Review

[논문리뷰] BiManiBench: A Hierarchical Benchmark for Evaluating Bimanual Coordination of Multimodal Large Language Models

arXiv에 게시된 'BiManiBench: A Hierarchical Benchmark for Evaluating Bimanual Coordination of Multimodal Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Bimanual Manipulation #MLLMs #Robotics Benchmark #Spatial Reasoning #Action Planning #End-Effector Control #Embodied AI #Multimodal LLMs

2026년 2월 18일

[논문리뷰] Visual Persuasion: What Influences Decisions of Vision-Language Models?

Nikhil Singh이 arXiv에 게시한 'Visual Persuasion: What Influences Decisions of Vision-Language Models?' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language Models #Visual Persuasion #Prompt Optimization #Image Generation #AI Agent Behavior #Interpretability #Behavioral Evaluation

2026년 2월 17일

[논문리뷰] UniT: Unified Multimodal Chain-of-Thought Test-time Scaling

Animesh Sinha이 arXiv에 게시한 'UniT: Unified Multimodal Chain-of-Thought Test-time Scaling' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal AI #Chain-of-Thought #Test-time Scaling #Unified Models #Iterative Reasoning #Image Generation #Visual Reasoning #Self-Correction

2026년 2월 17일

[논문리뷰] Understanding vs. Generation: Navigating Optimization Dilemma in Multimodal Models

Liwei Wang이 arXiv에 게시한 'Understanding vs. Generation: Navigating Optimization Dilemma in Multimodal Models' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Models #Generative AI #Understanding #Reason-Reflect-Refine (R3)#Reinforcement Learning (RL)#Text-to-Image Generation #Optimization Dilemma #Image Editing

2026년 2월 17일

[논문리뷰] Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?

Ivan Oseledets이 arXiv에 게시한 'Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?' 논문에 대한 자세한 리뷰입니다.

#Review #Sparse Autoencoders #Interpretability #Neural Network Internals #Evaluation Baselines #Feature Decomposition #LLMs #Mechanistic Interpretability

2026년 2월 17일

[논문리뷰] STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens

Zhilong Zheng이 arXiv에 게시한 'STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Large Language Models #Training Stability #Policy Optimization #Spurious Tokens #Entropy Regularization #Gradient Modulation

2026년 2월 17일

[논문리뷰] Revisiting the Platonic Representation Hypothesis: An Aristotelian View

Maria Brbić이 arXiv에 게시한 'Revisiting the Platonic Representation Hypothesis: An Aristotelian View' 논문에 대한 자세한 리뷰입니다.

#Review #Representational Similarity #Null Calibration #Permutation Testing #Confounder #Neural Network Representation #Platonic Representation Hypothesis #Aristotelian Representation Hypothesis

2026년 2월 17일

[논문리뷰] ResearchGym: Evaluating Language Model Agents on Real-World AI Research

Arman Cohan이 arXiv에 게시한 'ResearchGym: Evaluating Language Model Agents on Real-World AI Research' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #AI Research #Benchmark #Closed-loop Research #Agent Evaluation #Reproducibility #Real-world Tasks

2026년 2월 17일

[논문리뷰] Prescriptive Scaling Reveals the Evolution of Language Model Capabilities

Sham Kakade이 arXiv에 게시한 'Prescriptive Scaling Reveals the Evolution of Language Model Capabilities' 논문에 대한 자세한 리뷰입니다.

#Review #Prescriptive Scaling #Language Models #Capability Boundaries #Quantile Regression #Scaling Laws #Temporal Stability #I-Optimal Design #Benchmark Saturation

2026년 2월 17일

[논문리뷰] On Surprising Effectiveness of Masking Updates in Adaptive Optimizers

arXiv에 게시된 'On Surprising Effectiveness of Masking Updates in Adaptive Optimizers' 논문에 대한 자세한 리뷰입니다.

#Review #Adaptive Optimizers #Gradient Masking #LLM Training #Geometric Regularization #Momentum Alignment #RMSProp #Perplexity #Deep Learning

2026년 2월 17일

[논문리뷰] Learning Native Continuation for Action Chunking Flow Policies

Di Zhang이 arXiv에 게시한 'Learning Native Continuation for Action Chunking Flow Policies' 논문에 대한 자세한 리뷰입니다.

