Review

[논문리뷰] Imperceptible Jailbreaking against Large Language Models

arXiv에 게시된 'Imperceptible Jailbreaking against Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models #Jailbreaking #Imperceptible Attacks #Unicode Variation Selectors #Adversarial Suffixes #Safety Alignment #Prompt Injection

2025년 10월 7일

[논문리뷰] Hybrid Architectures for Language Models: Systematic Analysis and Design Insights

arXiv에 게시된 'Hybrid Architectures for Language Models: Systematic Analysis and Design Insights' 논문에 대한 자세한 리뷰입니다.

#Review #Hybrid LLM #Transformer Architecture #Mamba #State Space Models (SSM)#Computational Efficiency #Long-Context #Language Model Architectures #Scaling Laws

2025년 10월 7일

[논문리뷰] HiKE: Hierarchical Evaluation Framework for Korean-English Code-Switching Speech Recognition

arXiv에 게시된 'HiKE: Hierarchical Evaluation Framework for Korean-English Code-Switching Speech Recognition' 논문에 대한 자세한 리뷰입니다.

#Review #Code-Switching #Speech Recognition #Korean-English ASR #Evaluation Framework #Multilingual ASR #Loanword Processing #Fine-tuning #Hierarchical Labeling

2025년 10월 7일

[논문리뷰] Graph2Eval: Automatic Multimodal Task Generation for Agents via Knowledge Graphs

Zeyi Liao이 arXiv에 게시한 'Graph2Eval: Automatic Multimodal Task Generation for Agents via Knowledge Graphs' 논문에 대한 자세한 리뷰입니다.

#Review #Agent Evaluation #Task Generation #Knowledge Graphs #Multimodal AI #Web Interaction #Document Comprehension #LLM-driven Agents

2025년 10월 7일

[논문리뷰] Good Intentions Beyond ACL: Who Does NLP for Social Good, and Where?

Denis Peskoff이 arXiv에 게시한 'Good Intentions Beyond ACL: Who Does NLP for Social Good, and Where?' 논문에 대한 자세한 리뷰입니다.

#Review #NLP for Social Good #ACL Community #Scientometrics #Venue Analysis #Author Classification #Sustainable Development Goals #Neural Methods #Research Landscape

2025년 10월 7일

[논문리뷰] Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data

arXiv에 게시된 'Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models #Pretraining #Supervised Fine-tuning #Reasoning Data #Data Allocation #Diversity #Quality #Reinforcement Learning

2025년 10월 7일

[논문리뷰] Factuality Matters: When Image Generation and Editing Meet Structured Visuals

Boxiang Qiu이 arXiv에 게시한 'Factuality Matters: When Image Generation and Editing Meet Structured Visuals' 논문에 대한 자세한 리뷰입니다.

#Review #Structured Visuals #Image Generation #Image Editing #Multimodal Reasoning #Factual Fidelity #Chain-of-Thought #Evaluation Benchmark #Diffusion Models

2025년 10월 7일

[논문리뷰] EvolProver: Advancing Automated Theorem Proving by Evolving Formalized Problems via Symmetry and Difficulty

Xuanwu Wang이 arXiv에 게시한 'EvolProver: Advancing Automated Theorem Proving by Evolving Formalized Problems via Symmetry and Difficulty' 논문에 대한 자세한 리뷰입니다.

#Review #Automated Theorem Proving #Data Augmentation #Large Language Models #Formal Mathematics #Symmetry #Difficulty Evolution #Abstract Syntax Tree #Generalizability

2025년 10월 7일

[논문리뷰] Epistemic Diversity and Knowledge Collapse in Large Language Models

arXiv에 게시된 'Epistemic Diversity and Knowledge Collapse in Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models #Epistemic Diversity #Knowledge Collapse #Homogenization #Retrieval-Augmented Generation #LLM Evaluation #Information Diversity #Cultural Bias

2025년 10월 7일

[논문리뷰] Code4MeV2: a Research-oriented Code-completion Platform

arXiv에 게시된 'Code4MeV2: a Research-oriented Code-completion Platform' 논문에 대한 자세한 리뷰입니다.

#Review #Code Completion #Research Platform #Human-AI Interaction #Software Engineering #Open Science #JetBrains IDE Plugin #Telemetry #AI4SE

2025년 10월 7일

[논문리뷰] ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation

arXiv에 게시된 'ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Video Generation #Temporal Reasoning #World Simulation #Physical Consistency #Diffusion Models #Generative Models

2025년 10월 7일

[논문리뷰] Character Mixing for Video Generation

arXiv에 게시된 'Character Mixing for Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Character Mixing #Style Preservation #Multi-character Interaction #Text-to-Video #Cross-Domain Synthesis #Identity Preservation

2025년 10월 7일

[논문리뷰] Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails

Xinyuan Liu이 arXiv에 게시한 'Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Alignment #Self-Evolution #Behavioral Drift #Reinforcement Learning #Multi-Agent Systems #Alignment Tipping Process

2025년 10월 7일

[논문리뷰] Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

Fenglu Hong이 arXiv에 게시한 'Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Context Adaptation #Agentic AI #Self-Improving Systems #Prompt Engineering #Context Management #Dynamic Playbooks #Incremental Learning

2025년 10월 7일

[논문리뷰] AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning

Zeliang Zhang이 arXiv에 게시한 'AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-Agent Reinforcement Learning #Adversarial Co-evolution #LLM Safety #Jailbreak Attacks #Internalized Safety #Public Baseline #System Robustness

2025년 10월 7일

[논문리뷰] Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents

Boyi Wei이 arXiv에 게시한 'Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents' 논문에 대한 자세한 리뷰입니다.

#Review #Self-evolving Agents #LLM Safety #Misevolution #Emergent Risks #Model Evolution #Memory Evolution #Tool Evolution #Workflow Evolution

2025년 10월 6일

[논문리뷰] WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents

Neil Zhenqiang Gong이 arXiv에 게시한 'WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents' 논문에 대한 자세한 리뷰입니다.

#Review #Prompt Injection #Web Agents #Multimodal AI #Adversarial Attacks #Detection Benchmarking #Large Language Models #Image-based Detection #Text-based Detection

2025년 10월 6일

[논문리뷰] Triangle Splatting+: Differentiable Rendering with Opaque Triangles

Matheus Gadelha이 arXiv에 게시한 'Triangle Splatting+: Differentiable Rendering with Opaque Triangles' 논문에 대한 자세한 리뷰입니다.

#Review #Differentiable Rendering #3D Reconstruction #Novel View Synthesis #Triangles #Opaque Primitives #Game Engines #Gaussian Splatting #Mesh-based Rendering

2025년 10월 6일

[논문리뷰] TalkPlay-Tools: Conversational Music Recommendation with LLM Tool Calling

Juhan Nam이 arXiv에 게시한 'TalkPlay-Tools: Conversational Music Recommendation with LLM Tool Calling' 논문에 대한 자세한 리뷰입니다.

#Review #Conversational Recommendation #LLM Tool Calling #Music Recommendation #Multimodal Retrieval #Information Retrieval #Retrieval-Reranking #Semantic IDs

2025년 10월 6일

[논문리뷰] SurveyBench: How Well Can LLM(-Agents) Write Academic Surveys?

Shuo Wang이 arXiv에 게시한 'SurveyBench: How Well Can LLM(-Agents) Write Academic Surveys?' 논문에 대한 자세한 리뷰입니다.

#Review #LLM #LLM Agents #Academic Survey Generation #Evaluation Framework #Benchmark #Quiz-driven Evaluation #Content Quality Metrics

2025년 10월 6일