Author name cluster

Jaeyeon Kim

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

Gaze Beyond the Frame: Forecasting Egocentric 3D Visual Span

Heeseung Yun
Joonil Na
Jaeyeon Kim
Calvin Murdock
Gunhee Kim

People continuously perceive and interact with their surroundings based on underlying intentions that drive their exploration and behaviors. While research in egocentric user and scene understanding has focused primarily on motion and contact-based interaction, forecasting human visual perception itself remains less explored despite its fundamental role in guiding human actions and its implications for AR/VR and assistive technologies. We address the challenge of egocentric 3D visual span forecasting, predicting where a person's visual perception will focus next within their three-dimensional environment. To this end, we propose EgoSpanLift, a novel method that transforms egocentric visual span forecasting from 2D image planes to 3D scenes. EgoSpanLift converts SLAM-derived keypoints into gaze-compatible geometry and extracts volumetric visual span regions. We further combine EgoSpanLift with 3D U-Net and unidirectional transformers, enabling spatio-temporal fusion to efficiently predict future visual span in the 3D grid. In addition, we curate a comprehensive benchmark from raw egocentric multisensory data, creating a testbed with 364. 6K samples for 3D visual span forecasting. Our approach outperforms competitive baselines for egocentric gaze anticipation and 3D localization, while achieving comparable results even when projected back onto 2D image planes without additional 2D-specific training.

PDF Details

ICML Conference 2025 Conference Paper

LoRA Training Provably Converges to a Low-Rank Global Minimum Or It Fails Loudly (But it Probably Won't Fail)

Junsu Kim
Jaeyeon Kim
Ernest K. Ryu

Low-rank adaptation (LoRA) has become a standard approach for fine-tuning large foundation models. However, our theoretical understanding of LoRA remains limited as prior analyses of LoRA’s training dynamics either rely on linearization arguments or consider highly simplified setups. In this work, we analyze the LoRA loss landscape without such restrictive assumptions. We define two regimes: a "special regime", which includes idealized setups where linearization arguments hold, and a "generic regime" representing more realistic setups where linearization arguments do not hold. In the generic regime, we show that LoRA training converges to a global minimizer with low rank and small magnitude, or a qualitatively distinct solution with high rank and large magnitude. Finally, we argue that the zero-initialization and weight decay in LoRA training induce an implicit bias toward the low-rank, small-magnitude region of the parameter space—where global minima lie—thus shedding light on why LoRA training usually succeeds in finding global minima.

Details

TMLR Journal 2025 Journal Article

Task Diversity Shortens the In-Context Learning Plateau

Jaeyeon Kim
Sehyun Kwon
Joo Young Choi
Jongho Park
Jaewoong Cho
Jason D. Lee
Ernest K. Ryu

In-context learning (ICL) describes a language model's ability to generate outputs based on a set of input demonstrations and a subsequent query. To understand this remarkable capability, researchers have studied simplified, stylized models. These studies have consistently observed long loss plateaus, during which models exhibit minimal improvement, followed by a sudden, rapid surge of learning. In this work, we reveal that training on multiple diverse ICL tasks simultaneously shortens the loss plateaus, making each task easier to learn. This finding is surprising as it contradicts the natural intuition that the combined complexity of multiple ICL tasks would lengthen the learning process, not shorten it. Our result suggests that the recent success in large-scale training of language models may be attributed not only to the richness of the data at scale but also to the easier optimization (training) induced by the diversity of natural language training data.

PDF Details

ICML Conference 2025 Conference Paper

Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions

Jaeyeon Kim
Kulin Shah
Vasilis Kontonis
Sham M. Kakade
Sitan Chen

In recent years, masked diffusion models (MDMs) have emerged as a promising alternative approach for generative modeling over discrete domains. Compared to autoregressive models (ARMs), MDMs trade off complexity at training time with flexibility at inference time. At training time, they must learn to solve an exponentially large number of infilling problems, but at inference time, they can decode tokens in essentially arbitrary order. In this work we closely examine these two competing effects. On the training front, we theoretically and empirically demonstrate that MDMs indeed train on computationally intractable subproblems compared to their autoregressive counterparts. On the inference front, we show that a suitable strategy for adaptively choosing the token decoding order significantly enhances the capabilities of MDMs, allowing them to sidestep hard subproblems. On logic puzzles like Sudoku, we show that adaptive inference can boost solving accuracy in pretrained MDMs from $<7$% to $\approx 90$%, even outperforming ARMs that were explicitly trained via teacher forcing to learn the right order of decoding.

