Expertini Research Research

Browse Research Papers

25,335+ open-access research outputs.

✕ Clear
🔍 junyang cai
Showing 25335 results for "junyang cai"
AI & Data Science Preprint PDF DOI

Exploration Hacking: Can LLMs Learn to Resist RL Training?

Eyon Jang, Damon Falck, Joschka Braun, Nathalie Kirch, Achu Menon, Perusha Moodley, Scott Emmons, Roland S. Zimmermann, David Lindner · 2026

Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs) for reasoning, agentic capabilities and alignment. Successful RL relies on sufficient exploration …

Read Paper →
Mathematics Preprint PDF DOI

Can You Hear the Shape of a Hyperbolic Surface? Now for Real

Ludovico Battista, Juan Souto · 2026

We associate a musical instrument, a "hyperbolic marimba", to every pair $(X,\Gamma)$ where $X$ is a hyperbolic surface and $\Gamma\subset X$ a simple multicurve labeled with musical keys. It works as…

Read Paper →
AI & Data Science Preprint PDF DOI

Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future

Sihong Wu, Owen Jiang, Yilun Zhao, Tiansheng Hu, Yiling Ma, Kaiyan Zhang, Manasi Patwardhan, Arman Cohan · 2026

Peer review is a multi-stage process involving reviews, rebuttals, meta-reviews, final decisions, and subsequent manuscript revisions. Recent advances in large language models (LLMs) have motivated me…

Read Paper →
Computer Science Preprint PDF DOI

Can We Volunteer Out of the Peer Review Crisis?

Theo Tang, Toby Handfield, Julian Garcia · 2026

The volume of scientific manuscripts is growing faster than the capacity to evaluate them, yet the institutions that govern peer review have remained largely unchanged. The result is a widening mismat…

Read Paper →
Computer Science Preprint PDF DOI

AME-PIM: Can Memory be Your Next Tensor Accelerator?

Emanuele Venieri, Simone Manoni, Alberto Florian, Jaehyun Park, Kyomin Sohn, Andrea Bartolini · 2026

High Bandwidth Memory with Processing-in-Memory (HBM-PIM) offers an opportunity to reduce data movement by executing computation directly inside memory, but current commercial platforms expose limited…

Read Paper →
Engineering Preprint PDF DOI

Can Tabular Foundation Models Guide Exploration in Robot Policy Learning?

Buqing Ou, Frederike Dumbgen · 2026

Policy optimization in high-dimensional continuous control for robotics remains a challenging problem. Predominant methods are inherently local and often require extensive tuning and carefully chosen …

Read Paper →
AI & Data Science Preprint PDF DOI

From Context to Skills: Can Language Models Learn from Context Skillfully?

Shuzheng Si, Haozhe Zhao, Yu Lei, Qingyi Wang, Dingwei Chen, Zhitong Wang, Zhenhailong Wang, Kangyang Luo, Zheng Wang, Gang Chen, Fanchao Qi, Minjia Zhang, Maosong Sun · 2026

Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learning, where LMs directly learn relevant knowledge…

Read Paper →
Mathematics Preprint PDF DOI

How large part of a graph can be covered by the neighborhoods of k vertices?

Janos Pach · 2026

Let $k\ge 2$ be fixed integer, $0<c<1$ a constant. Consider a graph $G$ with $n$ vertices and average degree $cn$. We answer a question of Simon Griffiths by showing that $G$ has $k$ vertices such tha…

Read Paper →
AI & Data Science Preprint PDF DOI

Optimization before Evaluation: Evaluation with Unoptimised Prompts Can be Misleading

Nicholas Sadjoli, Tim Siefken, Atin Ghosh, Yifan Mai, Daniel Dahlmeier · 2026

Current Large Language Model (LLM) evaluation frameworks utilize the same static prompt template across all models under evaluation. This differs from the common industry practice of using prompt opti…

Read Paper →
Mathematics Preprint PDF DOI

Barriers, Barenblatt solutions and regularity of soda can domains for the heat equation and nonlinear $p$-parabolic equations

Anders Bjorn, Jana Bjorn · 2026

In this paper we study when the origin $(0,0)$ is a regular (or irregular) boundary point for the so-called soda can domains of the type \[ \Theta_{l,\theta}:= \{(x,t) \in \mathbf{R}^{n+1}: 0<-t < \th…

Read Paper →
AI & Data Science Preprint PDF DOI

Context as Prior: Bayesian-Inspired Intent Inference for Non-Speaking Agents with a Household Cat Testbed

Wenqian Zhang, Zehao Wang · 2026

Many agents in real-world environments cannot reliably communicate their goals through language, including household pets, pre-verbal infants, and other non-speaking embodied agents. In such settings,…

Read Paper →
AI & Data Science Preprint PDF DOI

InteractWeb-Bench: Can Multimodal Agent Escape Blind Execution in Interactive Website Generation?

