arXiv subjects

Taehwan Kim

Publications and source records attributed to Taehwan Kim.

At least 19 recordsLinked to original sources

arXiv2026

Agentic Neural Architecture Search

Neural architecture search (NAS) methods have grown increasingly efficient, yet they remain bounded by manually engineered search spaces that require substantial domain expertise and must be rebuilt for every new task. Large language models (LLMs) can generate architectures in an open-ended space, but how to optimally divide the labor between LLM-driven design and NAS-driven search remains unexplored. We propose a mechanism that bridges these two paradigms: an LLM produces a high-quality seed architecture, then decomposes it into a "slotted architecture", a scaffold with named, interchangeable module slots that automatically defines a bounded, task-specific search space for conventional NAS to explore, without manual engineering. We instantiate this mechanism in AgentNAS, a modular three-phase pipeline in which each component's contribution can be measured independently. On 17 tasks spanning classification, dense regression, segmentation, and multi-label tagging across diverse modalities (NAS-Bench-360 and Unseen NAS), AgentNAS establishes a new state of the art on 11 tasks, outperforming published baselines including task-specific expert designs. Ablation studies show that the two search mechanisms are broadly complementary: the LLM-generated seed already surpasses published baselines on the majority of tasks, and NAS delivers additional gains in most cases through combinatorial recombination across slots, a mode of search that independent LLM samples cannot replicate. These patterns hold across three LLMs of different capability levels, confirming that the division of labor is robust. Our code is available at https://github.com/alroimfebruary/AgentNAS.

cs.AI↗

arXiv2026

SVHighlights: Towards Extremely Long Sport Video Highlight Detection

While highlight detection for long-form videos is of great practical importance, most existing methods remain limited to short-form content, largely due to the absence of a suitable benchmark. To bridge this gap, we introduce SVHighlights, to the best of our knowledge, the first benchmark for highlight detection in extremely long sports videos, each exceeding one hour in duration, across multiple sports categories. SVHighlights is constructed from pairs of full-length sports videos and their corresponding official highlight videos using a dataset generation pipeline, enabling scalable label generation without conventional per-clip saliency annotation. The benchmark comprises 320 videos with an average duration of 2.00 hours and a total of 640.18 hours, substantially exceeding previous datasets. Existing methods also face fundamental challenges on long videos: models trained on short clips fail to generalize to hour-long content, and their clip-level scoring lacks the broader context needed to identify highlights. To address this and provide a strong baseline, we present TF-SELECTOR, a training-free segment-based approach that divides each video into context-aware segments by merging adjacent shots sharing the same semantic content, and predicts segment-level saliency scores using a large language model with multimodal inputs including visual captions, transcripts, and audio volume. Experiments demonstrate that TF-SELECTOR achieves superior performance across most metrics compared to Video Temporal Grounding (VTG)-tuned baselines, with improvements of +2.50 in HIT@1, +4.04 in HIT@K, and +2.95 in IoU. These results establish SVHighlights as a challenging testbed for long-form highlight detection and demonstrate that a simple segment-based strategy can effectively scale to hour-long videos.

cs.CV↗

arXiv2026

Totoro$^+$: An Adaptive and Scalable Edge Federated Learning System

Federated Learning (FL) is an emerging distributed machine learning (ML) technique that enables in-situ model training and inference on decentralized edge devices. We propose Totoro$^+$, a novel scalable FL system that enables massive FL applications to run simultaneously on edge networks. The key insight is to explore a distributed hash table (DHT)-based peer-to-peer (P2P) model to re-architect the centralized FL system design into a fully decentralized one. In contrast to previous studies where many FL applications shared one centralized parameter server, Totoro$^+$ assigns a dedicated parameter server to each application. Any edge node can act as any application's coordinator, aggregator, client selector, worker (participant device), or any combination of the above, thereby radically improving scalability and adaptivity. Totoro$^+$ introduces three innovations to realize its design: a locality-aware P2P multi-ring structure, a publish/subscribe-based forest abstraction, and a game-theoretic path planning model with a guarantee of an $\epsilon$-approximate Nash equilibrium. Real-world experiments on 500 Amazon EC2 servers show that Totoro$^+$ scales gracefully with the number of FL applications and $N$ edge nodes speeds up the total training time by $1.2\times-14.0\times$, achieves $\mathcal{O}(\log N)$ hops for model dissemination and gradient aggregation with millions of nodes, and efficiently adapts to the practical edge networks and churns.

