope module to capture global relationships between multiple spots. Additionally, we propose a similarity scaling strategy to regulate the distances between intra- and inter-slice spots, facilitating effective multi-slice integration. Extensive experiments demonstrate the superiority of Spotscape in various downstream tasks, including single-slice and multi-slice scenarios. Our code is available at the following link: https: //github.com/yunhak0/Spotscape.

cs.LG↗

arXiv2025

Autoregressive Distillation of Diffusion Transformers

Diffusion models with transformer architectures have demonstrated promising capabilities in generating high-fidelity images and scalability for high resolution. However, iterative sampling process required for synthesis is very resource-intensive. A line of work has focused on distilling solutions to probability flow ODEs into few-step student models. Nevertheless, existing methods have been limited by their reliance on the most recent denoised samples as input, rendering them susceptible to exposure bias. To address this limitation, we propose AutoRegressive Distillation (ARD), a novel approach that leverages the historical trajectory of the ODE to predict future steps. ARD offers two key benefits: 1) it mitigates exposure bias by utilizing a predicted historical trajectory that is less susceptible to accumulated errors, and 2) it leverages the previous history of the ODE trajectory as a more effective source of coarse-grained information. ARD modifies the teacher transformer architecture by adding token-wise time embedding to mark each input from the trajectory history and employs a block-wise causal attention mask for training. Furthermore, incorporating historical inputs only in lower transformer layers enhances performance and efficiency. We validate the effectiveness of ARD in a class-conditioned generation on ImageNet and T2I synthesis. Our model achieves a $5\times$ reduction in FID degradation compared to the baseline methods while requiring only 1.1\% extra FLOPs on ImageNet-256. Moreover, ARD reaches FID of 1.84 on ImageNet-256 in merely 4 steps and outperforms the publicly available 1024p text-to-image distilled models in prompt adherence score with a minimal drop in FID compared to the teacher. Project page: https://github.com/alsdudrla10/ARD.

cs.CV↗

arXiv2025

Diffusion Bridge AutoEncoders for Unsupervised Representation Learning

Diffusion-based representation learning has achieved substantial attention due to its promising capabilities in latent representation and sample generation. Recent studies have employed an auxiliary encoder to identify a corresponding representation from a sample and to adjust the dimensionality of a latent variable z. Meanwhile, this auxiliary structure invokes information split problem because the diffusion and the auxiliary encoder would divide the information from the sample into two representations for each model. Particularly, the information modeled by the diffusion becomes over-regularized because of the static prior distribution on xT. To address this problem, we introduce Diffusion Bridge AuteEncoders (DBAE), which enable z-dependent endpoint xT inference through a feed-forward architecture. This structure creates an information bottleneck at z, so xT becomes dependent on z in its generation. This results in two consequences: 1) z holds the full information of samples, and 2) xT becomes a learnable distribution, not static any further. We propose an objective function for DBAE to enable both reconstruction and generative modeling, with their theoretical justification. Empirical evidence supports the effectiveness of the intended design in DBAE, which notably enhances downstream inference quality, reconstruction, and disentanglement. Additionally, DBAE generates high-fidelity samples in the unconditional generation. Our code is available at https://github.com/aailab-kaist/DBAE.

cs.LG↗

arXiv2025

FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute

Despite their remarkable performance, modern Diffusion Transformers are hindered by substantial resource requirements during inference, stemming from the fixed and large amount of compute needed for each denoising step. In this work, we revisit the conventional static paradigm that allocates a fixed compute budget per denoising iteration and propose a dynamic strategy instead. Our simple and sample-efficient framework enables pre-trained DiT models to be converted into \emph{flexible} ones -- dubbed FlexiDiT -- allowing them to process inputs at varying compute budgets. We demonstrate how a single \emph{flexible} model can generate images without any drop in quality, while reducing the required FLOPs by more than $40$\% compared to their static counterparts, for both class-conditioned and text-conditioned image generation. Our method is general and agnostic to input and conditioning modalities. We show how our approach can be readily extended for video generation, where FlexiDiT models generate samples with up to $75$\% less compute without compromising performance.

cs.LG↗

arXiv2024

Reward-based Input Construction for Cross-document Relation Extraction

Relation extraction (RE) is a fundamental task in natural language processing, aiming to identify relations between target entities in text. While many RE methods are designed for a single sentence or document, cross-document RE has emerged to address relations across multiple long documents. Given the nature of long documents in cross-document RE, extracting document embeddings is challenging due to the length constraints of pre-trained language models. Therefore, we propose REward-based Input Construction (REIC), the first learning-based sentence selector for cross-document RE. REIC extracts sentences based on relational evidence, enabling the RE module to effectively infer relations. Since supervision of evidence sentences is generally unavailable, we train REIC using reinforcement learning with RE prediction scores as rewards. Experimental results demonstrate the superiority of our method over heuristic methods for different RE structures and backbones in cross-document RE. Our code is publicly available at https://github.com/aailabkaist/REIC.

