4 papers
STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning
Qinjian Zhao, Zhihao Dou, Dinggen Zhang +10
Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training paradigm for improving the reasoning abilities of large language models. However, existi…
GCE-MIL: Faithful and Recoverable Evidence for Multiple Instance Learning in Whole-Slide Imaging
Xiangyu Li, Ran Su
Multiple instance learning (MIL) is the standard approach for whole-slide image (WSI) classification and survival prediction, where attention-based models ag gregate patch features…
Spatial Blindness in Whole-Slide Multiple Instance Learning
Xiangyu Li, Ran Su
Whole-slide MIL models are often called context-aware once graphs, Transform ers, or state-space modules are placed above patch embeddings. We show that this label can be deceptive…
Benchmarking and Understanding Compositional Relational Reasoning of LLMs
Ruikang Ni, Da Xiao, Qingye Meng +3
Compositional relational reasoning (CRR) is a hallmark of human intelligence, but we lack a clear understanding of whether and how existing transformer large language models (LLMs)…