Expertini Research Research

Browse Research Papers

2,276+ open-access research outputs.

โœ• Clear
๐Ÿ” chen lu ๐Ÿ“‚ Computer Science
Showing 2276 results for "chen lu" in Computer Science
Computer Science Preprint PDF DOI

When and How AI Should Assist Brainstorming for AI Impact Assessment

Jarod Govers, Sanja Scepanovic, Daniele Quercia ยท 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 โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

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

Saber Zerhoudi ยท 2026

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

Read Paper โ†’
Computer Science Preprint PDF DOI

When Model Editing Meets Service Evolution: A Knowledge-Update Perspective for Service Recommendation

Guodong Fan, Cuiyun Gao, Chun Yong Chong, Lu Zhang, Jing Li, Jinglin Zhang, Shizhan Chen ยท 2026

The rapid evolution of software services poses substantial challenges to the design and implementation of effective recommendation systems. Traditional service recommendation approaches often rely on โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models

Dongxin Guo, Jikun Wu, Siu Ming Yiu ยท 2026

Large reasoning models such as DeepSeek-R1 and OpenAI o1 generate extended chains of thought spanning thousands of tokens, yet their integration with retrieval-augmented generation (RAG) remains fundaโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

When Prompt Under-Specification Improves Code Correctness: An Exploratory Study of Prompt Wording and Structure Effects on LLM-Based Code Generation

Amal AKLI, Mike PAPADAKIS, Maxime CORDY, Yves Le TRAON ยท 2026

Large language models are increasingly used for code generation, yet the correctness of their outputs depends not only on model capability but also on how tasks are specified. Prior studies demonstratโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Constructive Separations from Gate Elimination

Marco Carmosino, Ngu Dang, Tim Jackman ยท 2026

Gate elimination is the primary technique for proving explicit lower bounds against general Boolean circuits, including Li and Yang's state-of-the-art $3.1n - o(n)$ bound for affine dispersers (STOC 2โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

When the Agent Is the Adversary: Architectural Requirements for Agentic AI Containment After the April 2026 Frontier Model Escape

Richard Joseph Mitchell ยท 2026

The April 2026 disclosure that a frontier large language model escaped its security sandbox, executed unauthorized actions, and concealed its modifications to version control history demonstrates thatโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Training Machine Learning Models on Encrypted Data: A Privacy-Preserving Framework using Homomorphic Encryption

Alexandre Marques, Beatriz Sa, Rui Botelho, Pedro Pinto ยท 2026

The use of Machine Learning (ML) for data-driven decision-making often relies on access to sensitive datasets, which introduces privacy challenges. Traditional encryption methods protect data at rest โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

How Researchers Navigate Accountability, Transparency, and Trust When Using AI Tools in Early-Stage Research: A Think-Aloud Study

Sanjana Gautam, Houjiang Liu, Yujin Choi, Matthew Lease ยท 2026

In the early stages of scientific research, researchers rely on core scholarly judgments to identify relevant literature, assess credible evidence, and determine which directions merit pursuit. As AI โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Understanding teens' self-beliefs when learning to construct and deconstruct AI/ML systems: Developing a survey instrument

Luis Morales-Navarro, Deborah Fields, Michael T. Giang, Daniel J. Noh, Yasmin B. Kafai, Danae Metaxa ยท 2026

Despite growing calls to foster AI literacy, there are few available survey instruments designed for children and youth that study computational empowerment alongside construction and deconstruction aโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

When Constraints Limit and Inspire: Characterizing Presentation Authoring Practices for Evolving Narratives

Linxiu Zeng, Emily Kuang, Jian Zhao ยท 2026

Authoring presentation slides involves navigating contextual constraints that shape how content is structured, adapted, and reused. While prior work frames constraints as limitations, little is known โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

When Transparency Falls Short: Auditing Platform Moderation During a High-Stakes Election

Benedetta Tessa, Gautam Kishore Shahi, Amaury Trujillo, Stefano Cresci ยท 2026

During major political events, social media platforms encounter increased systemic risks. However, it is still unclear if and how they adjust their moderation practices in response. The Digital Servicโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

When AI Models Become Dependencies: Studying the Evolution of Pre-Trained Model Reuse in Downstream Software Systems

Peerachai Banyongrakkul, Mansooreh Zahedi, Christoph Treude, Haoyu Gao, Patanamon Thongtanunam ยท 2026

Modern software systems have transitioned from purely code-based architectures to AI-integrated systems where pre-trained models (PTMs) serve as permanent dependencies. However, while the evolution ofโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

RLM-on-KG: Heuristics First, LLMs When Needed: Adaptive Retrieval Control over Mention Graphs for Scattered Evidence

Andrea Volpini, Elie Raad ยท 2026

When does an LLM controller outperform rule-based traversal for knowledge graph exploration? We study this question through RLM-on-KG, a retrieval system that treats an LLM as an autonomous navigator โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

When does a control system compute? Digital, mechanical and open-loop systems

Dominic Horsman, Susan Stepney, Tim Clarke, Viv Kendon ยท 2026

Control systems are ubiquitous in modern technology, comprising an engineered plant to be kept within specific, often fine-tuned, limits, and a separate controller that ensures this is the case. Whileโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

The Relic Condition: When Published Scholarship Becomes Material for Its Own Replacement

Lin Deng, Chang-bo Liu ยท 2026

We extracted the scholarly reasoning systems of two internationally prominent humanities and social science scholars from their published corpora alone, converted those systems into structured inferenโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

"When I see Jodie, I feel relaxed": Examining the Impact of a Virtual Supporter in Remote Psychotherapy

Jiashuo Cao, Chen Li, Wujie Gao, Simon Hoermann, Nilufar Baghaei, Mark Billinghurst ยท 2026

Virtual agents have shown promising potential in mental health applications, but current research has predominantly focused on contexts outside of traditional therapy sessions. This paper examines theโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Explicit Constant-Alphabet Subspace Design Codes

Rohan Goyal, Venkatesan Guruswami, Jun-Ting Hsieh ยท 2026

The subspace design property for additive codes is a higher-dimensional generalization of the minimum distance property. As shown recently by Brakensiek, Chen, Dhar and Zhang, it implies that the codeโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

When Drawing Is Not Enough: Exploring Spontaneous Speech with Sketch for Intent Alignment in Multimodal LLMs

Weiyan Shi, Dorien Herremans, Kenny Tsu Wei Choo ยท 2026

Early-stage design ideation often relies on rough sketches created under time pressure, leaving much of the designer's intent implicit. In practice, designers frequently speak while sketching, verballโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Entropic independence via sparse localization

Vishesh Jain, Huy Tuan Pham, Thuy-Duong Vuong ยท 2026

Entropic independence is a structural property of measures that underlies modern proofs of functional inequalities, notably (modified) log-Sobolev inequalities, via ``annealing'' or local-to-global scโ€ฆ

Read Paper โ†’
Page 1 of 114 Next โ†’