Expertini Research Research

Browse Research Papers

34,098+ open-access research outputs.

✕ Clear
🔍 siheng chen
Showing 34098 results for "siheng chen"
AI & Data Science Preprint PDF DOI

Agent-Agnostic Evaluation of SQL Accuracy in Production Text-to-SQL Systems

Taslim Jamal Arif, Kuldeep Singh · 2026

Text-to-SQL (T2SQL) evaluation in production environments poses fundamental challenges that existing benchmarks do not address. Current evaluation methodologies whether rule-based SQL matching or sche…

Read Paper →
Computer Science Preprint PDF DOI

When and How AI Should Assist Brainstorming for AI Impact Assessment

Jarod Govers, Sanja Scepanovic, Daniele Quercia · 2026

A key task in AI practice is to assess potential impacts to prevent harm. Current AI tools assisting AI impact assessment have not been designed or evaluated for collaborative team brainstorming, and …

Read Paper →
Computer Science Preprint PDF DOI

SimEval-IR: A Unified Toolkit and Benchmark Suite for Evaluating User Simulators and Search Sessions

Saber Zerhoudi · 2026

User simulators are increasingly central to interactive information retrieval, yet the community lacks standardized evaluation tools. Simulators serve two objectives, behavioral realism (matching real…

Read Paper →
Computer Science Preprint PDF DOI

Test Before You Deploy: Governing Updates in the LLM Supply Chain

Mohd Sameen Chishti, Damilare Peter Oyinloye, Jingyue Li · 2026

Large Language Models (LLMs) are increasingly used as core dependencies in software systems. However, the hosted LLM services evolve continuously through provider-side updates without explicit version…

Read Paper →
Physics Preprint PDF DOI

Chern number reversal and emergent superconductivity in rhombohedral graphene induced by in-plane magnetic fields

Xiaozhou Zan, Hangzhe Li, Jiawei Guo, Gengdong Zhou, Kangyao Chen, Cihan Gao, Zijun Xu, Kenji Watanabe, Takashi Taniguchi, Anqi Wang, Jie Shen, Jinsong Zhang, Zhida Song, Yayu Wang · 2026

Rhombohedral graphene with topological flat bands offers an ideal platform for realizing correlated and topological quantum phases. Here we investigate hBN aligned eight-layer rhombohedral graphene mo…

Read Paper →
Computer Science Preprint PDF DOI

Understanding Bugs in Template Engine-Based Applications: Symptoms, Root Causes, and Fix Patterns

Kai Gao, Yu Sun, Chang-ai Sun · 2026

Template engines are indispensable components in modern software ecosystems, enabling the generation of structured documents and scripts across domains such as web development, Infrastructure as Code,…

Read Paper →
AI & Data Science Preprint PDF DOI

When Agents Evolve, Institutions Follow

Chao Fei, Hongcheng Guo, Yanghua Xiao · 2026

Across millennia, complex societies have faced the same coordination problem of how to organize collective action among cognitively bounded and informationally incomplete individuals. Different civili…

Read Paper →
AI & Data Science Preprint PDF DOI

When Does Structure Matter in Continual Learning? Dimensionality Controls When Modularity Shapes Representational Geometry

Kathrin Korte, Joachim Winter Pedersen, Eleni Nisioti, Sebastian Risi · 2026

To preserve previously learned representations, continual learning systems must strike a balance between plasticity, the ability to acquire new knowledge, and stability. This stability-plasticity dile…

Read Paper →
AI & Data Science Preprint PDF DOI

Mapping how LLMs debate societal issues when shadowing human personality traits, sociodemographics and social media behavior

Ali Aghazadeh Ardebili, Massimo Stella · 2026

Large Language Models (LLMs) can strongly shape social discourse, yet datasets investigating how LLM outputs vary across controlled social and contextual prompting remain sparse. Cognitive Digital Sha…

Read Paper →
AI & Data Science Preprint PDF DOI

Trace-Level Analysis of Information Contamination in Multi-Agent Systems

Anna Mazhar, Huzaifa Suri, Sainyam Galhotra · 2026

Reasoning over heterogeneous artifacts (PDFs, spreadsheets, slide decks, etc.) increasingly occurs within structured agent workflows that iteratively extract, transform, and reference external informa…

