Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents
Paper • 2610.33956 • Published • 46
VWMG
classroom
AI & ML interests
None defined yet.
Recent Activity
View all activity
HaoyuZhao
authored 2
papers 6 days ago
HaoyuZhao
submitted a
paper to Daily Papers 6 days ago
williamium
submitted a
paper to Daily Papers 14 days ago
HaoyuZhao
submitted a
paper to Daily Papers 23 days ago
HaoyuZhao
updated a
dataset about 2 months ago
HaoyuZhao
published a
dataset 2 months ago
williamium
authored 5
papers 2 months ago
Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization
Paper • 2608.16072 • Published • 31
Self-Supervised Visual On-Policy Distillation
Paper • 2608.14144 • Published • 55
On-Policy Self-Distillation without Any Supervision
Paper • 2608.06296 • Published • 126
Attention Sinks and Outliers in Attention Residuals
Paper • 2605.17887 • Published • 5
Demystifying Agent Skills: Why They Work-Until They Don't
Paper • 2608.14036 • Published • 57
williamium
submitted 2
papers to Daily Papers 2 months ago
williamium
submitted 3
papers to Daily Papers 3 months ago
Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization
Paper • 2608.16072 • Published • 31
Self-Supervised Visual On-Policy Distillation
Paper • 2608.14144 • Published • 55
On-Policy Self-Distillation without Any Supervision
Paper • 2608.06296 • Published • 126
williamium
authored 3
papers 3 months ago
Visual Contrastive Self-Distillation
Paper • 2607.21556 • Published • 48
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models
Paper • 2607.06553 • Published • 15
SPACENUM: Revisiting Spatial Numerical Understanding in VLMs
Paper • 2605.23898 • Published • 7