collaborators

5 papers

cs.CL2026

ExCAM: Explainable Cultural Awareness Metrics

Christoph Leiter, Haiyue Song, Hour Kaing +4

Evaluating the cultural awareness of large language models is crucial to ensure the fairness of generated text and the generalizability of applications across the world. Recent ben…

cs.CL2025

PrahokBART: A Pre-trained Sequence-to-Sequence Model for Khmer Natural Language Generation

Hour Kaing, Raj Dabre, Haiyue Song +3

This work introduces {\it PrahokBART}, a compact pre-trained sequence-to-sequence model trained from scratch for Khmer using carefully curated Khmer and English corpora. We focus o…

cs.CL2025

When Alignment Hurts: Decoupling Representational Spaces in Multilingual Models

Ahmed Elshabrawy, Hour Kaing, Haiyue Song +4

Alignment with high-resource standard languages is often assumed to aid the modeling of related low-resource varieties. We challenge this assumption by demonstrating that excessive…

cs.CL2025

TikZero: Zero-Shot Text-Guided Graphics Program Synthesis

Jonas Belouadi, Eddy Ilg, Margret Keuper +5

Automatically synthesizing figures from text captions is a compelling capability. However, achieving high geometric precision and editability requires representing figures as graph…

cs.CL2025

IteRABRe: Iterative Recovery-Aided Block Reduction

Haryo Akbarianto Wibowo, Haiyue Song, Hideki Tanaka +3

Large Language Models (LLMs) have grown increasingly expensive to deploy, driving the need for effective model compression techniques. While block pruning offers a straightforward…