cs.CL↗

arXiv2024

Diffusion Rejection Sampling

Recent advances in powerful pre-trained diffusion models encourage the development of methods to improve the sampling performance under well-trained diffusion models. This paper introduces Diffusion Rejection Sampling (DiffRS), which uses a rejection sampling scheme that aligns the sampling transition kernels with the true ones at each timestep. The proposed method can be viewed as a mechanism that evaluates the quality of samples at each intermediate timestep and refines them with varying effort depending on the sample. Theoretical analysis shows that DiffRS can achieve a tighter bound on sampling error compared to pre-trained models. Empirical results demonstrate the state-of-the-art performance of DiffRS on the benchmark datasets and the effectiveness of DiffRS for fast diffusion samplers and large-scale text-to-image diffusion models. Our code is available at https://github.com/aailabkaist/DiffRS.

cs.LG↗

arXiv2024

Training Unbiased Diffusion Models From Biased Dataset

With significant advancements in diffusion models, addressing the potential risks of dataset bias becomes increasingly important. Since generated outputs directly suffer from dataset bias, mitigating latent bias becomes a key factor in improving sample quality and proportion. This paper proposes time-dependent importance reweighting to mitigate the bias for the diffusion models. We demonstrate that the time-dependent density ratio becomes more precise than previous approaches, thereby minimizing error propagation in generative learning. While directly applying it to score-matching is intractable, we discover that using the time-dependent density ratio both for reweighting and score correction can lead to a tractable form of the objective function to regenerate the unbiased data density. Furthermore, we theoretically establish a connection with traditional score-matching, and we demonstrate its convergence to an unbiased distribution. The experimental evidence supports the usefulness of the proposed method, which outperforms baselines including time-independent importance reweighting on CIFAR-10, CIFAR-100, FFHQ, and CelebA with various bias settings. Our code is available at https://github.com/alsdudrla10/TIW-DSM.

cs.LG↗

arXiv2024

Label-Noise Robust Diffusion Models

Conditional diffusion models have shown remarkable performance in various generative tasks, but training them requires large-scale datasets that often contain noise in conditional inputs, a.k.a. noisy labels. This noise leads to condition mismatch and quality degradation of generated data. This paper proposes Transition-aware weighted Denoising Score Matching (TDSM) for training conditional diffusion models with noisy labels, which is the first study in the line of diffusion models. The TDSM objective contains a weighted sum of score networks, incorporating instance-wise and time-dependent label transition probabilities. We introduce a transition-aware weight estimator, which leverages a time-dependent noisy-label classifier distinctively customized to the diffusion process. Through experiments across various datasets and noisy label settings, TDSM improves the quality of generated samples aligned with given conditions. Furthermore, our method improves generation performance even on prevalent benchmark datasets, which implies the potential noisy labels and their risk of generative model learning. Finally, we show the improved performance of TDSM on top of conventional noisy label corrections, which empirically proving its contribution as a part of label-noise robust generative models. Our code is available at: https://github.com/byeonghu-na/tdsm.

cs.LG↗

arXiv2023

Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models

The proposed method, Discriminator Guidance, aims to improve sample generation of pre-trained diffusion models. The approach introduces a discriminator that gives explicit supervision to a denoising sample path whether it is realistic or not. Unlike GANs, our approach does not require joint training of score and discriminator networks. Instead, we train the discriminator after score training, making discriminator training stable and fast to converge. In sample generation, we add an auxiliary term to the pre-trained score to deceive the discriminator. This term corrects the model score to the data score at the optimal discriminator, which implies that the discriminator helps better score estimation in a complementary way. Using our algorithm, we achive state-of-the-art results on ImageNet 256x256 with FID 1.83 and recall 0.64, similar to the validation data's FID (1.68) and recall (0.66). We release the code at https://github.com/alsdudrla10/DG.

cs.CV↗

arXiv2022

AltUB: Alternating Training Method to Update Base Distribution of Normalizing Flow for Anomaly Detection

Unsupervised anomaly detection is coming into the spotlight these days in various practical domains due to the limited amount of anomaly data. One of the major approaches for it is a normalizing flow which pursues the invertible transformation of a complex distribution as images into an easy distribution as N(0, I). In fact, algorithms based on normalizing flow like FastFlow and CFLOW-AD establish state-of-the-art performance on unsupervised anomaly detection tasks. Nevertheless, we investigate these algorithms convert normal images into not N(0, I) as their destination, but an arbitrary normal distribution. Moreover, their performances are often unstable, which is highly critical for unsupervised tasks because data for validation are not provided. To break through these observations, we propose a simple solution AltUB which introduces alternating training to update the base distribution of normalizing flow for anomaly detection. AltUB effectively improves the stability of performance of normalizing flow. Furthermore, our method achieves the new state-of-the-art performance of the anomaly segmentation task on the MVTec AD dataset with 98.8% AUROC.

cs.LG↗