Program Schedule

← Back to main page

Time Session Title
9:00 –9: 10 am Workshop Opening
9:10–9:55 am Invited Talk: David Adeline
Mila – Quebec AI Institute
Scaling Multilingual Evaluation of LLMs to Many Languages
10:45–11:00 am Break / Posters
11:05–11:20 am Oral Talk 1 Toward Automatic Safe Driving Instruction: A Large-Scale Vision-Language Model Approach
11:25–11:40 am Oral Talk 2 BengaliFig: A Low-Resource Challenge for Figurative and Culturally Grounded Reasoning in Bengali
11:45 am–12:00 pm Oral Talk 3 Towards Blind and Low-Vision Accessibility of Lightweight VLMs and Custom LLM-Evals
12:00–12:15 pm Oral Talk 4 Artwork Interpretation with Vision Language Models: A Case Study on Emotions and Emotion Symbols
12:15–12:30 pm Oral Talk 5 TRepLiNa: Layer-wise CKA + REPINA Alignment Improves Low-Resource Machine Translation in Aya-23 8B
12:30–1:45 pm Lunch / Posters
1:45–2:30 pm Invited Talk: Roy Ka-Wei Lee
Singapore University of Technology and Design
Tackling Hateful Video Content with Multimodal AI
2:35–3:20 pm Invited Talk: Shamsudeen Muhammad
Google DeepMind Academic Fellow
The Illusion of Inclusion: How LLMs Misrepresent African Languages and Cultural Contexts
3:25–3:40 pm Oral Talk 6 MemeGuard: Transformer-Based Fusion for Multimodal Propaganda Detection in Low-Resource Social Media Memes
3:45–4:00 pm Oral Talk 8 (Challenge Track) LoRAs in All Directions: Directional Adapters and Noisy-Channel Reranking for Indic MT
4:00–4:15 pm Oral Talk 9 (Challenge Track) Breaking Language Barriers: Adapting NLLB-200 and mBART for Bhilli, Gondi, Mundari, and Santali Without Source Language Proficiency
4:15–4:30 pm Oral Talk 10 (Challenge Track) Divide and Translate: Parameter Isolation with Encoder Freezing for Low-Resource Indic NMT
4:30–4:45 pm Oral Talk 11 (Challenge Track) JHARNA-MT: A Copy-Augmented Hybrid of LoRA-Tuned NLLB and Lexical SMT with Minimum Bayes Risk Decoding for Low-Resource Indic Languages