Review

[논문리뷰] SeGPruner: Semantic-Geometric Visual Token Pruner for 3D Question Answering

arXiv에 게시된 'SeGPruner: Semantic-Geometric Visual Token Pruner for 3D Question Answering' 논문에 대한 자세한 리뷰입니다.

#Review #3D Question Answering #Vision-Language Models #Visual Token Pruning #Semantic-Awareness #Geometry-Guided

2026년 3월 31일

[논문리뷰] PoseDreamer: Scalable and Photorealistic Human Data Generation Pipeline with Diffusion Models

arXiv에 게시된 'PoseDreamer: Scalable and Photorealistic Human Data Generation Pipeline with Diffusion Models' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Human Mesh Recovery #Synthetic Data #Direct Preference Optimization #Data Generation Pipeline #3D-2D Consistency

2026년 3월 31일

[논문리뷰] OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training

arXiv에 게시된 'OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training' 논문에 대한 자세한 리뷰입니다.

#Review #Continual Pre-training #Model Merging #Distribution Vector #Bayesian Optimization #LLM Adaptation

2026년 3월 31일

[논문리뷰] MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models

arXiv에 게시된 'MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models #Chain-of-Thought #Monitorability #Benchmark #AI Safety #Stress-Test #Faithfulness

2026년 3월 31일

[논문리뷰] MMFace-DiT: A Dual-Stream Diffusion Transformer for High-Fidelity Multimodal Face Generation

Ajita Rattani이 arXiv에 게시한 'MMFace-DiT: A Dual-Stream Diffusion Transformer for High-Fidelity Multimodal Face Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Transformer #Multimodal Face Generation #Cross-Modal Fusion #RoPE Attention #Controlled Generation

2026년 3월 31일

[논문리뷰] LongCat-Next: Lexicalizing Modalities as Discrete Tokens

arXiv에 게시된 'LongCat-Next: Lexicalizing Modalities as Discrete Tokens' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodality #Autoregressive Modeling #Discrete Tokenization #Vision Transformer #Audio Tokenization #Mixture-of-Experts #Next-Token Prediction

2026년 3월 31일

[논문리뷰] Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells

arXiv에 게시된 'Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells' 논문에 대한 자세한 리뷰입니다.

#Review #Generative Model #Single-cell Transcriptomics #Discrete Diffusion Model #Virtual Cell #Perturbation Prediction #Cellular World Model

2026년 3월 31일

[논문리뷰] Learn2Fold: Structured Origami Generation with World Model Planning

Zhengzhong Tu이 arXiv에 게시한 'Learn2Fold: Structured Origami Generation with World Model Planning' 논문에 대한 자세한 리뷰입니다.

#Review #Origami Generation #Neuro-symbolic Framework #World Model #Constraint-Aware Planning #Program Induction #Spatial Intelligence

2026년 3월 31일

[논문리뷰] It Takes Two: A Duet of Periodicity and Directionality for Burst Flicker Removal

arXiv에 게시된 'It Takes Two: A Duet of Periodicity and Directionality for Burst Flicker Removal' 논문에 대한 자세한 리뷰입니다.

#Review #Flicker Removal #Vision Transformer #Phase Correlation #Autocorrelation #Wavelet Transform #Burst Photography

2026년 3월 31일

[논문리뷰] How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation

arXiv에 게시된 'How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation' 논문에 대한 자세한 리뷰입니다.

#Review #Auditory Knowledge #Large Language Models #Large Audio Language Models #AKB-2000 #Cascade Evaluation #Audio-grounded Evaluation

2026년 3월 31일

[논문리뷰] Ghost-FWL: A Large-Scale Full-Waveform LiDAR Dataset for Ghost Detection and Removal

Takahiro Kado이 arXiv에 게시한 'Ghost-FWL: A Large-Scale Full-Waveform LiDAR Dataset for Ghost Detection and Removal' 논문에 대한 자세한 리뷰입니다.

#Review #Full-Waveform LiDAR #Ghost Removal #Masked Autoencoder #Mobile LiDAR #Dataset #Representation Learning

2026년 3월 31일

[논문리뷰] FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration

arXiv에 게시된 'FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration' 논문에 대한 자세한 리뷰입니다.

#Review #Scientific Idea Generation #Flow-Guided MCTS #GFlowNet #Test-Time Evolution #Isolation Island Paradigm #Generative Reward Model #Autonomous Research

2026년 3월 31일

[논문리뷰] FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization

arXiv에 게시된 'FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Large Language Models #Future-KL #Policy Optimization #GRPO #Chain-of-Thought #Credit Assignment

2026년 3월 31일

[논문리뷰] Extend3D: Town-Scale 3D Generation

arXiv에 게시된 'Extend3D: Town-Scale 3D Generation' 논문에 대한 자세한 리뷰입니다.

#Review #3D Scene Generation #Training-free #Latent Flow Model #Overlapping Patch-wise Flow #Under-noising #SDEdit #3D-aware Optimization

2026년 3월 31일

[논문리뷰] Distilling Human-Aligned Privacy Sensitivity Assessment from Large Language Models

arXiv에 게시된 'Distilling Human-Aligned Privacy Sensitivity Assessment from Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #privacy evaluation #knowledge distillation #de-identification #LLM-as-a-Judge #textual privacy

2026년 3월 31일

[논문리뷰] Distilling Conversations: Abstract Compression of Conversational Audio Context for LLM-based ASR

arXiv에 게시된 'Distilling Conversations: Abstract Compression of Conversational Audio Context for LLM-based ASR' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal ASR #Large Language Models #Conversational Context #Abstract Compression #Contextual Biasing #Latent Bottleneck

2026년 3월 31일

[논문리뷰] CutClaw: Agentic Hours-Long Video Editing via Music Synchronization

arXiv에 게시된 'CutClaw: Agentic Hours-Long Video Editing via Music Synchronization' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Language Models #Video Editing #Audio-Visual Alignment #Multi-Agent System #Hierarchical Planning

2026년 3월 31일

[논문리뷰] CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence

Hong Zhang이 arXiv에 게시한 'CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence' 논문에 대한 자세한 리뷰입니다.

#Review #Embodied Intelligence #Simulation Infrastructure #CARLA #AirSim #Air-Ground Cooperation #Unreal Engine

2026년 3월 31일

[논문리뷰] AutoWeather4D: Autonomous Driving Video Weather Conversion via G-Buffer Dual-Pass Editing

arXiv에 게시된 'AutoWeather4D: Autonomous Driving Video Weather Conversion via G-Buffer Dual-Pass Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Autonomous Driving #Weather Synthesis #G-buffer #3D-aware Editing #Neural Rendering #Video Diffusion #Relighting

2026년 3월 31일

[논문리뷰] ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactions

Wangmeng Zuo이 arXiv에 게시한 'ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactions' 논문에 대한 자세한 리뷰입니다.

#Review #4D Reconstruction #Hand-Object Interaction #Foundation Models #Articulated Objects #Monocular Video #Optimization

2026년 3월 31일