3 citations · 3 across the 10 of their papers we have counts for
11 papers
Placement Is Free, Composition Is Not: The Latin Square as a Provably-Balanced Construction for Heterogeneous Sequence-Mixer Stacks
Taebong Kim, Youngsik Hong, Minsik Kim +3
Since GPT, most Transformers have repeated the same attention mechanism at every layer. Yet this design is largely a convention rather than a tested conclusion. When multiple seque…
The Mask Is Not the Model: Auditing Prefix Invariance in Attention, State-Space, and Hybrid Sequence Models
Taebong Kim, Youngsik Hong, Minsik Kim +3
Hybrid sequence models must satisfy prefix invariance: representations at position t must not depend on future inputs, yet this is rarely verified. We formalize prefix invariance a…
A Numerical Realization of Suzuki's Weil-Quadratic-Form Operator: The Archimedean Spectral Law, its Universality, and an Operator Form of Weil's Positivity Criterion
Taebong Kim, Youngsik Hong, Minsik Kim +3
This paper presents the first numerical realization of Suzuki's Weil-Quadratic-Form operator, a candidate for the Hilbert--Pólya program linking spectral positivity to the Riemann…
Quantum Cryptanalysis on IBM Quantum Hardware: Extending Even--Mansour Period Recovery from to
Taebong Kim, Youngsik Hong, Minsik Kim +4
We report genuine-un-compiled, textbook-faithful-quantum cryptanalysis of symmetric-cipher structures executed on real IBM quantum hardware (ibm\_kingston, Heron generation). Using…
Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance
Minchan Kwon, Sunghyun Baek, Minseo Kim +3
Large Language Model (LLM) Red-Teaming, which proactively identifies vulnerabilities of LLMs, is an essential process for ensuring safety. Finding effective and diverse attacks in…
Asymmetric Flow Models
Hansheng Chen, Jan Ackermann, Minseo Kim +2
Flow-based generation in high-dimensional spaces is difficult because velocity prediction requires modeling high-dimensional noise, even when data has strong low-rank structure. We…
CrystalBoltz: End-to-End Protein Structure Determination via Experiment-Guided Diffusion for X-Ray Crystallography
Minseo Kim, Huanghao Mai, Jay Shenoy +3
Generative models trained on public databases of protein structures, most of which have been determined by X-ray crystallography, now provide powerful priors for structure predicti…
Towards Continuous Sign Language Conversation from Isolated Signs
Youngmin Kim, Kyobin Choo, Jiwoo Park +4
Sign language is the primary language for many Deaf and Hard-of-Hearing (DHH) signers, yet most conversational AI systems still mediate interaction through spoken or written langua…
Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning
Taebong Kim, Youngsik Hong, Minsik Kim +4
We present Darwin Family, a framework for training-free evolutionary merging of large language models via gradient-free weight-space recombination. We ask whether frontier-level re…
MAGE: All-[MASK] Block Already Knows Where to Look in Block Diffusion LLM
Omin Kwon, Yeonjae Kim, Doyeon Kim +3
Block diffusion LLMs are an emerging paradigm for parallel language generation, but their KV caching makes memory access the dominant bottleneck in long-context inference. Sparse a…
Comparison Reveals Commonality: Customized Image Generation through Contrastive Inversion
Minseo Kim, Minchan Kwon, Dongyeun Lee +2
The recent demand for customized image generation raises a need for techniques that effectively extract the common concept from small sets of images. Existing methods typically rel…