97 citations · 133 across the 9 of their papers we have counts for
15 papers
Counterfactual Gate-Support Decomposition: Separating Selection from Redistribution in Training-Data Filtering
Hyojung Han, Jongmin Kim, Seung-Hun Jeon
A training-data quality gate changes both which examples survive within regions of the input space and how training mass is distributed across those regions, so a gate-versus-rando…
When Should Enterprise Policy Decisions Be Learned, and When Should They Be Reasoned?
Hyojung Han, Ryangkyung Kang, Youngeun Kim +1
An enterprise agent that answers under a written policy must choose an action before it says anything: answer, ask for a missing fact, ask for confirmation, call one or several too…
Quantize by Drift: Label-Free Mixed-Precision Post-Training Quantization for Text Embedders
Hyojung Han, Jongmin Kim, Seung-Hun Jeon
Mixed-precision post-training quantization needs a per-module sensitivity signal; for a text embedder the obvious one -- the retrieval quality a module costs when quantized -- need…
On-Device Commercial Intent Retrieval Under Size, Latency, and Privacy Constraints: A 3 MiB Retrieval System with Typed Egress Boundaries
Hyojung Han
We study commercial intent inference that runs entirely on the user's device, under three constraints frozen before the work began: the downloaded payload under 3 MiB, Tier-0 infer…
Metric-Construction Coupling Inflates Measured Synthetic Dialect Recovery
Hyojung Han
Korean dialect corpora are available but not redistributable: weights may be released, while reproducing training and evaluation from the underlying data cannot be. We ask how much…
Where Post-Training Quantization Breaks Text Embedders: A Measured Map Across Four Embedder Families
Hyojung Han
Weight-only post-training quantization is the cheapest way to shrink a retrieval embedder, and the received advice for applying it -- protect the embedding table, allocate bits by…
Off-Target Effects of Response-Style Alignment in a Korean 27B Language Model
Hyojung Han
We post-train Qwen3.8-27B for Korean response style -- verbosity, list and markdown usage, discourse structure and register -- and measure two behaviours the objective never target…
SpeechQE: Estimating the Quality of Direct Speech Translation
HyoJung Han, Kevin Duh, Marine Carpuat
Recent advances in automatic quality estimation for machine translation have exclusively focused on written language, leaving the speech modality underexplored. In this work, we fo…
Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?
HyoJung Han, Akiko Eriguchi, Haoran Xu +3
Vocabulary adaptation, which integrates new vocabulary into pre-trained language models, enables expansion to new languages and mitigates token over-fragmentation. However, existin…
The Prompt Report: A Systematic Survey of Prompt Engineering Techniques
Sander Schulhoff, Michael Ilie, Nishant Balepur +28
Generative Artificial Intelligence (GenAI) systems are increasingly being deployed across diverse industries and research domains. Developers and end-users interact with these syst…
XLAVS-R: Cross-Lingual Audio-Visual Speech Representation Learning for Noise-Robust Speech Perception
HyoJung Han, Mohamed Anwar, Juan Pino +4
Speech recognition and translation systems perform poorly on noisy inputs, which are frequent in realistic environments. Augmenting these systems with visual signals has the potent…
Bridging Background Knowledge Gaps in Translation with Automatic Explicitation
HyoJung Han, Jordan Lee Boyd-Graber, Marine Carpuat
Translations help people understand content written in another language. However, even correct literal translations do not fulfill that goal when people lack the necessary backgrou…
Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement
HyoJung Han, Seokchan Ahn, Yoonjung Choi +3
Recent work in simultaneous machine translation is often trained with conventional full sentence translation corpora, leading to either excessive latency or necessity to anticipate…
Faster Re-translation Using Non-Autoregressive Model For Simultaneous Neural Machine Translation
Hyojung Han, Sathish Indurthi, Mohd Abbas Zaidi +5
Recently, simultaneous translation has gathered a lot of attention since it enables compelling applications such as subtitle translation for a live event or real-time video-call tr…
Data Efficient Direct Speech-to-Text Translation with Modality Agnostic Meta-Learning
Sathish Indurthi, Houjeung Han, Nikhil Kumar Lakumarapu +4
End-to-end Speech Translation (ST) models have several advantages such as lower latency, smaller model size, and less error compounding over conventional pipelines that combine Aut…