Yong Dai

The paper proposes Skill-Conditioned Gated Self-Distillation (SGSD), a novel framework that uses retrieved, potentially noisy skills to guide LLM reasoning, achieving state-of-the-art performance on mathematical reasoning benchmarks.

VLA-Trace is a diagnostic framework that analyzes Vision-Language-Action (VLA) models by tracing their internal representations and external behaviors, revealing that while these models are good at visual grounding, they struggle with fine-grained semantic following.

The paper introduces Unified Context Evolution (UCE), a gradient-free framework that externalizes and manages agent experience into a typed, evolving library, significantly improving performance on multi-step interactive tasks.

The paper introduces CaDDTree, a cost-aware method that optimizes token throughput by jointly selecting the tree structure and node budget for speculative decoding, outperforming existing methods like DDTree.