4 papers
RISED: RubrIcs for agentic multi-environment Selection and sElf-Distillation
Jingtan Wang, Sirajul Salekin, Young mok Jung +3
Training a single LLM agent jointly across diverse interactive environments has attracted increasing attention as a route to generalist agents. Existing curriculum and data-selecti…
SCLATE: a Substrate for Continual-Learning Agent Training and Evaluation
Youngmok Jung, Sirajul Salekin, Henry Tran +3
Continual-learning agents are systems of models, harnesses, and memory operating over long multi-session horizons. Evaluating and training them requires interleaving tasks with age…
MixAtlas: Uncertainty-aware Data Mixture Optimization for Multimodal LLM Midtraining
Bingbing Wen, Sirajul Salekin, Feiyang Kang +4
Domain reweighting can improve sample efficiency and downstream generalization, but data-mixture optimization for multimodal midtraining remains largely unexplored. Current multimo…
RubiCap: Rubric-Guided Reinforcement Learning for Dense Image Captioning
Tzu-Heng Huang, Sirajul Salekin, Javier Movellan +2
Dense image captioning is critical for vision-language pretraining and for text-to-image generation, but scaling expert-quality annotations is prohibitively expensive. While synthe…