Review

[논문리뷰] Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations

Noam Koenigstein이 arXiv에 게시한 'Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations' 논문에 대한 자세한 리뷰입니다.

#Review #Saliency Maps #Explainable AI (XAI)#Taxonomy #Evaluation Framework #Faithfulness Metrics #Contrastive Explanations #Granularity

2025년 11월 23일

[논문리뷰] Planning with Sketch-Guided Verification for Physics-Aware Video Generation

Shayegan Omidshafiei이 arXiv에 게시한 'Planning with Sketch-Guided Verification for Physics-Aware Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Motion Planning #Physics-Aware AI #Multimodal Verification #Diffusion Models #Test-Time Optimization #Sketch-Guided

2025년 11월 23일

[논문리뷰] Parrot: Persuasion and Agreement Robustness Rating of Output Truth -- A Sycophancy Robustness Benchmark for LLMs

arXiv에 게시된 'Parrot: Persuasion and Agreement Robustness Rating of Output Truth -- A Sycophancy Robustness Benchmark for LLMs' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Sycophancy #Model Robustness #AI Alignment #Benchmark #Confidence Calibration #Behavioral Taxonomy #Social Influence #Epistemic Collapse

2025년 11월 23일

[논문리뷰] OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe

arXiv에 게시된 'OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Reasoning #Large Multimodal Models #Supervised Fine-tuning #Reinforcement Learning #Data Curation #Open-source #Multimodal Benchmarks

2025년 11월 23일

[논문리뷰] OmniScientist: Toward a Co-evolving Ecosystem of Human and AI Scientists

Weiquan Lin이 arXiv에 게시한 'OmniScientist: Toward a Co-evolving Ecosystem of Human and AI Scientists' 논문에 대한 자세한 리뷰입니다.

#Review #AI Scientist #Large Language Models (LLMs)#Human-AI Collaboration #Scientific Ecosystem #Research Automation #Omni Scientific Protocol (OSP)#ScienceArena #Knowledge Graph

2025년 11월 23일

[논문리뷰] O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents

arXiv에 게시된 'O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents' 논문에 대한 자세한 리뷰입니다.

#Review #Memory System #LLM Agents #Personalization #User Profiling #Hierarchical Retrieval #Long-Term Interaction #Self-Evolving Agents #Contextual Consistency

2025년 11월 23일

[논문리뷰] Multi-Faceted Attack: Exposing Cross-Model Vulnerabilities in Defense-Equipped Vision-Language Models

arXiv에 게시된 'Multi-Faceted Attack: Exposing Cross-Model Vulnerabilities in Defense-Equipped Vision-Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language Models (VLMs)#Adversarial Attack #Jailbreaking #Reward Hacking #Content Moderation Bypass #Cross-Model Transferability #Safety Vulnerabilities

2025년 11월 23일

[논문리뷰] MergeDNA: Context-aware Genome Modeling with Dynamic Tokenization through Token Merging

arXiv에 게시된 'MergeDNA: Context-aware Genome Modeling with Dynamic Tokenization through Token Merging' 논문에 대한 자세한 리뷰입니다.

#Review #Genome Modeling #Dynamic Tokenization #Token Merging #Context-aware Learning #DNA Foundation Models #Transformer Architecture #Multi-omics

2025년 11월 23일

[논문리뷰] Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight

arXiv에 게시된 'Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action (VLA) Models #Visual Foresight #Diffusion Transformer (DiT)#Robotics #Multimodal Learning #Adaptive Temporal Ensemble #Latent Actions

2025년 11월 23일

[논문리뷰] Loomis Painter: Reconstructing the Painting Process

arXiv에 게시된 'Loomis Painter: Reconstructing the Painting Process' 논문에 대한 자세한 리뷰입니다.

#Review #Painting Process Generation #Video Diffusion Models #Media Transfer #Reverse Painting #Dataset Curation #Perceptual Distance Profile #Artistic Workflow #Generative AI

2025년 11월 23일

[논문리뷰] Insights from the ICLR Peer Review and Rebuttal Process

Nedjma Ousidhoum이 arXiv에 게시한 'Insights from the ICLR Peer Review and Rebuttal Process' 논문에 대한 자세한 리뷰입니다.

#Review #Peer Review #Rebuttal Process #ICLR #Score Dynamics #LLM Analysis #Reviewer Engagement #Academic Publishing #OpenReview

2025년 11월 23일

[논문리뷰] GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization

arXiv에 게시된 'GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization' 논문에 대한 자세한 리뷰입니다.

#Review #Geolocalization #Agentic Models #Visual Reasoning #Web-Augmented #Multimodal LLMs #Reinforcement Learning #Tool Use #GeoBench

2025년 11월 23일

[논문리뷰] Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Models

Serena Yeung-Levy이 arXiv에 게시한 'Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Models' 논문에 대한 자세한 리뷰입니다.

#Review #Small Multimodal Models #LLM Downscaling #Perception Bottleneck #Reasoning Bottleneck #Visual Extraction Tuning #Chain-of-Thought Reasoning #Multimodal Learning

2025년 11월 23일

[논문리뷰] Diversity Has Always Been There in Your Visual Autoregressive Models

Yaxing Wang이 arXiv에 게시한 'Diversity Has Always Been There in Your Visual Autoregressive Models' 논문에 대한 자세한 리뷰입니다.

#Review #Visual Autoregressive Models #Diversity Collapse #Generative Diversity #Soft-Suppression Regularization #Soft-Amplification Regularization #Training-Free #Image Generation #Singular Value Decomposition

2025년 11월 23일

[논문리뷰] Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO

arXiv에 게시된 'Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Next Event Prediction #Reinforcement Learning #Vision-Language Model #Video Diffusion Model #Joint Optimization #Multimodal AI #Procedural Learning

2025년 11월 20일

[논문리뷰] V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models

Baijiong Lin이 arXiv에 게시한 'V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Reasoning Benchmark #Chain-of-Frame #Evaluation #Multimodal AI #Physical Dynamics #Spatial Cognition #Pattern Inference

2025년 11월 20일

[논문리뷰] TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval

arXiv에 게시된 'TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval' 논문에 대한 자세한 리뷰입니다.

#Review #Information Retrieval #Turkish Language #Late-Interaction Models #ColBERT #Dense Retrieval #MUVERA #Benchmarking #Low-Resource NLP #Fine-tuning

2025년 11월 20일

[논문리뷰] TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding

arXiv에 게시된 'TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding' 논문에 대한 자세한 리뷰입니다.

#Review #Long Video Understanding #Hybrid Mamba-Transformer #Vision-Language Model #Token Compression #Vision-to-Text Aggregation #Efficient LLM #Multimodal AI

2025년 11월 20일

[논문리뷰] Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation

Xinyan Chen이 arXiv에 게시한 'Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Visual Generation #Textual Reasoning #Interleaving #Large Multimodal Models (LMMs)#Chain-of-Thought (CoT)#Zero-shot Learning #Supervised Fine-tuning (SFT)#Reinforcement Learning (RL)

2025년 11월 20일

[논문리뷰] Step-Audio-R1 Technical Report

arXiv에 게시된 'Step-Audio-R1 Technical Report' 논문에 대한 자세한 리뷰입니다.

#Review #Audio Reasoning #Multimodal LLMs #Modality-Grounded Reasoning Distillation (MGRD)#Chain-of-Thought #Reinforcement Learning #Audio Understanding #Self-Distillation

2025년 11월 20일