collaborators

10 papers

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…

cs.LG2026

The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms

Jinghan Zhang, Zerui Cheng, Shiqi Chen +5

Traditional evaluations measure a learning algorithm's final performance on an i.i.d. test set, reducing learning to a single aggregate score. This approach obscures a fundamental…

cs.LG2026

On the Residual Scaling of Looped Transformers: Stability and Transferability

Shaowen Wang, Bingrui Li, Ge Zhang +3

Looped (weight-tied) Transformers apply a shared residual block times (, same at each step), increasing effective depth without adding p…

cs.LG2026

TabularMath: Evaluating Computational Extrapolation in Tabular Learning via Program-Verified Synthesis

Zerui Cheng, Jiashuo Liu, Jianzhu Yao +3

Standard tabular benchmarks mainly focus on the evaluation of a model's capability to interpolate values inside a data manifold, where models good at performing local statistical s…

cs.AI2026

VeRA: Verified Reasoning Data Augmentation at Scale

Zerui Cheng, Jiashuo Liu, Chunjie Wu +4

The main issue with most evaluation schemes today is their "static" nature: the same problems are reused repeatedly, allowing for memorization, format exploitation, and eventual sa…

cs.CL2025

MME-CC: A Challenging Multi-Modal Evaluation Benchmark of Cognitive Capacity

Kaiyuan Zhang, Chenghao Yang, Zhoufutu Wen +19

As reasoning models scale rapidly, the essential role of multimodality in human cognition has come into sharp relief, driving a growing need to probe vision-centric cognitive behav…