cs.DC↗

arXiv2026

Environmental Understanding Vision-Language Model for Embodied Agent

Vision-language models (VLMs) have shown strong perception and reasoning abilities for instruction-following embodied agents. However, despite these abilities and their generalization performance, they still face limitations in environmental understanding, often failing on interactions or relying on environment metadata during execution. To address this challenge, we propose a novel framework named Environmental Understanding Embodied Agent (EUEA), which fine-tunes four core skills: 1) object perception for identifying relevant objects, 2) task planning for generating interaction subgoals, 3) action understanding for judging success likelihood, and 4) goal recognition for determining goal completion. By fine-tuning VLMs with EUEA skills, our framework enables more reliable task execution for instruction-following. We further introduce a recovery step that leverages these core skills and a group relative policy optimization (GRPO) stage that refines inconsistent skill predictions. The recovery step samples alternative actions to correct failure cases, and the GRPO stage refines inconsistent skill predictions. Across ALFRED tasks, our VLM significantly outperforms a behavior-cloning baseline, achieving an 8.86% improvement in average success rate. The recovery and GRPO stages provide an additional 3.03% gain, further enhancing overall performance. Finally, our skill-level analyses reveal key limitations in the environmental understanding of closed- and open-source VLMs and identify the capabilities necessary for effective agent-environment interaction.

cs.CV↗

arXiv2026

Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Video

Talking face generation has gained significant attention as a core application of generative models. To enhance the expressiveness and realism of synthesized videos, emotion editing in talking face video plays a crucial role. However, existing approaches often limit expressive flexibility and struggle to generate extended emotions. Label-based methods represent emotions with discrete categories, which fail to capture a wide range of emotions. Audio-based methods can leverage emotionally rich speech signals - and even benefit from expressive text-to-speech (TTS) synthesis - but they fail to express the target emotions because emotions and linguistic contents are entangled in emotional speeches. Images-based methods, on the other hand, rely on target reference images to guide emotion transfer, yet they require high-quality frontal views and face challenges in acquiring reference data for extended emotions (e.g., sarcasm). To address these limitations, we propose Cross-Modal Emotion Transfer (C-MET), a novel approach that generates facial expressions based on speeches by modeling emotion semantic vectors between speech and visual feature spaces. C-MET leverages a large-scale pretrained audio encoder and a disentangled facial expression encoder to learn emotion semantic vectors that represent the difference between two different emotional embeddings across modalities. Extensive experiments on the MEAD and CREMA-D datasets demonstrate that our method improves emotion accuracy by 14% over state-of-the-art methods, while generating expressive talking face videos - even for unseen extended emotions. Code, checkpoint, and demo are available at https://chanhyeok-choi.github.io/C-MET/

cs.CV↗

arXiv2026

Sentence Curve Language Models

Language models (LMs) are a central component of modern AI systems, and diffusion language models (DLMs) have recently emerged as a competitive alternative. Both paradigms rely on word embeddings not only to represent the input sentence, but also to represent the target sentence that backbone models are trained to predict. We argue that such static embedding of the target word is insensitive to neighboring words, encouraging locally accurate word prediction while global sentence structure is less emphasized. To address this, we propose a continuous sentence representation, termed sentence curve, defined as a spline curve whose control points affect multiple words in the sentence. Based on this representation, we introduce sentence curve language model (SCLM), which extends DLMs to predict sentence curves instead of the static word embeddings. We theoretically show that sentence curve prediction induces a regularization effect that promotes global structure modeling, and characterize how different sentence curve types affect this behavior. Empirically, SCLM achieves state-of-the-art performance among DLMs on IWSLT14 and WMT14, shows stable training without burdensome knowledge distillation, and demonstrates promising potential compared to discrete DLMs on LM1B.

cs.CL↗

arXiv2025

V-Warper: Appearance-Consistent Video Diffusion Personalization via Value Warping

