1 citations · 2 across the 9 of their papers we have counts for
10 papers
STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes
Chenjun Xu, Zhennan Zhou, Zhan Su +3
Long chain-of-thought (Long CoT) reasoning improves performance on multi-step problems, but it also induces overthinking. This inefficiency is especially problematic in low-data fi…
From Atoms to Trees: Building a Structured Feature Forest with Hierarchical Sparse Autoencoders
Yifan Luo, Yang Zhan, Jiedong Jiang +4
Sparse autoencoders (SAEs) have proven effective for extracting monosemantic features from large language models (LLMs), yet these features are typically identified in isolation. H…
Recursive contracts in non-convex environments
Chengfeng Shen, Felix Kübler, Zhennan Zhou
Many dynamic contracting problems in economics are non-convex, and deterministic optima can be dominated by randomized solutions. We develop a recursive method to compute optimal l…
InverseScope: Scalable Activation Inversion for Interpreting Large Language Models
Yifan Luo, Zhennan Zhou, Bin Dong
Understanding the internal representations of large language models (LLMs) is a central challenge in interpretability research. Existing feature interpretability methods often rely…
A Lagrangian Approach to Optimal Randomization
Chengfeng Shen, Felix Kübler, Yucheng Yang +1
We develop an efficient method for solving non-convex constrained optimization problems that are pervasive in economics. The optimal solution to these problems often involves rando…
Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weighting
Yifan Luo, Zhennan Zhou, Meitan Wang +1
In this paper, we investigate the safety mechanisms of instruction fine-tuned large language models (LLMs). We discover that re-weighting MLP neurons can significantly compromise a…
Prompt Engineering Through the Lens of Optimal Control
Yifan Luo, Yiming Tang, Chengfeng Shen +2
Prompt Engineering (PE) has emerged as a critical technique for guiding Large Language Models (LLMs) in solving intricate tasks. Its importance is highlighted by its potential to s…
Meta-DSP: A Meta-Learning Approach for Data-Driven Nonlinear Compensation in High-Speed Optical Fiber Systems
Xinyu Xiao, Zhennan Zhou, Bin Dong +3
Nonlinear effects in high-speed optical fiber systems fundamentally limit channel capacity. While traditional Digital Backward Propagation (DBP) with adaptive filters addresses the…
Tumor growth with a necrotic core as an obstacle problem in pressure
Xu'an Dou, Chengfeng Shen, Zhennan Zhou
Motivated by the incompressible limit of a cell density model, we propose a free boundary tumor growth model where the pressure satisfies an obstacle problem on an evolving domain…
Fictitious Play for Mean Field Games with Optimal Stopping: Convergence and Computation
Chengfeng Shen, Yifan Luo, Zhennan Zhou +1
This paper studies mean field games with optimal stopping time (OSMFGs) where agents make optimal exit decisions. Such a model features a coupled obstacle problem and Fokker-Planck…