Expertini Research Research

Browse Research Papers

10,616+ open-access research outputs.

✕ Clear
🔍 berat dogan
Showing 10616 results for "berat dogan"
AI & Data Science Preprint PDF DOI

Beyond Semantics: Measuring Fine-Grained Emotion Preservation in Small Language Model-Based Machine Translation

Dawid Wisniewski, Igor Czudy · 2026

Preserving affective nuance remains a challenge in Machine Translation (MT), where semantic equivalence often takes precedence over emotional fidelity. This paper evaluates the performance of three st…

Read Paper →
AI & Data Science Preprint PDF DOI

Emotion-Aware Clickbait Attack in Social Media

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

Clickbait is characterized by disproportionately high emotional intensity relative to informational content, often reinforced by specific structural patterns. However, current research considers click…

Read Paper →
Computer Science Preprint PDF DOI

Cross-lingual Comparison of Research Funding Projects with Multilingual Sentence-BERT: Evidence from KAKENHI, NIH, NSF, and UKRI

Miki Kimura-Ida · 2026

Cross-national comparison of research funding projects is increasingly important for science policy and strategic planning, but language differences remain a major obstacle. In particular, KAKENHI pro…

Read Paper →
Mathematics Preprint PDF DOI

On Arithmetic Mirror Symmetry for smooth Fano fourfolds

Mikhail Ovcharenko · 2026

We introduce an explicit class of tempered Laurent polynomials in the sense of Villegas and Doran--Kerr in $n \leqslant 4$ variables including all Landau--Ginzburg models for smooth Fano threefolds wi…

Read Paper →
Computer Science Preprint PDF DOI

Identifying and Characterizing Semantic Clones of Solidity Functions

Ermanno Francesco Sannini, Francesco Salzano, Simone Scalabrino, Rocco Oliveto, Remo Pareschi, Corrado Aaron Visaggio, Andrea Di Sorbo · 2026

Smart Contracts are essential blockchain components, mainly written in Solidity. The high availability of public Solidity code leads to frequent reuse and high clone ratios. Since cloning can propagat…

Read Paper →
AI & Data Science Preprint PDF DOI

Benchmarking Complex Multimodal Document Processing Pipelines: A Unified Evaluation Framework for Enterprise AI

Saurabh K. Singh, Sachin Raj · 2026

Most enterprise document AI today is a pipeline. Parse, index, retrieve, generate. Each of those stages has been studied to death on its own -- what's still hard is evaluating the system as a whole. …

Read Paper →
AI & Data Science Preprint PDF DOI

G-Loss: Graph-Guided Fine-Tuning of Language Models

Sharma Aditya, Agarwal Vinti, Kumar Rajesh · 2026

Traditional loss functions, including cross-entropy, contrastive, triplet, and su pervised contrastive losses, used for fine-tuning pre-trained language models such as BERT, operate only within local …

Read Paper →
AI & Data Science Preprint PDF DOI

Magnification-Invariant Image Classification via Domain Generalization and Stable Sparse Embedding Signatures

Ifeanyi Ezuma, Olusiji Medaiyese · 2026

Magnification shift is a major obstacle to robust histopathology classification, because models trained on one imaging scale often generalize poorly to another. Here, we evaluated this problem on the …

Read Paper →
Computer Science Preprint PDF DOI

SymphonyGen: 3D Hierarchical Orchestral Generation with Controllable Harmony Skeleton

Xuzheng He, Nan Nan, Zhilin Wang, Ziyue Kang, Zhuoru Mo, Ao Li, Yu Pan, Xiaobing Li, Feng Yu, Xiaohong Guan · 2026

Generating symphonic music requires simultaneously managing high-level structural form and dense, multi-track orchestration. Existing symbolic models often struggle with a "complexity-control imbalanc…

Read Paper →
Mathematics Preprint PDF DOI

Balanced and pluriclosed metrics on real semisimple Lie groups

Joseph Kwong · 2026

We characterise the existence of balanced and pluriclosed metrics on compact quotients of real semisimple Lie groups equipped with regular complex structures, in terms of Vogan diagrams. Consequently,…

