4 papers
State of Thought Enables Endogenous Reasoning
Zhiren Gong, Yikun Hou, Zihao Zeng +3
Test-time compute has emerged as a major approach to improving the capabilities of Large Language Models (LLMs). However, existing test-time reasoning paradigms rely heavily on ext…
XDomainBench: Diagnosing Reasoning Collapse in High-Dimensional Scientific Knowledge Composition
Gong Zhiren, Tiantong Wu, Jiaming Zhang +9
Large Language Models (LLMs) are increasingly deployed for knowledge synthesis, yet their capacity for compositional generalization in scientific knowledge remains under-characteri…
Revisiting Frank-Wolfe for Structured Nonconvex Optimization
Hoomaan Maskan, Yikun Hou, Suvrit Sra +1
We introduce a new projection-free (Frank-Wolfe) method for optimizing structured nonconvex functions that are expressed as a difference of two convex functions. This problem class…
Implicit Bias in Matrix Factorization and its Explicit Realization in a New Architecture
Yikun Hou, Suvrit Sra, Alp Yurtsever
Gradient descent for matrix factorization exhibits an implicit bias toward approximately low-rank solutions. While existing theories often assume the boundedness of iterates, empir…