Read Paper →
Mathematics Preprint PDF DOI

Pancyclicity in Graph Families with the Ore-Type Condition

Luyi Li, Yubo Wang, Guiying Yan · 2026

Let $ n \in \mathbb{N} $ with $ n \geq 3 $, and let $\mathcal{G} = \{G_i:i\in [n]\} $ be a family of $ n $-vertex graphs on a common vertex set $V$, where the graphs in the family do not need to be di…

Read Paper →
AI & Data Science Preprint PDF DOI

Softmax-GS: Generalized Gaussians Learning When to Blend or Bound

Chen Ziwen, Peng Wang, Hao Tan, Zexiang Xu, Li Fuxin · 2026

3D Gaussian Splatting (3D GS) is widely adopted for novel view synthesis due to its high training and rendering efficiency. However, its efficiency relies on the key assumption that Gaussians do not o…

Read Paper →
Engineering Preprint PDF DOI

Feedback Linearization of Hyperbolic PDEs with Volterra Nonlinearities

Miroslav Krstic · 2026

Alberto Isidori's framework of geometric nonlinear control, and particularly of feedback linearization, is the inspiration behind PDE backstepping: apply a transfromation of the state to cast the plan…

Read Paper →
AI & Data Science Preprint PDF DOI

Judge, Then Drive: A Critic-Centric Vision Language Action Framework for Autonomous Driving

Lijin Yang, Jianing Huang, Zhongzhan Huang, Shu Liu, Hao Yang · 2026

Recent advances in vision language action (VLA) models have shown remarkable potential for autonomous driving by directly mapping multimodal inputs to control signals. However, previous VLA-based meth…

Read Paper →
Physics Preprint PDF DOI

Topological phase transitions in twisted bilayer graphene/hBN from interlayer coupling and substrate potentials

Huiwen Wang, Wei Jiang · 2026

Twisted bilayer graphene aligned with hexagonal boron nitride (TBG/hBN) hosts rich topological and correlated quantum phases, such as (fractional) Chern insulators, whose character is dictated by the …

Read Paper →
AI & Data Science Preprint PDF DOI

Learning When to Remember: Risk-Sensitive Contextual Bandits for Abstention-Aware Memory Retrieval in LLM-Based Coding Agents

Mehmet Iscan · 2026

Large language model (LLM)-based coding agents increasingly rely on external memory to reuse prior debugging experience, repair traces, and repository-local operational knowledge. However, retrieved m…

Read Paper →
AI & Data Science Preprint PDF DOI

When 2D Tasks Meet 1D Serialization: On Serialization Friction in Structured Tasks

Chung-Hsiang Lo, Lu Li, Diji Yang, Tianyu Zhang, Yunkai Zhang, Yoshua Bengio, Yi Zhang · 2026

Large language models (LLMs) conventionally process structured inputs as 1D token sequences. While natural for prose, such linearization may introduce additional representational burden for tasks whos…

Read Paper →
AI & Data Science Preprint PDF DOI

When Roles Fail: Epistemic Constraints on Advocate Role Fidelity in LLM-Based Political Statement Analysis

Juergen Dietrich · 2026

Democratic discourse analysis systems increasingly rely on multi-agent LLM pipelines in which distinct evaluator models are assigned adversarial roles to generate structured, multi-perspective assessm…

Read Paper →
Physics Preprint PDF DOI

Dynamical delocalization in disordered 2D Chern insulators

Gianluca Panati, Constanza Rojas-Molina, Vincenzo Rossi · 2026

We show the existence of energies exhibiting dynamical delocalization in discrete 2D Chern insulators perturbed by a random potential in a general setting. Our proof exploits two main features of the …

Read Paper →
AI & Data Science Preprint PDF DOI

Step-level Optimization for Efficient Computer-use Agents

Jinbiao Wei, Kangqi Ni, Yilun Zhao, Guo Gan, Arman Cohan · 2026

Computer-use agents provide a promising path toward general software automation because they can interact directly with arbitrary graphical user interfaces instead of relying on brittle, application-s…

Read Paper →
Page 1 of 1705 Next →