7 papers
Efficient Reasoning via Constrained Optimization in Latent Space
Zhinan Hou, Xingchen Li, XingChen Li +1
Large Reasoning Models (LRMs) have shown remarkable reasoning capabilities, yet they still suffer from overthinking, generating redundant reasoning steps which incur substantial to…
GeoTrussRover: Morphological Computation with Contact-Semantic Control Primitives
Muyuan Ma, Yi Zhang, Yang Yang +12
Reconfigurable robots can change their contact geometry when a fixed body cannot negotiate an obstacle. A variable-geometry truss (VGT) distributes this shape change through a load…
What Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection
Zhinan Hou, Jiaqi Zhang, Xunliang Cai +1
On-Policy Distillation (OPD) has emerged as a widely adopted post-training paradigm for enhancing large language models in reasoning domains. However, the data-centric mechanisms i…
LLM4Branch: Large Language Model for Discovering Efficient Branching Policies of Integer Programs
Zhinan Hou, Xingchen Li, Yankai Zhang +2
Efficient branching policies are essential for accelerating Mixed Integer Linear Programming (MILP) solvers. Their design has long relied on hand-crafted heuristics, and now machin…
The FM Agent
Annan Li, Chufan Wu, Zengle Ge +19
Large language models (LLMs) are catalyzing the development of autonomous AI research agents for scientific and engineering discovery. We present FM Agent, a novel and general-purp…
Reliably Learn to Trim Multiparametric Quadratic Programs via Constraint Removal
Zhinan Hou, Keyou You
In a wide range of applications, we are required to rapidly solve a sequence of convex multiparametric quadratic programs (mp-QPs) on resource-limited hardwares. This is a nontrivi…
Harnessing Data for Accelerating Model Predictive Control by Constraint Removal
Zhinan Hou, Feiran Zhao, Keyou You
Model predictive control (MPC) solves a receding-horizon optimization problem in real-time, which can be computationally demanding when there are thousands of constraints. To accel…