Hyeonseok Moon

Interference, measured by task vector variance, predicts LLM merge collapse and guides repair, revealing that sign conflict statistics are anti-predictive.

Turning text into images cuts reranking token overhead by up to 50% and yields a 1.70× throughput boost—all while outperforming standard sub-4B text rerankers across BEIR.

DART boosts reasoning accuracy by up to 22.5 points while slashing thinking token usage by over 50%, all without requiring labeled training data.

SHIFT effectively eliminates language bias in multilingual information retrieval, enhancing access to semantically relevant documents across diverse languages.

Unlock high-performance sparse retrieval in any language: SemBridge's smart initialization closes the cross-lingual gap without sacrificing precision.

Llamion proves you can transplant a model's brain (capabilities like long context and coding) into a new body (Llama architecture) with minimal training, opening the door to easier architecture upgrades and model merging.

Forget generic legal LLMs – LegalMidm shows that focusing on specific Korean legal use cases, with data curated by legal pros, unlocks real-world performance gains.

LLMs can now perform inference without ever seeing raw text, opening the door to privacy-preserving applications without sacrificing performance.

Multilingual retrievers often prioritize irrelevant English documents over relevant foreign-language documents, even when the query is in that foreign language.

Forget just mining hard negatives: the secret to better knowledge distillation for retrieval lies in matching the *entire* score distribution of your teacher model.