Video personalization aims to generate videos that faithfully reflect a user-provided subject while following a text prompt. However, existing approaches often rely on heavy video-based finetuning or large-scale video datasets, which impose substantial computational cost and are difficult to scale. Furthermore, they still struggle to maintain fine-grained appearance consistency across frames. To address these limitations, we introduce V-Warper, a training-free coarse-to-fine personalization framework for transformer-based video diffusion models. The framework enhances fine-grained identity fidelity without requiring any additional video training. (1) A lightweight coarse appearance adaptation stage leverages only a small set of reference images, which are already required for the task. This step encodes global subject identity through image-only LoRA and subject-embedding adaptation. (2) A inference-time fine appearance injection stage refines visual fidelity by computing semantic correspondences from RoPE-free mid-layer query--key features. These correspondences guide the warping of appearance-rich value representations into semantically aligned regions of the generation process, with masking ensuring spatial reliability. V-Warper significantly improves appearance fidelity while preserving prompt alignment and motion dynamics, and it achieves these gains efficiently without large-scale video finetuning.

cs.CV↗

arXiv2025

Data Descriptions from Large Language Models with Influence Estimation

Deep learning models have been successful in many areas but understanding their behaviors still remains a black-box. Most prior explainable AI (XAI) approaches have focused on interpreting and explaining how models make predictions. In contrast, we would like to understand how data can be explained with deep learning model training and propose a novel approach to understand the data via one of the most common media - language - so that humans can easily understand. Our approach proposes a pipeline to generate textual descriptions that can explain the data with large language models by incorporating external knowledge bases. However, generated data descriptions may still include irrelevant information, so we introduce to exploit influence estimation to choose the most informative textual descriptions, along with the CLIP score. Furthermore, based on the phenomenon of cross-modal transferability, we propose a novel benchmark task named cross-modal transfer classification to examine the effectiveness of our textual descriptions. In the experiment of zero-shot setting, we show that our textual descriptions are more effective than other baseline descriptions, and furthermore, we successfully boost the performance of the model trained only on images across all nine image classification datasets. These results are further supported by evaluation using GPT-4o. Through our approach, we may gain insights into the inherent interpretability of the decision-making process of the model.

cs.AI↗

arXiv2025

VEHME: A Vision-Language Model For Evaluating Handwritten Mathematics Expressions

Automatically assessing handwritten mathematical solutions is an important problem in educational technology with practical applications, but it remains a significant challenge due to the diverse formats, unstructured layouts, and symbolic complexity of student work. To address this challenge, we introduce VEHME-a Vision-Language Model for Evaluating Handwritten Mathematics Expressions-designed to assess open-form handwritten math responses with high accuracy and interpretable reasoning traces. VEHME integrates a two-phase training pipeline: (i) supervised fine-tuning using structured reasoning data, and (ii) reinforcement learning that aligns model outputs with multi-dimensional grading objectives, including correctness, reasoning depth, and error localization. To enhance spatial understanding, we propose an Expression-Aware Visual Prompting Module, trained on our synthesized multi-line math expressions dataset to robustly guide attention in visually heterogeneous inputs. Evaluated on AIHub and FERMAT datasets, VEHME achieves state-of-the-art performance among open-source models and approaches the accuracy of proprietary systems, demonstrating its potential as a scalable and accessible tool for automated math assessment. Our training and experiment code is publicly available at our GitHub repository.

cs.CL↗

arXiv2025

Grouped Differential Attention

The self-attention mechanism, while foundational to modern Transformer architectures, suffers from a critical inefficiency: it frequently allocates substantial attention to redundant or noisy context. Differential Attention addressed this by using subtractive attention maps for signal and noise, but its required balanced head allocation imposes rigid constraints on representational flexibility and scalability. To overcome this, we propose Grouped Differential Attention (GDA), a novel approach that introduces unbalanced head allocation between signal-preserving and noise-control groups. GDA significantly enhances signal focus by strategically assigning more heads to signal extraction and fewer to noise-control, stabilizing the latter through controlled repetition (akin to GQA). This design achieves stronger signal fidelity with minimal computational overhead. We further extend this principle to group-differentiated growth, a scalable strategy that selectively replicates only the signal-focused heads, thereby ensuring efficient capacity expansion. Through large-scale pretraining and continual training experiments, we demonstrate that moderate imbalance ratios in GDA yield substantial improvements in generalization and stability compared to symmetric baselines. Our results collectively establish that ratio-aware head allocation and selective expansion offer an effective and practical path toward designing scalable, computation-efficient Transformer architectures.

