Pala Tej Deep's picture

1 13 2

Pala Tej Deep

Tej3

·

Tej-Deep

AI & ML interests

None yet

Recent Activity

upvoted a paper 10 days ago

Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics

upvoted a paper about 1 month ago

NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards

upvoted a paper 3 months ago

Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned

View all activity

Organizations

Tej3 's models 3

Tej3/trustalign_qwen3_4b_dpo

4B • Updated May 30 • 4

Tej3/trustalign_llama3.1_8b_dpo

8B • Updated May 30 • 6

Tej3/open_llama_3b_v2_chat_dolly

Text Generation • Updated Mar 21, 2024 • 12