arXiv subjects

Jiyoung Lee

Publications and source records attributed to Jiyoung Lee.

At least 19 recordsLinked to original sources

arXiv2026

Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs

Touch supplies the physical grounding needed to perceive intrinsic material properties, such as friction and compliance, that vision alone often cannot resolve. Recent efforts for equipping multimodal LLMs with this tactile sense, however, expose a zero-sum trade-off: the limited parameter budget of compact models forces a choice between acquiring the new sensory modality and preserving the established vision-language reasoning. We present Splash, a mask-isolated tactile alignment learning framework for MLLMs. Splash quantifies the significance of each pretrained parameter, and partitions the parameter space into a dormant and critical subspace. While the frozen critical subspace acts as a stable anchor to safeguard general visual knowledge, Splash updates the isolated dormant subspace to internalize tactile alignment towards LLMs. This selective, non-destructive expansion effectively prevents catastrophic forgetting and ensures non-destructive modality expansion. Extensive experiments show that Splash effectively achieves tactile reasoning without additional inference overhead in the LLM part, demonstrating state-of-the-art performance on visuo-tactile benchmarks, including SSVTP, TVL, and TacQuad, while preserving its original general-purpose capabilities.

cs.CV↗

arXiv2026

V-LynX: Token Interface Alignment for Video+X LLMs

This study introduces an intriguing phenomenon in Video LLMs: rather than merely translating frames into textual embeddings, Video LLMs establish a continuous manifold, token interface, allowing visual tokens to operate as standalone entities within the architecture. Exploiting this discovery, we propose V-LynX, a scalable framework that integrates novel modalities into Video LLMs by repurposing the internalized interface. Departing from conventional paradigms that necessitate heavy modality-specific encoders or paired supervision, V-LynX employs a lightweight auxiliary pathway in parallel with the frozen vision encoder. Our method integrates new sensory inputs with intrinsic video priors by aligning both attention responses and statistical distributions using unpaired unimodal data sets. This ensures manifold compatibility while preserving the integrity of the Video LLMs. Extensive benchmarks demonstrate that V-LynX achieves SOTA and efficiency across audio-visual QA, 3D reasoning, high-frame-rate, and multi-view video understanding. The code is available at https://github.com/park-jungin/lynx.

cs.CV↗

arXiv2026

Saliency-Aware Model Merging

Model merging aims to consolidate multiple task-specific models fine-tuned on different datasets into a unified architecture that performs cross-domain proficiency. Current data-free model merging methods often struggle to scale as they rely on simple parameter-level heuristics that ignore inter-layer dependencies and non-uniform distribution of expertise. This work proposes SA-Merging, which is built upon connectivity-based saliency formulations from structural pruning (e.g., SynFlow) and extends them to the data-free model merging setting. We define a saliency score over task vectors relative to a shared base model, and further introduce merge-aware modulation that incorporates agreement across experts to mitigate task interference. Based on this formulation, an iterative saliency-aware merging procedure progressively removes non-informative updates while preserving end-to-end connectivity. Furthermore, we extend SA-Merging to introduce rank-wise saliency decomposition for LoRAs without compromising their structural integrity. Extensive experiments on vision and language tasks demonstrate the effectiveness of our saliency-based approach, further reducing the gap between data-free and test-time adaptation methods.

cs.LG↗

arXiv2026

EXAONE 4.5 Technical Report

This technical report introduces EXAONE 4.5, the first open-weight vision language model released by LG AI Research. EXAONE 4.5 is architected by integrating a dedicated visual encoder into the existing EXAONE 4.0 framework, enabling native multimodal pretraining over both visual and textual modalities. The model is trained on large-scale data with careful curation, particularly emphasizing document-centric corpora that align with LG's strategic application domains. This targeted data design enables substantial performance gains in document understanding and related tasks, while also delivering broad improvements across general language capabilities. EXAONE 4.5 extends context length up to 256K tokens, facilitating long-context reasoning and enterprise-scale use cases. Comparative evaluations demonstrate that EXAONE 4.5 achieves competitive performance in general benchmarks while outperforming state-of-the-art models of similar scale in document understanding and Korean contextual reasoning. As part of LG's ongoing effort toward practical industrial deployment, EXAONE 4.5 is designed to be continuously extended with additional domains and application scenarios to advance AI for a better life.