Details

ICLR Conference 2025 Conference Paper

ViSAGe: Video-to-Spatial Audio Generation

Jaeyeon Kim
Heeseung Yun
Gunhee Kim

Spatial audio is essential for enhancing the immersiveness of audio-visual experiences, yet its production typically demands complex recording systems and specialized expertise. In this work, we address a novel problem of generating first-order ambisonics, a widely used spatial audio format, directly from silent videos. To support this task, we introduce YT-Ambigen, a dataset comprising 102K 5-second YouTube video clips paired with corresponding first-order ambisonics. We also propose new evaluation metrics to assess the spatial aspect of generated audio based on audio energy maps and saliency metrics. Furthermore, we present Video-to-Spatial Audio Generation (ViSAGe), an end-to-end framework that generates first-order ambisonics from silent video frames by leveraging CLIP visual features, autoregressive neural audio codec modeling with both directional and visual guidance. Experimental results demonstrate that ViSAGe produces plausible and coherent first-order ambisonics, outperforming two-stage approaches consisting of video-to-audio generation and audio spatialization. Qualitative examples further illustrate that ViSAGe generates temporally aligned high-quality spatial audio that adapts to viewpoint changes.

Details

ICML Conference 2024 Conference Paper

Optimal Acceleration for Minimax and Fixed-Point Problems is Not Unique

Taeho Yoon
Jaeyeon Kim
Jaewook J. Suh
Ernest K. Ryu

Recently, accelerated algorithms using the anchoring mechanism for minimax optimization and fixed-point problems have been proposed, and matching complexity lower bounds establish their optimality. In this work, we present the surprising observation that the optimal acceleration mechanism in minimax optimization and fixed-point problems is not unique. Our new algorithms achieve exactly the same worst-case convergence rates as existing anchor-based methods while using materially different acceleration mechanisms. Specifically, these new algorithms are dual to the prior anchor-based accelerated methods in the sense of H-duality. This finding opens a new avenue of research on accelerated algorithms since we now have a family of methods that empirically exhibit varied characteristics while having the same optimal worst-case guarantee.

Details

NeurIPS Conference 2023 Conference Paper

Time-Reversed Dissipation Induces Duality Between Minimizing Gradient Norm and Function Value

Jaeyeon Kim
Asuman Ozdaglar
Chanwoo Park
Ernest Ryu

In convex optimization, first-order optimization methods efficiently minimizing function values have been a central subject study since Nesterov's seminal work of 1983. Recently, however, Kim and Fessler's OGM-G and Lee et al. 's FISTA-G have been presented as alternatives that efficiently minimize the gradient magnitude instead. In this paper, we present H-duality, which represents a surprising one-to-one correspondence between methods efficiently minimizing function values and methods efficiently minimizing gradient magnitude. In continuous-time formulations, H-duality corresponds to reversing the time dependence of the dissipation/friction term. To the best of our knowledge, H-duality is different from Lagrange/Fenchel duality and is distinct from any previously known duality or symmetry relations. Using H-duality, we obtain a clearer understanding of the symmetry between Nesterov's method and OGM-G, derive a new class of methods efficiently reducing gradient magnitudes of smooth convex functions, and find a new composite minimization method that is simpler and faster than FISTA-G.

PDF Details

AAAI Conference 2022 Conference Paper

Learning Economic Indicators by Aggregating Multi-Level Geospatial Information

Sungwon Park
Sungwon Han
Donghyun Ahn
Jaeyeon Kim
Jeasurk Yang
Susang Lee
Seunghoon Hong
Jihee Kim

High-resolution daytime satellite imagery has become a promising source to study economic activities. These images display detailed terrain over large areas and allow zooming into smaller neighborhoods. Existing methods, however, have utilized images only in a single-level geographical unit. This research presents a deep learning model to predict economic indicators via aggregating traits observed from multiple levels of geographical units. The model first measures hyperlocal economy over small communities via ordinal regression. The next step extracts district-level features by summarizing interconnection among hyperlocal economies. In the final step, the model estimates economic indicators of districts via aggregating the hyperlocal and district information. Our new multi-level learning model substantially outperforms strong baselines in predicting key indicators such as population, purchasing power, and energy consumption. The model is also robust against data shortage; the trained features from one country can generalize to other countries when evaluated with data gathered from Malaysia, the Philippines, Thailand, and Vietnam. We discuss the multi-level model’s implications for measuring inequality, which is the essential first step in policy and social science research on inequality and poverty.

PDF Details