cs.LG↗

arXiv2025

Towards Human-like Multimodal Conversational Agent by Generating Engaging Speech

Human conversation involves language, speech, and visual cues, with each medium providing complementary information. For instance, speech conveys a vibe or tone not fully captured by text alone. While multimodal LLMs focus on generating text responses from diverse inputs, less attention has been paid to generating natural and engaging speech. We propose a human-like agent that generates speech responses based on conversation mood and responsive style information. To achieve this, we build a novel MultiSensory Conversation dataset focused on speech to enable agents to generate natural speech. We then propose a multimodal LLM-based model for generating text responses and voice descriptions, which are used to generate speech covering paralinguistic information. Experimental results demonstrate the effectiveness of utilizing both visual and audio modalities in conversation to generate engaging speech. The source code is available in https://github.com/kimtaesu24/MSenC

cs.HC↗

arXiv2025

MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning

Systems such as video chatbots and navigation robots often depend on streaming image captioning to interpret visual inputs. Existing approaches typically employ large multimodal language models (MLLMs) for this purpose, but their substantial computational cost hinders practical application. This limitation motivates our development of a lightweight captioning model. Our investigation begins by replacing the large-scale language component in MLLMs with a compact 125M-parameter model. Surprisingly, this compact model, despite a 93x reduction in size, achieves comparable performance to MLLMs, suggesting that factual image captioning does not significantly require the complex reasoning abilities of LLMs. Despite this promising result, our lightweight model still lacks reliability. To address this, we draw inspiration from the human visual process: perceiving a global and coarse understanding of the scene before attending to finer details. Accordingly, we propose a multimodal self-refinement framework that guides the model to utilize features from salient regions, identified by referencing the previous coarse caption, and to produce a refined description. Experimental results demonstrate the superiority of our model in both single-sentence and detailed captioning, extending even to long-range video QA tasks.

cs.CV↗

arXiv2025

Audio-Guided Visual Editing with Complex Multi-Modal Prompts

Visual editing with diffusion models has made significant progress but often struggles with complex scenarios that textual guidance alone could not adequately describe, highlighting the need for additional non-text editing prompts. In this work, we introduce a novel audio-guided visual editing framework that can handle complex editing tasks with multiple text and audio prompts without requiring additional training. Existing audio-guided visual editing methods often necessitate training on specific datasets to align audio with text, limiting their generalization to real-world situations. We leverage a pre-trained multi-modal encoder with strong zero-shot capabilities and integrate diverse audio into visual editing tasks, by alleviating the discrepancy between the audio encoder space and the diffusion model's prompt encoder space. Additionally, we propose a novel approach to handle complex scenarios with multiple and multi-modal editing prompts through our separate noise branching and adaptive patch selection. Our comprehensive experiments on diverse editing tasks demonstrate that our framework excels in handling complicated editing scenarios by incorporating rich information from audio, where text-only approaches fail.

cs.CV↗

arXiv2025

Motif 2.6B Technical Report

Recent advancements in Large Language Models (LLMs) have revolutionized artificial intelligence, yet developing an effective foundational LLM that balances high performance with computational efficiency remains challenging, especially for emerging research groups. To address this gap, we introduce Motif-2.6B, a 2.6-billion-parameter foundation model designed to democratize advanced LLM capabilities. Motif-2.6B incorporates several innovative architectural enhancements, including Differential Attention and PolyNorm activation functions, which improve long-context comprehension, reduce hallucination, and enhance in-context learning capabilities. We rigorously tested multiple novel architectural components through extensive experimentation to determine the optimal architecture for Motif-2.6B. Comprehensive evaluations demonstrate that Motif-2.6B consistently meets or exceeds the performance of similarly sized state-of-the-art models across diverse benchmarks, showcasing its effectiveness, scalability, and real-world applicability. Through detailed experiments and tailored techniques, Motif-2.6B significantly advances the landscape of efficient, scalable, and powerful foundational LLMs, offering valuable insights and a robust foundation for future research and deployment.

