collaborators

5 papers

cs.AI2026

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis

Xinhao Yao, Yuanzhuo Liu, Changhao Wang +6

Deep search is becoming a core capability of modern agent systems, yet it is typically evaluated solely based on end-to-end answer accuracy. This coupled evaluation paradigm entang…

cs.LG2026

Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning

Xinhao Yao, Ruifeng Ren, Yun Liao +2

Chain-of-Thought (CoT) training has markedly advanced the reasoning capabilities of large language models (LLMs), yet the mechanisms by which CoT training enhances generalization r…

cs.LG2026

Transformers as Intrinsic Optimizers: Forward Inference through the Energy Principle

Ruifeng Ren, Sheng Ouyang, Huayi Tang +1

Attention-based Transformers have demonstrated strong adaptability across a wide range of tasks and have become the backbone of modern Large Language Models (LLMs). However, their…

cs.LG2025

Exploring the Limitations of Mamba in COPY and CoT Reasoning

Ruifeng Ren, Zhicong Li, Yong Liu

Transformers have become the backbone of modern Large Language Models (LLMs); however, their inference overhead grows linearly with the sequence length, posing challenges for model…

cs.LG2025

Revisiting Transformers through the Lens of Low Entropy and Dynamic Sparsity

Ruifeng Ren, Yong Liu

Compression has been a critical lens to understand the success of Transformers. In the past, we have typically taken the target distribution as a criterion to evaluate a model's co…