4 papers
CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation
Chaoyu Li, Fei Tao, Pooyan Fazli
Vision-language models achieve strong performance across a wide range of multimodal understanding and reasoning tasks, yet their multi-step reasoning remains unstable. Repeated sam…
ChitroJera: A Regionally Relevant Visual Question Answering Dataset for Bangla
Deeparghya Dutta Barua, Md Sakib Ul Rahman Sourove, Md Fahim +6
Visual Question Answer (VQA) poses the problem of answering a natural language question about a visual context. Bangla, despite being a widely spoken language, is considered low-re…
BanTH: A Multi-label Hate Speech Detection Dataset for Transliterated Bangla
Fabiha Haider, Fariha Tanjim Shifat, Md Farhan Ishmam +4
The proliferation of transliterated texts in digital spaces has emphasized the need for detecting and classifying hate speech in languages beyond English, particularly in low-resou…
Enhancing Heterogeneous Multi-Agent Cooperation in Decentralized MARL via GNN-driven Intrinsic Rewards
Jahir Sadik Monon, Deeparghya Dutta Barua, Md. Mosaddek Khan
Multi-agent Reinforcement Learning (MARL) is emerging as a key framework for various sequential decision-making and control tasks. Unlike their single-agent counterparts, multi-age…