cs.CL↗

arXiv2026

Erasing Your Voice Before It's Heard: Training-free Speaker Unlearning for Zero-shot Text-to-Speech

Modern zero-shot text-to-speech (TTS) models offer unprecedented expressivity but also pose serious crime risks, as they can synthesize voices of individuals who never consented. In this context, speaker unlearning aims to prevent the generation of specific speaker identities upon request. Existing approaches, reliant on retraining, are costly and limited to speakers seen in the training set. We present TruS, a training-free speaker unlearning framework that shifts the paradigm from data deletion to inference-time control. TruS steers identity-specific hidden activations to suppress target speakers while preserving other attributes (e.g., prosody and emotion). Experimental results show that TruS effectively prevents voice generation on both seen and unseen opt-out speakers, establishing a scalable safeguard for speech synthesis. The demo and code are available on http://mmai.ewha.ac.kr/trus.

eess.AS↗

arXiv2026

K-EXAONE Technical Report

This technical report presents K-EXAONE, a large-scale multilingual language model developed by LG AI Research. K-EXAONE is built on a Mixture-of-Experts architecture with 236B total parameters, activating 23B parameters during inference. It supports a 256K-token context window and covers six languages: Korean, English, Spanish, German, Japanese, and Vietnamese. We evaluate K-EXAONE on a comprehensive benchmark suite spanning reasoning, agentic, general, Korean, and multilingual abilities. Across these evaluations, K-EXAONE demonstrates performance comparable to open-weight models of similar size. K-EXAONE, designed to advance AI for a better life, is positioned as a powerful proprietary AI foundation model for a wide range of industrial and research applications.

cs.CL↗

arXiv2025

Hear What Matters! Text-conditioned Selective Video-to-Audio Generation

This work introduces a new task, text-conditioned selective video-to-audio (V2A) generation, which produces only the user-intended sound from a multi-object video. This capability is especially crucial in multimedia production, where audio tracks are handled individually for each sound source for precise editing, mixing, and creative control. We propose SELVA, a novel text-conditioned V2A model that treats the text prompt as an explicit selector to distinctly extract prompt-relevant sound-source visual features from the video encoder. To suppress text-irrelevant activations with efficient video encoder finetuning, the proposed supplementary tokens promote cross-attention to yield robust semantic and temporal grounding. SELVA further employs an autonomous video-mixing scheme in a self-supervised manner to overcome the lack of mono audio track supervision. We evaluate SELVA on VGG-MONOAUDIO, a curated benchmark of clean single-source videos for such a task. Extensive experiments and ablations consistently verify its effectiveness across audio quality, semantic alignment, and temporal synchronization.

cs.CV↗

arXiv2025

CountSteer: Steering Attention for Object Counting in Diffusion Models

Text-to-image diffusion models generate realistic and coherent images but often fail to follow numerical instructions in text, revealing a gap between language and visual representation. Interestingly, we found that these models are not entirely blind to numbers-they are implicitly aware of their own counting accuracy, as their internal signals shift in consistent ways depending on whether the output meets the specified count. This observation suggests that the model already encodes a latent notion of numerical correctness, which can be harnessed to guide generation more precisely. Building on this intuition, we introduce CountSteer, a training-free method that improves generation of specified object counts by steering the model's cross-attention hidden states during inference. In our experiments, CountSteer improved object-count accuracy by about 4% without compromising visual quality, demonstrating a simple yet effective step toward more controllable and semantically reliable text-to-image generation.

