Review

[논문리뷰] Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting

arXiv에 게시된 'Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting' 논문에 대한 자세한 리뷰입니다.

#Review #Supervised Fine-Tuning (SFT)#Catastrophic Forgetting #Entropy-Adaptive Fine-Tuning (EAFT)#Large Language Models (LLMs)#Domain Adaptation #Reinforcement Learning (RL)#Confident Conflicts

2026년 1월 7일

[논문리뷰] E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models

arXiv에 게시된 'E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Flow Models #Entropy-aware Sampling #Group Relative Policy Optimization #SDE #Human Preference Alignment #Image Generation

2026년 1월 7일

[논문리뷰] X-MuTeST: A Multilingual Benchmark for Explainable Hate Speech Detection and A Novel LLM-consulted Explanation Framework

Shwetank Shekhar Singh이 arXiv에 게시한 'X-MuTeST: A Multilingual Benchmark for Explainable Hate Speech Detection and A Novel LLM-consulted Explanation Framework' 논문에 대한 자세한 리뷰입니다.

#Review #Hate Speech Detection #Explainable AI (XAI)#Multilingual NLP #Large Language Models (LLMs)#Attention Mechanism #N-gram Explanations #Human Rationales #Benchmark Dataset

2026년 1월 6일

[논문리뷰] UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision

XinYu Sun이 arXiv에 게시한 'UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision' 논문에 대한 자세한 리뷰입니다.

#Review #Unified Multimodal Models #Self-Supervised Learning #Text-to-Image Generation #Multi-Agent Framework #Cognitive Pattern Reconstruction #Cycle-Consistency #Conduction Aphasia

2026년 1월 6일

[논문리뷰] Steerability of Instrumental-Convergence Tendencies in LLMs

j-hoscilowic이 arXiv에 게시한 'Steerability of Instrumental-Convergence Tendencies in LLMs' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Steerability #Instrumental Convergence #AI Safety #AI Security #Open-Weight Models #Prompt Engineering #Model Control #Behavioral Alignment

2026년 1월 6일

[논문리뷰] SOP: A Scalable Online Post-Training System for Vision-Language-Action Models

arXiv에 게시된 'SOP: A Scalable Online Post-Training System for Vision-Language-Action Models' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action Models #Online Post-training #Scalable Robot Learning #Distributed Systems #Multi-task Learning #Imitation Learning #Reinforcement Learning

2026년 1월 6일

[논문리뷰] Parallel Latent Reasoning for Sequential Recommendation

Yuning Jiang이 arXiv에 게시한 'Parallel Latent Reasoning for Sequential Recommendation' 논문에 대한 자세한 리뷰입니다.

#Review #Sequential Recommendation #Latent Reasoning #Parallel Processing #Computational Scaling #Mixture of Experts #Contrastive Learning #Transformer Architecture

2026년 1월 6일

[논문리뷰] NitroGen: An Open Foundation Model for Generalist Gaming Agents

arXiv에 게시된 'NitroGen: An Open Foundation Model for Generalist Gaming Agents' 논문에 대한 자세한 리뷰입니다.

#Review #Generalist Agents #Foundation Models #Behavior Cloning #Video Games #Action Extraction #Multi-game #Embodied AI

2026년 1월 6일

[논문리뷰] MiMo-V2-Flash Technical Report

arXiv에 게시된 'MiMo-V2-Flash Technical Report' 논문에 대한 자세한 리뷰입니다.

#Review #Mixture-of-Experts #Sliding Window Attention #Multi-Token Prediction #Multi-Teacher On-Policy Distillation #Reinforcement Learning #Long-Context Modeling #Agentic AI

2026년 1월 6일

[논문리뷰] LTX-2: Efficient Joint Audio-Visual Foundation Model

Andrew Kvochko이 arXiv에 게시한 'LTX-2: Efficient Joint Audio-Visual Foundation Model' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal AI #Text-to-Audio-Video #Diffusion Transformer #Cross-Modal Attention #Classifier-Free Guidance #Efficient Inference #Foundation Model

2026년 1월 6일

[논문리뷰] InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields

arXiv에 게시된 'InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields' 논문에 대한 자세한 리뷰입니다.

#Review #Depth Estimation #Neural Implicit Fields #Arbitrary Resolution #Fine-Grained #Novel View Synthesis #Vision Transformer #Synth4K Benchmark

2026년 1월 6일

[논문리뷰] FFP-300K: Scaling First-Frame Propagation for Generalizable Video Editing

Peng Tang이 arXiv에 게시한 'FFP-300K: Scaling First-Frame Propagation for Generalizable Video Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Video Editing #First-Frame Propagation (FFP)#Large-Scale Dataset #Generative Models #Temporal Consistency #Spatio-Temporal RoPE #Self-Distillation

2026년 1월 6일

[논문리뷰] DreamStyle: A Unified Framework for Video Stylization

arXiv에 게시된 'DreamStyle: A Unified Framework for Video Stylization' 논문에 대한 자세한 리뷰입니다.

#Review #Video Stylization #Unified Framework #Diffusion Models #LoRA #Data Curation #Multi-modal Input #Image-to-Video

2026년 1월 6일

[논문리뷰] CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving

Tao Feng이 arXiv에 게시한 'CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal LLMs #Visual Reasoning #Mathematical Problem Solving #Knowledge Internalization #Reinforcement Learning #Cognitive-Inspired AI #Perception-Reasoning Alignment

2026년 1월 6일

[논문리뷰] VINO: A Unified Visual Generator with Interleaved OmniModal Context

Kun Gai이 arXiv에 게시한 'VINO: A Unified Visual Generator with Interleaved OmniModal Context' 논문에 대한 자세한 리뷰입니다.

#Review #Unified Generation #Multimodal Diffusion #Vision-Language Model #Image Editing #Video Editing #Interleaved Context #Progressive Training #Diffusion Transformer

2026년 1월 5일

[논문리뷰] VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation

arXiv에 게시된 'VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Visual Autoregressive Models #Reinforcement Learning #Policy Conflicts #GRPO #Text-to-Image Generation #Credit Assignment #Multi-scale Generation

2026년 1월 5일

[논문리뷰] Toward Stable Semi-Supervised Remote Sensing Segmentation via Co-Guidance and Co-Fusion

Shiying Wang이 arXiv에 게시한 'Toward Stable Semi-Supervised Remote Sensing Segmentation via Co-Guidance and Co-Fusion' 논문에 대한 자세한 리뷰입니다.

#Review #Semi-Supervised Learning #Semantic Segmentation #Remote Sensing #Vision Foundation Models #Pseudo-Label Drift #Co-Guidance #Feature Fusion

2026년 1월 5일

[논문리뷰] Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes

Shuo Yang이 arXiv에 게시한 'Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Text-Guided Image Editing #Object-Level Transformation #Geometric Transformation #Diffusion Models #GRPO #Scene Editing #Spatially Grounded Rewards

2026년 1월 5일

[논문리뷰] SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving

arXiv에 게시된 'SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving' 논문에 대한 자세한 리뷰입니다.

#Review #Software Engineering #Issue Resolution #Supervised Fine-tuning (SFT)#Large Language Models (LLMs)#Hybrid Dataset #Error Masking #Curriculum Learning #Test-Time Scaling (TTS)#Generative Verifiers

2026년 1월 5일

[논문리뷰] Recursive Language Models

arXiv에 게시된 'Recursive Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Recursive Language Models #Large Language Models #Long Context Processing #Inference Scaling #REPL Environment #Task Decomposition #Sub-LM Calls #Context Management

2026년 1월 5일