Read Paper →
AI & Data Science Preprint PDF DOI

DiRe-RAPIDS: Topology-faithful dimensionality reduction at scale

Alexander Kolpakov, Igor Rivin · 2026

Dimensionality reduction methods such as UMAP and t-SNE are central tools for visualising high-dimensional data, but their local-neighborhood objectives can preserve sampling noise while distorting gl…

Read Paper →
AI & Data Science Preprint PDF DOI

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Zhiheng Liu, Weiming Ren, Xiaoke Huang, Shoufa Chen, Tianhong Li, Mengzhao Chen, Yatai Ji, Sen He, Jonas Schult, Belinda Zeng, Tao Xiang, Wenhu Chen, Ping Luo, Luke Zettlemoyer, Yuren Cong · 2026

Unified multimodal models typically rely on pretrained vision encoders and use separate visual representations for understanding and generation, creating misalignment between the two tasks and prevent…

Read Paper →
Physics Preprint PDF DOI

Emergent Features in $U(N) \times U(\tilde{N})$ Bi-adjoint Cubic Theory

Lauren Smyth · 2026

This work investigates the role of the $U(N) \times U(\tilde{N})$ global symmetry in tree-level scattering amplitudes of the bi-adjoint $\phi^3$ theory from three perspectives: combinatorics, correlat…

Read Paper →
Mathematics Preprint PDF DOI

Colored Stallings graphs and Counterexamples to Stallings equalizer conjecture

Jialin Lei, Teng Zhang · 2026

The famous Stallings equalizer conjecture has remained open for more than 40 years, which states that, for any free group \(F_n\) of rank \(n\ge 2\), any free group \(F\), and any two monomorphisms $g…

Read Paper →
Computer Science Preprint PDF DOI

Geometric Analysis of Self-Supervised Vision Representations for Semantic Image Retrieval

Esteban Rodriguez-Betancourt, Edgar Casasola-Murillo · 2026

Content-based image retrieval (CBIR) systems enable users to search images based on visual content instead of relying on metadata. The text domain has benefited from vector search of representations c…

Read Paper →
AI & Data Science Preprint PDF DOI

ELSA: Exact Linear-Scan Attention for Fast and Memory-Light Vision Transformers

Chih-Chung Hsu, Xin-Di Ma, Wo-Ting Liao, Chia-Ming Lee · 2026

Existing attention accelerators often trade exact softmax semantics, depend on fused Tensor Core kernels, or incur sequential depth that limits FP32 throughput on long sequences. We present \textbf{EL…

Read Paper →
AI & Data Science Preprint PDF DOI

The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation

Shuaizhi Cheng, Xiang Shi, Mingwei Li · 2026

Hypernetwork-based methods such as Doc-to-LoRA internalize a document into an LLM's weights in a single forward pass, but they fail systematically on conflicts: when the document contradicts pretraini…

Read Paper →
AI & Data Science Preprint PDF DOI

Rank, Head-Channel Non-Identifiability, and Symmetry Breaking: A Precise Analysis of Representational Collapse in Transformers

Giansalvo Cirrincione · 2026

A widely cited result by Dong et al. (2021) showed that Transformers built from self-attention alone, without skip connections or feed-forward layers, suffer from rapid rank collapse: all token repres…

Read Paper →
AI & Data Science Preprint PDF DOI

ComplianceNLP: Knowledge-Graph-Augmented RAG for Multi-Framework Regulatory Gap Detection

Dongxin Guo, Jikun Wu, Siu Ming Yiu · 2026

Financial institutions must track over 60,000 regulatory events annually, overwhelming manual compliance teams; the industry has paid over USD 300 billion in fines and settlements since the 2008 finan…

Read Paper →
Computer Science Preprint PDF DOI

Automating Categorization of Scientific Texts with In-Context Learning and Prompt-Chaining in Large Language Models

Gautam Kishore Shahi, Oliver Hummel · 2026

The relentless expansion of scientific literature presents significant challenges for navigation and knowledge discovery. Within Research Information Retrieval, established tasks such as text summariz…

Read Paper →
Page 1 of 531 Next →