#Review #Action Chunking #Flow-based Policies #Trajectory Continuation #Robotics #Vision-Language-Action (VLA)#Denoising Dynamics #Schedule-shaped Guidance #Real-time Control

2026년 2월 17일

[논문리뷰] Geometry-Aware Rotary Position Embedding for Consistent Video World Model

arXiv에 게시된 'Geometry-Aware Rotary Position Embedding for Consistent Video World Model' 논문에 대한 자세한 리뷰입니다.

#Review #Video World Model #Generative AI #Transformer #Positional Encoding #3D Consistency #View Synthesis #Sparse Attention #Loop Closure

2026년 2월 17일

[논문리뷰] GLM-5: from Vibe Coding to Agentic Engineering

GLM-5 Team이 arXiv에 게시한 'GLM-5: from Vibe Coding to Agentic Engineering' 논문에 대한 자세한 리뷰입니다.

#Review #Foundation Model #Agentic AI #Reinforcement Learning #Sparse Attention #Software Engineering #Long-Context Models #GPU Optimization

2026년 2월 17일

[논문리뷰] Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook

Ming Li이 arXiv에 게시한 'Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook' 논문에 대한 자세한 리뷰입니다.

#Review #AI Agent Societies #Socialization #Large Language Models (LLMs)#Collective Dynamics #Semantic Analysis #Network Analysis #Moltbook

2026년 2월 17일

[논문리뷰] ClinAlign: Scaling Healthcare Alignment from Clinician Preference

Chaohe Zhang이 arXiv에 게시한 'ClinAlign: Scaling Healthcare Alignment from Clinician Preference' 논문에 대한 자세한 리뷰입니다.

#Review #Healthcare AI #LLM Alignment #Clinician Preference #Rubric-based RLHF #Medical LLMs #Data Curation #HealthBench #Principle-based Supervision

2026년 2월 17일

[논문리뷰] Causal-JEPA: Learning World Models through Object-Level Latent Interventions

arXiv에 게시된 'Causal-JEPA: Learning World Models through Object-Level Latent Interventions' 논문에 대한 자세한 리뷰입니다.

#Review #World Models #Object-Centric Representations #Latent Interventions #Masked Prediction #Causal Inductive Bias #Joint Embedding Predictive Architecture (JEPA)#Visual Question Answering (VQA)#Model Predictive Control (MPC)

2026년 2월 17일

[논문리뷰] COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression

arXiv에 게시된 'COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression' 논문에 대한 자세한 리뷰입니다.

#Review #Transformer Compression #Matrix Factorization #Sparse Dictionary Learning #Post-Training Quantization #Procrustes Analysis #Orthogonal Dictionary #Dynamic Allocation

2026년 2월 17일

[논문리뷰] UniWeTok: An Unified Binary Tokenizer with Codebook Size 2^{128} for Unified Multimodal Large Language Model

arXiv에 게시된 'UniWeTok: An Unified Binary Tokenizer with Codebook Size 2^{128} for Unified Multimodal Large Language Model' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal LLM #Visual Tokenizer #Binary Codebook #Image Generation #Semantic Extraction #Pre-Post Distillation #Hybrid Architecture

2026년 2월 16일

[논문리뷰] REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents

arXiv에 게시된 'REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents' 논문에 대한 자세한 리뷰입니다.

#Review #Long-Horizon Search #Multimodal LLM #Task Synthesis #Agentic Mid-Training #Reinforcement Learning #Tool-Augmented Agents #Web Search

2026년 2월 16일

[논문리뷰] Qute: Towards Quantum-Native Database

Surui Tang이 arXiv에 게시한 'Qute: Towards Quantum-Native Database' 논문에 대한 자세한 리뷰입니다.

#Review #Quantum Database #Quantum Computing #SQL Compilation #Hybrid Optimizer #Quantum Indexing #Fidelity-Preserving Storage #Grover's Algorithm

2026년 2월 16일