cs.CV↗

arXiv2025

Seeing What You Say: Expressive Image Generation from Speech

This paper proposes VoxStudio, the first unified and end-to-end speech-to-image model that generates expressive images directly from spoken descriptions by jointly aligning linguistic and paralinguistic information. At its core is a speech information bottleneck (SIB) module, which compresses raw speech into compact semantic tokens, preserving prosody and emotional nuance. By operating directly on these tokens, VoxStudio eliminates the need for an additional speech-to-text system, which often ignores the hidden details beyond text, e.g., tone or emotion. We also release VoxEmoset, a large-scale paired emotional speech-image dataset built via an advanced TTS engine to affordably generate richly expressive utterances. Comprehensive experiments on the SpokenCOCO, Flickr8kAudio, and VoxEmoset benchmarks demonstrate the feasibility of our method and highlight key challenges, including emotional consistency and linguistic ambiguity, paving the way for future research.

eess.AS↗

arXiv2025

Referee: Reference-aware Audiovisual Deepfake Detection

Deepfakes generated by advanced generative models have rapidly posed serious threats, yet existing audiovisual deepfake detection approaches struggle to generalize to unseen manipulation methods. To address this, we propose a novel reference-aware audiovisual deepfake detection method, called Referee to capture fine-grained identity discrepancies. Unlike existing methods that overfit to transient spatiotemporal artifacts, Referee employs identity bottleneck and matching modules to model the relational consistency of speaker-specific cues captured by a single one-shot example as a biometric anchor. Extensive experiments on FakeAVCeleb, FaceForensics++, and KoDF demonstrate that Referee achieves state-of-the-art results on cross-dataset and cross-language evaluation protocols, including a 99.4% AUC on KoDF. These results highlight that explicitly correlating reference-based biometric priors is a key frontier for achieving generalized and reliable audiovisual forensics. The code is available at https://github.com/ewha-mmai/referee.

cs.CV↗

arXiv2025

TwinShift: Benchmarking Audio Deepfake Detection across Synthesizer and Speaker Shifts

Audio deepfakes pose a growing threat, already exploited in fraud and misinformation. A key challenge is ensuring detectors remain robust to unseen synthesis methods and diverse speakers, since generation techniques evolve quickly. Despite strong benchmark results, current systems struggle to generalize to new conditions limiting real-world reliability. To address this, we introduce TWINSHIFT, a benchmark explicitly designed to evaluate detection robustness under strictly unseen conditions. Our benchmark is constructed from six different synthesis systems, each paired with disjoint sets of speakers, allowing for a rigorous assessment of how well detectors generalize when both the generative model and the speaker identity change. Through extensive experiments, we show that TWINSHIFT reveals important robustness gaps, uncover overlooked limitations, and provide principled guidance for developing ADD systems. The TWINSHIFT benchmark can be accessed at https://github.com/intheMeantime/TWINSHIFT.

cs.SD↗

arXiv2025

Learning What To Hear: Boosting Sound-Source Association For Robust Audiovisual Instance Segmentation

Audiovisual instance segmentation (AVIS) requires accurately localizing and tracking sounding objects throughout video sequences. Existing methods suffer from visual bias stemming from two fundamental issues: uniform additive fusion prevents queries from specializing to different sound sources, while visual-only training objectives allow queries to converge to arbitrary salient objects. We propose Audio-Centric Query Generation using cross-attention, enabling each query to selectively attend to distinct sound sources and carry sound-specific priors into visual decoding. Additionally, we introduce Sound-Aware Ordinal Counting (SAOC) loss that explicitly supervises sounding object numbers through ordinal regression with monotonic consistency constraints, preventing visual-only convergence during training. Experiments on AVISeg benchmark demonstrate consistent improvements: +1.64 mAP, +0.6 HOTA, and +2.06 FSLA, validating that query specialization and explicit counting supervision are crucial for accurate audiovisual instance segmentation.

