16 papers
DUDA-Bench: Benchmarking LLM Agents on Multimodal Data-Driven Urban Diagnosis
Yizhi Song, Hang Ni, Weijia Zhang +1
Urban diagnosis integrates heterogeneous observations to identify urban problems, localize affected areas, and investigate contributing factors, informing evidence-based urban plan…
Vector Balancing in Polynomial Time
Shengtao Guo, Ethan X. Fang, Junwei Lu
We present a spectral signing algorithm solving the Komlós problem with a constant discrepancy in polynomial time. Given a matrix whose columns have Eu…
Unimodality of Independence Polynomials for Sufficiently Large Forests
Ethan X. Fang, Junwei Lu, Eran Nevo +2
We prove that the independence sequence of every sufficiently large forest is unimodal. The result follows from establishing log-concavity on a central interval of the sequence, al…
Vector Balancing via Directional Total Variation
Shengtao Guo, Ethan X. Fang, Junwei Lu
Our main result is a bound for the Komlós signing problem: every finite family of real vectors of Euclidean norm at most one admits a signed sum of -norm…
Optimal Value Inference for Reinforcement Learning
Nan Lu, Ethan Lee, James M. Robins +2
We study offline inference for the optimal value in reinforcement learning under finite state and action spaces. Two new nuisances are derived as fixed points of a self-induced Bel…
An Improved Lower Bound for the Complex Grothendieck Constant
Shengtao Guo, Ethan X. Fang, Junwei Lu
We prove for the classical complex Grothendieck constant, closing more than one quarter of the gap between Davie's lower bound and Haagerup's up…
A Complex Structure on
Shengtao Guo, Ethan X. Fang, Junwei Lu
We show that admits a complex structure. Starting from a modular family of complex two-tori associated with the triangle group and the compactificati…
A Metric with Positive Sectional Curvature on
Shengtao Guo, Ethan X. Fang, Junwei Lu
We prove that admits a Riemannian metric with positive sectional curvature. We view it as a principal circle bundle over . A diagonal Cheeger deforma…
Weak-Type Bounds for Convolution on the Boolean Hypercube
Junwei Lu, Shengtao Guo, Ethan X. Fang
Let be the Boolean hypercube which carries uniform measure , and let denote convolution by a finite positive measure on . For $ψ_μ(u)=\sup\{uλ(\{T_μf\geq u\}):f…
Hypothesis-Disciplined Multi-Agent Automated Formalization of Asymptotic Statistical Theory
Tingzhou Wei, Zeyu Zheng, Ethan X. Fang +1
Asymptotic statistical theory is a challenging domain for AI-assisted formalization: its central results mix convergence statements, asymptotic expansions, functional analysis, and…
Channel-Preserving Representation Alignment for EEG-to-Music Reconstruction
Jiaxin Qing, Junwei Lu, Lexin Li
Reconstructing naturalistic music from EEG requires extracting music-specific information from weak signals distributed across electrodes. Existing spectrogram regression and diffu…
Uncertainty Quantification for Large Language Model Reward Learning under Heterogeneous Human Feedback
Pangpang Liu, Junwei Lu, Will Wei Sun
We study estimation and statistical inference for reward models used in aligning large language models (LLMs). A key component of LLM alignment is reinforcement learning from human…
MOTION: ML-Assisted On-Device Low-Latency Motion Recognition
Veeramani Pugazhenthi, Wei-Hsiang Chu, Junwei Lu +5
The use of tiny devices capable of low-latency gesture recognition is gaining momentum in everyday human-computer interaction and especially in medical monitoring fields. Embedded…
Fisher Random Walk: Automatic Debiasing Contextual Preference Inference for Large Language Model Evaluation
Yichi Zhang, Alexander Belloni, Ethan X. Fang +2
Motivated by the need for rigorous and scalable evaluation of large language models, we study contextual preference inference for pairwise comparison functionals of context-depende…
Electric field tunable magnetoexcitons in Xenes-hBN-TMDC, Xenes-hBN-BP, and Xenes-hBN-TMTC heterostructures
Roman Ya. Kezerashvili, Anastasia Spiridonova, Klaus Ziegler
In this work, we propose novel van der Waals (vdW) heterostructures composed of Xenes, transition metal dichalcogenides (TMDCs), phosphorene, and transition metal trichalcogenides…
Confidence Diagram of Nonparametric Ranking for Uncertainty Assessment in Large Language Models Evaluation
Zebin Wang, Yi Han, Ethan X. Fang +2
We consider the inference for the ranking of large language models (LLMs). Alignment arises as a significant challenge to mitigate hallucinations in the use of LLMs. Ranking LLMs h…