cs.LG↗

arXiv2025

Semi-Supervised Audio-Visual Video Action Recognition with Audio Source Localization Guided Mixup

Video action recognition is a challenging but important task for understanding and discovering what the video does. However, acquiring annotations for a video is costly, and semi-supervised learning (SSL) has been studied to improve performance even with a small number of labeled data in the task. Prior studies for semi-supervised video action recognition have mostly focused on using single modality - visuals - but the video is multi-modal, so utilizing both visuals and audio would be desirable and improve performance further, which has not been explored well. Therefore, we propose audio-visual SSL for video action recognition, which uses both visual and audio together, even with quite a few labeled data, which is challenging. In addition, to maximize the information of audio and video, we propose a novel audio source localization-guided mixup method that considers inter-modal relations between video and audio modalities. In experiments on UCF-51, Kinetics-400, and VGGSound datasets, our model shows the superior performance of the proposed semi-supervised audio-visual action recognition framework and audio source localization-guided mixup.

cs.CV↗

arXiv2025

RingFormer: Rethinking Recurrent Transformer with Adaptive Level Signals

Transformers have achieved great success in effectively processing sequential data such as text. Their architecture consisting of several attention and feedforward blocks can model relations between elements of a sequence in parallel manner, which makes them very efficient to train and effective in sequence modeling. Even though they have shown strong performance in processing sequential data, the size of their parameters is considerably larger when compared to other architectures such as RNN and CNN based models. Therefore, several approaches have explored parameter sharing and recurrence in Transformer models to address their computational demands. However, such methods struggle to maintain high performance compared to the original transformer model. To address this challenge, we propose our novel approach, RingFormer, which employs one Transformer layer that processes input repeatedly in a circular, ring-like manner, while utilizing low-rank matrices to generate input-dependent level signals. This allows us to reduce the model parameters substantially while maintaining high performance in a variety of tasks such as translation and image classification, as validated in the experiments.

cs.LG↗

arXiv2025

DiffListener: Discrete Diffusion Model for Listener Generation

The listener head generation (LHG) task aims to generate natural nonverbal listener responses based on the speaker's multimodal cues. While prior work either rely on limited modalities (e.g. audio and facial information) or employ autoregressive approaches which have limitations such as accumulating prediction errors. To address these limitations, we propose DiffListener, a discrete diffusion based approach for non-autoregressive listener head generation. Our model takes the speaker's facial information, audio, and text as inputs, additionally incorporating facial differential information to represent the temporal dynamics of expressions and movements. With this explicit modeling of facial dynamics, DiffListener can generate coherent reaction sequences in a non-autoregressive manner. Through comprehensive experiments, DiffListener demonstrates state-of-the-art performance in both quantitative and qualitative evaluations. The user study shows that DiffListener generates natural context-aware listener reactions that are well synchronized with the speaker. The code and demo videos are available in https://siyeoljung.github.io/DiffListener

cs.LG↗

arXiv2025

Multi-aspect Knowledge Distillation with Large Language Model

Recent advancements in deep learning have significantly improved performance on computer vision tasks. Previous image classification methods primarily modify model architectures or add features, and they optimize models using cross-entropy loss on class logits. Since they focus on classifying images with considering class labels, these methods may struggle to learn various \emph{aspects} of classes (e.g., natural positions and shape changes). Rethinking the previous approach from a novel view, we propose a multi-aspect knowledge distillation method using Multimodal Large Language Models (MLLMs). Our approach involves: 1) querying Large Language Model with multi-aspect questions relevant to the knowledge we want to transfer to the model, 2) extracting corresponding logits from MLLM, and 3) expanding the model's output dimensions to distill these multi-aspect logits. We then apply cross-entropy loss to class logits and binary cross-entropy loss to multi-aspect logits. Through our method, the model can learn not only the knowledge about visual aspects but also the abstract and complex aspects that require a deeper understanding. We primarily apply our method to image classification, and to explore the potential for extending our model, such as object detection. In all experimental results, our method improves the performance of the baselines. Additionally, we analyze the effect of multi-aspect knowledge distillation. These results demonstrate that our method can transfer knowledge about various aspects to the model and the aspect knowledge can enhance model performance in computer vision tasks.

cs.CV↗