Pala Tej Deep's picture

1 13 2

Pala Tej Deep

Tej3

·

Tej-Deep

AI & ML interests

None yet

Recent Activity

upvoted a paper 11 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

authored 2 papers 7 months ago

Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision

Paper • 2505.19706 • Published May 26 • 3

Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning

Paper • 2412.11974 • Published Dec 16, 2024 • 10

authored a paper 11 months ago

Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique

Paper • 2408.10701 • Published Aug 20, 2024 • 12

authored a paper over 1 year ago

DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling

Paper • 2406.11617 • Published Jun 17, 2024 • 8