Review

[논문리뷰] A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning

Jiangmiao이 arXiv에 게시한 'A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Robotics #Reinforcement Learning (RL)#Vision-Language-Action (VLA) Models #Reward Modeling #Human-in-the-Loop #Dense Rewards #Generalization #Autoregressive Models

2025년 9월 22일

[논문리뷰] WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance

Ruibo Li이 arXiv에 게시한 'WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance' 논문에 대한 자세한 리뷰입니다.

#Review #Video Diffusion Models #3D/4D Generation #Training-Free Guidance #Camera Trajectory Control #Novel View Synthesis #Geometric Consistency #Inference-Time Optimization

2025년 9월 19일

[논문리뷰] Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding

Rynson W. H. Lau이 arXiv에 게시한 'Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding' 논문에 대한 자세한 리뷰입니다.

#Review #Spatio-Temporal Video Grounding #Multimodal Large Language Models #Zero-Shot Learning #Visual Grounding #Decomposed Spatio-Temporal Highlighting #Logit-Guided Re-attention #Temporal-Augmented Assembling

2025년 9월 19일

[논문리뷰] Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation

Xihui Liu이 arXiv에 게시한 'Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Autoregressive Models #Image Generation #Self-Supervised Learning #Visual Understanding #Masked Image Modeling #Contrastive Learning #Next-Token Prediction #LlamaGen

2025년 9월 19일

[논문리뷰] ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

Zehao Li이 arXiv에 게시한 'ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data' 논문에 대한 자세한 리뷰입니다.

#Review #Computer Use Agents #Vision-Language Models #Cross-Platform Data #GUI Automation #Data Scaling #Open-Source #Task Completion #GUI Grounding

2025년 9월 19일

[논문리뷰] RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

SpaceProduct이 arXiv에 게시한 'RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action (VLA) Model #Robot Manipulation #Human Demonstrations #Video Generative Pretraining #Ego-Centric Video #Trajectory Prediction #ActionVAE #Transformer

2025년 9월 19일

[논문리뷰] RecoWorld: Building Simulated Environments for Agentic Recommender Systems

Mingyuan Wu이 arXiv에 게시한 'RecoWorld: Building Simulated Environments for Agentic Recommender Systems' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic Recommender Systems #Simulated Environments #LLM-driven Simulation #Multi-turn Interaction #Reinforcement Learning #User Retention #Instruction Following #Multi-agent Systems

2025년 9월 19일

[논문리뷰] Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration

Zhilin Wang이 arXiv에 게시한 'Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration' 논문에 대한 자세한 리뷰입니다.

#Review #LLMs #Specification Alignment #Test-Time Deliberation #Safety-Behavior Trade-off #ALIGN3 #SPECBENCH #Prompt Engineering

2025년 9월 19일

[논문리뷰] MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks

Xijun Gu이 arXiv에 게시한 'MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks' 논문에 대한 자세한 리뷰입니다.

#Review #Instruction-based Image Editing #Dataset #Multi-modal LLM #Image Generation #Style Transfer #Multi-task Learning #Fine-tuning

2025년 9월 19일

[논문리뷰] Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs

Katharina von der Wense이 arXiv에 게시한 'Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Evaluation #Multiple-Choice QA #Tokenization #Prompt Sensitivity #Accuracy #Calibration #Model Ranking

2025년 9월 19일

[논문리뷰] FlowRL: Matching Reward Distributions for LLM Reasoning

Hengli Li이 arXiv에 게시한 'FlowRL: Matching Reward Distributions for LLM Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Large Language Models #Reward Distribution Matching #GFlowNets #Mode Collapse #Diverse Reasoning #Flow-Balanced Optimization

2025년 9월 19일

[논문리뷰] FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning

Jiashuo Liu이 arXiv에 게시한 'FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #Financial LLMs #Agent Benchmarking #Open-domain Search #Financial Reasoning #Time-Sensitive Data #Multi-hop QA #Tool Use

2025년 9월 19일

[논문리뷰] FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection

Zhewei Zhang이 arXiv에 게시한 'FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection' 논문에 대한 자세한 리뷰입니다.

#Review #Change Detection #Remote Sensing #Frequency-Spatial Analysis #Wavelet Transform #Attention Mechanism #Gated Fusion #Deep Learning

2025년 9월 19일

[논문리뷰] Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation

Kishan Panaganti이 arXiv에 게시한 'Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation' 논문에 대한 자세한 리뷰입니다.

#Review #Label-free Reinforcement Learning #LLMs #Self-improvement #Entropy Collapse #Novelty Reward #Test-Time RL #GRPO #Evolutionary Computing Principles

2025년 9월 19일

[논문리뷰] EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence

Qinghua Huang이 arXiv에 게시한 'EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language Models #Ultrasound Imaging #Medical Diagnosis #Mixture-of-Experts (MoE)#Instruction Tuning #Multimodal AI #Report Generation #VQA

2025년 9월 19일

[논문리뷰] AToken: A Unified Tokenizer for Vision

Mingze Xu이 arXiv에 게시한 'AToken: A Unified Tokenizer for Vision' 논문에 대한 자세한 리뷰입니다.

#Review #Unified Visual Tokenizer #Multimodal AI #Transformer Architecture #4D Representation #Adversarial-free Training #Reconstruction #Semantic Understanding #Generative Models

2025년 9월 19일

[논문리뷰] Wan-Animate: Unified Character Animation and Replacement with Holistic Replication

Mingyang Huang이 arXiv에 게시한 'Wan-Animate: Unified Character Animation and Replacement with Holistic Replication' 논문에 대한 자세한 리뷰입니다.

#Review #Character Animation #Video Replacement #Diffusion Models #Transformer #DiT #Relighting LoRA #Holistic Replication #Open-Source

2025년 9월 18일

[논문리뷰] THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning

Yicheng Pan이 arXiv에 게시한 'THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #Mathematical Reasoning #Tool-Integrated Reasoning #Reinforcement Learning #Hierarchical Optimization #Self-Correction #Large Language Models #Code Generation

2025년 9월 18일

[논문리뷰] SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

Zhun Wang이 arXiv에 게시한 'SteeringControl: Holistic Evaluation of Alignment Steering in LLMs' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Alignment #Representation Steering #Benchmark #Behavioral Entanglement #Bias Mitigation #Harmful Generation #Hallucination Control #Modular Framework

2025년 9월 18일

[논문리뷰] Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning

Zhou Yang이 arXiv에 게시한 'Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning' 논문에 대한 자세한 리뷰입니다.

#Review #Code Language Models #Machine Unlearning #Sensitive Memorization #Privacy #Gradient Ascent #Model Utility #Code Generation

2025년 9월 18일