activity
20222026
most citedRTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer

76 citations · 78 across the 17 of their papers we have counts for

collaborators
Showing cs.CLShow all

2 papers · 1 filter

cs.CL2026

Sample-Efficient Learning from Agent Experience

Chenhui Gou, Haoqin Tu, Yunhao Fang +2

Real-world agent learning is often constrained by costly environment interactions, such as running time-consuming experiments or obtaining human feedback. In-context learning offer…

cs.CL2026

EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments

Deyao Zhu, Xin Zhou, Shengling Qin +44

Pretraining scaling laws reveal that model capability improves predictably with data and compute. But learning from real world environments after deployment remains far less unders…