Review

[논문리뷰] Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies

arXiv에 게시된 'Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Large Language Models #Policy Optimization #Interpretability #Transformer #Internal Policy #Entropy Analysis

2025년 12월 23일

[논문리뷰] Active Intelligence in Video Avatars via Closed-loop World Modeling

Cheng Meng이 arXiv에 게시한 'Active Intelligence in Video Avatars via Closed-loop World Modeling' 논문에 대한 자세한 리뷰입니다.

#Review #Video Avatars #Active Intelligence #World Models #Closed-loop Reasoning #POMDP #Generative AI #Hierarchical Planning #Cognitive Architecture

2025년 12월 23일

[논문리뷰] WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion

arXiv에 게시된 'WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion' 논문에 대한 자세한 리뷰입니다.

#Review #Novel View Synthesis #3D Geometry Propagation #Video Diffusion Models #Gaussian Splatting #Autoregressive Generation #Spatio-Temporal Noise #Geometric Consistency

2025년 12월 22일

[논문리뷰] Understanding Syllogistic Reasoning in LLMs from Formal and Natural Language Perspectives

Sujata Ghosh이 arXiv에 게시한 'Understanding Syllogistic Reasoning in LLMs from Formal and Natural Language Perspectives' 논문에 대한 자세한 리뷰입니다.

#Review #Syllogistic Reasoning #Large Language Models (LLMs)#Belief Bias #Natural Language Understanding (NLU)#Formal Logic #Prompt Engineering #Self-Consistency #Cognitive Psychology

2025년 12월 22일

[논문리뷰] UCoder: Unsupervised Code Generation by Internal Probing of Large Language Models

Yuqing Ma이 arXiv에 게시한 'UCoder: Unsupervised Code Generation by Internal Probing of Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Unsupervised Learning #Code Generation #Large Language Models (LLMs)#Internal Probing #Self-Bootstrapping #Consensus Clustering #Code Intelligence

2025년 12월 22일

[논문리뷰] The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding

Ziwei Liu이 arXiv에 게시한 'The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding' 논문에 대한 자세한 리뷰입니다.

#Review #Unified Autoencoding #Prism Hypothesis #Semantic Representations #Pixel Representations #Frequency-Band Modulator #Foundation Models #Spectral Bias #Generative Models

2025년 12월 22일

[논문리뷰] StoryMem: Multi-shot Long Video Storytelling with Memory

arXiv에 게시된 'StoryMem: Multi-shot Long Video Storytelling with Memory' 논문에 대한 자세한 리뷰입니다.

#Review #Video Storytelling #Multi-shot Video Generation #Memory Mechanism #Diffusion Models #Cross-shot Consistency #Latent Video Diffusion #ROPE Shift #Keyframe Selection

2025년 12월 22일

[논문리뷰] Region-Constraint In-Context Generation for Instructional Video Editing

arXiv에 게시된 'Region-Constraint In-Context Generation for Instructional Video Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Video Editing #In-Context Learning #Diffusion Models #Region-Constraint #Instruction-based Editing #Latent Space Regularization #Attention Space Regularization #Large-scale Dataset

2025년 12월 22일

[논문리뷰] Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs

arXiv에 게시된 'Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs' 논문에 대한 자세한 리뷰입니다.

#Review #Latent Variable Models #Variational Autoencoder (VAE)#Reinforcement Learning (RL)#Exploration #Large Language Models (LLMs)#Vision-Language Models (VLMs)#Controllable Generation #Reasoning Strategies

2025년 12월 22일

[논문리뷰] Real2Edit2Real: Generating Robotic Demonstrations via a 3D Control Interface

Liliang Chen이 arXiv에 게시한 'Real2Edit2Real: Generating Robotic Demonstrations via a 3D Control Interface' 논문에 대한 자세한 리뷰입니다.

#Review #Robotics #Demonstration Generation #3D Control Interface #Data Efficiency #Visuomotor Policy Learning #Spatial Generalization #Depth Map #Video Generation

2025년 12월 22일

[논문리뷰] QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation

Lu Cheng이 arXiv에 게시한 'QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Dynamic RAG #Hallucination Detection #Corpus Statistics #Uncertainty Quantification #Pre-training Data #LLM Calibration #Infini-gram #Multi-hop QA

2025년 12월 22일

[논문리뷰] Name That Part: 3D Part Segmentation and Naming

Alan Yuille이 arXiv에 게시한 'Name That Part: 3D Part Segmentation and Naming' 논문에 대한 자세한 리뷰입니다.

#Review #3D Semantic Segmentation #Part Naming #Open-Vocabulary #LLM #Set Alignment #Geometric Deep Learning #Annotation Engine #Affordance Description

2025년 12월 22일

[논문리뷰] MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive, and MCP-Augmented Environments

arXiv에 게시된 'MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive, and MCP-Augmented Environments' 논문에 대한 자세한 리뷰입니다.

#Review #Mobile Agents #GUI Benchmarking #Agent-User Interaction #Tool-Augmented Agents #Model Context Protocol (MCP)#Long-Horizon Tasks #Reproducible Evaluation #Android Environment

2025년 12월 22일

[논문리뷰] MatSpray: Fusing 2D Material World Knowledge on 3D Geometry

arXiv에 게시된 'MatSpray: Fusing 2D Material World Knowledge on 3D Geometry' 논문에 대한 자세한 리뷰입니다.

#Review #3D Reconstruction #Material Estimation #Diffusion Models #Gaussian Splatting #Inverse Rendering #PBR #Relighting #Neural Merger

2025년 12월 22일

[논문리뷰] LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding

arXiv에 게시된 'LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding' 논문에 대한 자세한 리뷰입니다.

#Review #dLLM #Parallel Decoding #Lookahead #Inference Acceleration #Token Filling Order #Branch Parallelism #Diffusion Models

2025년 12월 22일

[논문리뷰] LoGoPlanner: Localization Grounded Navigation Policy with Metric-aware Visual Geometry

Yuan Shen이 arXiv에 게시한 'LoGoPlanner: Localization Grounded Navigation Policy with Metric-aware Visual Geometry' 논문에 대한 자세한 리뷰입니다.

#Review #Autonomous Navigation #End-to-end Learning #Localization Grounded #Visual Geometry #Metric-aware Perception #Diffusion Policy #RGB-D

2025년 12월 22일

[논문리뷰] Infinite-Homography as Robust Conditioning for Camera-Controlled Video Generation

arXiv에 게시된 'Infinite-Homography as Robust Conditioning for Camera-Controlled Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Camera Control #Homography #Diffusion Models #Data Augmentation #Novel View Synthesis #Pose Fidelity

2025년 12월 22일

[논문리뷰] GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators

arXiv에 게시된 'GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Environment Simulation #Co-evolution #Curriculum Learning #Data Efficiency #Reinforcement Learning #Adaptive Simulation #Difficulty Alignment

2025년 12월 22일

[논문리뷰] Does It Tie Out? Towards Autonomous Legal Agents in Venture Capital

arXiv에 게시된 'Does It Tie Out? Towards Autonomous Legal Agents in Venture Capital' 논문에 대한 자세한 리뷰입니다.

#Review #Legal AI #Venture Capital #Due Diligence #Capitalization Table #Multi-document Reasoning #Knowledge Graph #World Model #Neuro-Symbolic AI

2025년 12월 22일

[논문리뷰] DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI

arXiv에 게시된 'DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Data Preparation #Workflow Automation #Data-Centric AI #Synthetic Data #Multi-Agent System #Framework #Reproducibility

2025년 12월 22일