Qiyao Wang, Haoran Hu, Longze Chen, Hongbo Wang, Hamid Alinejad-Rokny, Yuan Lin, Min Yang · 2026

With the advancement of multimodal large language models (MLLMs) and coding agents, the website development has shifted from manual programming to agent-based project-level code synthesis. Existing be…

Read Paper →
Computer Science Preprint PDF DOI

From Notepad AI to Social Media: How Can Text Style Transformation Mitigate Social Harm?

Syed Mhamudul Hasan, Mohd. Farhan Israk Soumik, Abdur R. Shahid · 2026

The rapid proliferation of harmful and emotionally damaging content on social media platforms has intensified concerns regarding societal harm. While content moderation efforts primarily focus on dete…

Read Paper →
Economics & Finance Preprint PDF DOI

Treatment-effect heterogeneity and interactive fixed effects: Can we control for too much?

Murilo Cardoso, Bruno Ferman, Marcelo Fernandes · 2026

This paper studies the interactive fixed effects (IFE) estimator in a panel-data setting with heterogeneous treatment effects. We show that, if the treatment-effect heterogeneity admits a linear facto…

Read Paper →
Physics Preprint PDF DOI

The A Supergiant Eclipsing Binary BM Cas: An Evolved, Intermediate Mass System

T. J. Davidge · 2026

The evolutionary state of the 198 day eclipsing binary BM Cas is examined using spectra that cover five orbital cycles. Radial velocities measured from SiII 6347 and SiII 6371 track the motion of the …

Read Paper →
AI & Data Science Preprint PDF DOI

CL-bench Life: Can Language Models Learn from Real-Life Context?

Shihan Dou, Yujiong Shen, Chenhao Huang, Junjie Ye, Jiayi Chen, Junzhe Wang, Qianyu He, Shichun Liu, Changze Lv, Jiahang Lin, Jiazheng Zhang, Ming Zhang, Shaofan Liu, Tao Ji, Zhangyue Yin, Cheng Zhang, Huaibing Xie, Jianglu Hu, Jingcheng Deng, Lincheng Li, Minda Hu, Shaolei Wang, Syrus Zhao, Weichao Wang, Yan Lei, Yang Liu, Yanling Xiao, Yiting Liu, Zenan Xu, Zhen Guo, Ziliang Zhao, Pluto Zhou, Tao Gui, Qi Zhang, Xuanjing Huang, Yu-Gang Jiang, Di Wang, Shunyu Yao · 2026

Today's AI assistants such as OpenClaw are designed to handle context effectively, making context learning an increasingly important capability for models. As these systems move beyond professional se…

Read Paper →
Biology & Life Sciences Preprint PDF DOI

Can we teach generative artificial intelligence the design language of engineered living materials?

Andres Diaz Lantada, Jose A. Yanez, William Solorzano-Requejo, Monsur Islam · 2026

This study presents a versatile ontology and a useful codification scheme for describing all kinds of engineered living materials (ELMs). The different components of the ontology, namely: families acc…

Read Paper →
Engineering Preprint PDF DOI

FeatureFox: Sample-Efficient Panoptic Graph Segmentation for Machining Feature Recognition in B-Rep 3D-CAD Models

Bertram Fuchs, Altay Kacan, Aaron Haag, Oliver Lohse · 2026

Automatic feature recognition (AFR) on B-Rep 3D-CAD models is central to CAD/CAM automation, yet most learning-based methods are complex, data-hungry, and evaluate instance grouping and semantic label…

Read Paper →
Medicine & Health Preprint PDF DOI

Simulation of complex DNA damage enhancement and biological effect validation for Proton-CAT

Lang Dong, Dechao An, Junxiang Wu, Tianle Wang, Zhao Sun, Jiajun Kang, Xianliang Wang, Lintao Li, Shun Lu, Tianli Qiu, Da Zhang, Zhencen He, Zhimin Hu · 2026

Proton therapy has been rapidly advancing due to its excellent conformal index, but its relatively low relative biological effect (RBE) has somewhat limited its therapeutic efficacy for certain tumors…

Read Paper →
Physics Preprint PDF DOI

All pure entangled states can lead to fully nonlocal correlations

Martin J. Renner, Edwin Peter Lobo, Arturo Konderak, Remigiusz Augusiak, Antonio Acin · 2026

It is a well-established fact that some quantum correlations can be nonlocal, meaning that they cannot be described by a local hidden variable model. Certain quantum correlations have a form of nonloc…

Read Paper →
Page 1 of 1267 Next →