eess.AS↗

arXiv2025

Language-guided Recursive Spatiotemporal Graph Modeling for Video Summarization

Video summarization aims to select keyframes that are visually diverse and can represent the whole story of a given video. Previous approaches have focused on global interlinkability between frames in a video by temporal modeling. However, fine-grained visual entities, such as objects, are also highly related to the main content of the video. Moreover, language-guided video summarization, which has recently been studied, requires a comprehensive linguistic understanding of complex real-world videos. To consider how all the objects are semantically related to each other, this paper regards video summarization as a language-guided spatiotemporal graph modeling problem. We present recursive spatiotemporal graph networks, called VideoGraph, which formulate the objects and frames as nodes of the spatial and temporal graphs, respectively. The nodes in each graph are connected and aggregated with graph edges, representing the semantic relationships between the nodes. To prevent the edges from being configured with visual similarity, we incorporate language queries derived from the video into the graph node representations, enabling them to contain semantic knowledge. In addition, we adopt a recursive strategy to refine initial graphs and correctly classify each frame node as a keyframe. In our experiments, VideoGraph achieves state-of-the-art performance on several benchmarks for generic and query-focused video summarization in both supervised and unsupervised manners. The code is available at https://github.com/park-jungin/videograph.

cs.CV↗

arXiv2025

Trans-EnV: A Framework for Evaluating the Linguistic Robustness of LLMs Against English Varieties

Large Language Models (LLMs) are predominantly evaluated on Standard American English (SAE), often overlooking the diversity of global English varieties. This narrow focus may raise fairness concerns as degraded performance on non-standard varieties can lead to unequal benefits for users worldwide. Therefore, it is critical to extensively evaluate the linguistic robustness of LLMs on multiple non-standard English varieties. We introduce Trans-EnV, a framework that automatically transforms SAE datasets into multiple English varieties to evaluate the linguistic robustness. Our framework combines (1) linguistics expert knowledge to curate variety-specific features and transformation guidelines from linguistic literature and corpora, and (2) LLM-based transformations to ensure both linguistic validity and scalability. Using Trans-EnV, we transform six benchmark datasets into 38 English varieties and evaluate seven state-of-the-art LLMs. Our results reveal significant performance disparities, with accuracy decreasing by up to 46.3% on non-standard varieties. These findings highlight the importance of comprehensive linguistic robustness evaluation across diverse English varieties. Each construction of Trans-EnV was validated through rigorous statistical testing and consultation with a researcher in the field of second language acquisition, ensuring its linguistic validity. Our code and datasets are publicly available at https://github.com/jiyounglee-0523/TransEnV and https://huggingface.co/collections/jiyounglee0523/transenv-681eadb3c0c8cf363b363fb1.

cs.CL↗

arXiv2025

Descriptive Image-Text Matching with Graded Contextual Similarity

Image-text matching aims to build correspondences between visual and textual data by learning their pairwise similarities. Most existing approaches have adopted sparse binary supervision, indicating whether a pair of images and sentences matches or not. However, such sparse supervision covers a limited subset of image-text relationships, neglecting their inherent many-to-many correspondences; an image can be described in numerous texts at different descriptive levels. Moreover, existing approaches overlook the implicit connections from general to specific descriptions, which form the underlying rationale for the many-to-many relationships between vision and language. In this work, we propose descriptive image-text matching, called DITM, to learn the graded contextual similarity between image and text by exploring the descriptive flexibility of language. We formulate the descriptiveness score of each sentence with cumulative term frequency-inverse document frequency (TF-IDF) to balance the pairwise similarity according to the keywords in the sentence. Our method leverages sentence descriptiveness to learn robust image-text matching in two key ways: (1) to refine the false negative labeling, dynamically relaxing the connectivity between positive and negative pairs, and (2) to build more precise matching, aligning a set of relevant sentences in a generic-to-specific order. By moving beyond rigid binary supervision, DITM enhances the discovery of both optimal matches and potential positive pairs. Extensive experiments on MS-COCO, Flickr30K, and CxC datasets demonstrate the effectiveness of our method in representing complex image-text relationships compared to state-of-the-art approaches. In addition, DITM enhances the hierarchical reasoning ability of the model, supported by the extensive analysis on HierarCaps benchmark.

