DIVE Lab, Texas A&M University

university

https://github.com/divelab

AI & ML interests

None defined yet.

Recent Activity

shubhamprshr new activity about 10 hours ago

divelab/Qwen3-8B-a2d-init:Improve model card: add metadata and official links

shubhamprshr new activity about 10 hours ago

divelab/Qwen3-4B-a2d-init:Improve model card with paper info, metadata and links

shubhamprshr updated a dataset about 10 hours ago

divelab/opdlm_eval_data

View all activity

Papers

Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation

Learnability-Informed Fine-Tuning of Diffusion Language Models

View all Papers

divelab 's papers 3

Submitted by

Shubham Parashar

Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation

divelab

DIVE Lab, Texas A&M University

Learnability-Informed Fine-Tuning of Diffusion Language Models

divelab

DIVE Lab, Texas A&M University

Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning

divelab

DIVE Lab, Texas A&M University