Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization
Paper • 2608.16072 • Published • 51
SMILE LAB@Northeastern
SmilelabNEU
AI & ML interests
Northeastern Synergetic Media Learning Lab
Computer Vision, Generative AI, Deep Learning, Artificial Intelligence
Recent Activity
upvoted a paper 6 months ago
ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning ModelOrganizations
None yet
upvoted a paper about 1 month ago
upvoted 3
papers 6 months ago
ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
Paper • 2603.22281 • Published • 22
Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models
Paper • 2503.16980 • Published • 4
Dense Video Understanding with Gated Residual Tokenization
Paper • 2509.14199 • Published • 3