cs.CV↗

arXiv2025

Bootstrap Your Own Views: Masked Ego-Exo Modeling for Fine-grained View-invariant Video Representations

View-invariant representation learning from egocentric (first-person, ego) and exocentric (third-person, exo) videos is a promising approach toward generalizing video understanding systems across multiple viewpoints. However, this area has been underexplored due to the substantial differences in perspective, motion patterns, and context between ego and exo views. In this paper, we propose a novel masked ego-exo modeling that promotes both causal temporal dynamics and cross-view alignment, called Bootstrap Your Own Views (BYOV), for fine-grained view-invariant video representation learning from unpaired ego-exo videos. We highlight the importance of capturing the compositional nature of human actions as a basis for robust cross-view understanding. Specifically, self-view masking and cross-view masking predictions are designed to learn view-invariant and powerful representations concurrently. Experimental results demonstrate that our BYOV significantly surpasses existing approaches with notable gains across all metrics in four downstream ego-exo video tasks. The code is available at https://github.com/park-jungin/byov.

cs.CV↗

arXiv2025

Optimized Memory System Architecture for VESA VDC-M Decoder with Multi-Slice Support

Video compression plays a pivotal role in managing and transmitting large-scale display data, particularly given the growing demand for higher resolutions and improved video quality. This paper proposes an optimized memory system architecture for Video Electronics Standards Association (VESA) Display Compression-M (VDC-M) decoder, characterized by its substantial on-chip buffer requirements. We design and analyze three architectures categorized by optimization levels and management complexity. Our strategy focuses on enhancing line buffer access scheduling and minimizing reconstruction buffer, targeting prediction and multi-slice operation that are the major resource consumers in the decoder. By adjusting line delay and segmenting SRAM bank alongside reconstructed block forwarding, we achieve a 33.3% size reduction in the line buffer and 77.3% in the reconstruction buffer compared to Baseline VDC-M decoder. Synthesized using a 28 nm CMOS process, the proposed architecture achieves a 31.5% reduction in gate count of the decoder backend hardware, supporting real-time performance with up to 96.45 fps for 4K UHD resolution at 200 MHz operating frequency and a throughput of 4 pixels per cycle.

cs.AR↗

arXiv2024

Single Ground Truth Is Not Enough: Adding Flexibility to Aspect-Based Sentiment Analysis Evaluation

Aspect-based sentiment analysis (ABSA) is a challenging task of extracting sentiments along with their corresponding aspects and opinion terms from the text. The inherent subjectivity of span annotation makes variability in the surface forms of extracted terms, complicating the evaluation process. Traditional evaluation methods often constrain ground truths (GT) to a single term, potentially misrepresenting the accuracy of semantically valid predictions that differ in surface form. To address this limitation, we propose a novel and fully automated pipeline that expands existing evaluation sets by adding alternative valid terms for aspect and opinion. Our approach facilitates an equitable assessment of language models by accommodating multiple-answer candidates, resulting in enhanced human agreement compared to single-answer test sets (achieving up to a 10\%p improvement in Kendall's Tau score). Experimental results demonstrate that our expanded evaluation set helps uncover the capabilities of large language models (LLMs) in ABSA tasks, which is concealed by the single-answer GT sets. Consequently, our work contributes to the development of a flexible evaluation framework for ABSA by embracing diverse surface forms to span extraction tasks in a cost-effective and reproducible manner. Our code and dataset is open at https://github.com/dudrrm/zoom-in-n-out-absa.

cs.CL↗