Review

[논문리뷰] From Perception to Action: An Interactive Benchmark for Vision Reasoning

Zhiqiang Hu이 arXiv에 게시한 'From Perception to Action: An Interactive Benchmark for Vision Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language Models #Physical Reasoning #Interactive AI #3D Benchmark #Mechanical Puzzles #Spatial Packing #Embodied AI

2026년 2월 24일

[논문리뷰] FlowPrefill: Decoupling Preemption from Prefill Scheduling Granularity to Mitigate Head-of-Line Blocking in LLM Serving

Jidong Zhai이 arXiv에 게시한 'FlowPrefill: Decoupling Preemption from Prefill Scheduling Granularity to Mitigate Head-of-Line Blocking in LLM Serving' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Serving #Head-of-Line Blocking #Preemption #Prefill Scheduling #Time-to-First-Token (TTFT)#SLO-aware Scheduling #Operator-Level Preemption #Event-Driven Scheduling

2026년 2월 24일

[논문리뷰] DREAM: Deep Research Evaluation with Agentic Metrics

arXiv에 게시된 'DREAM: Deep Research Evaluation with Agentic Metrics' 논문에 대한 자세한 리뷰입니다.

#Review #Deep Research Evaluation #Agentic Evaluation #LLM Evaluation #Capability Parity #Factuality #Temporal Validity #Reasoning Quality #Research Agents #Mirage of Synthesis

2026년 2월 24일

[논문리뷰] Conv-FinRe: A Conversational and Longitudinal Benchmark for Utility-Grounded Financial Recommendation

arXiv에 게시된 'Conv-FinRe: A Conversational and Longitudinal Benchmark for Utility-Grounded Financial Recommendation' 논문에 대한 자세한 리뷰입니다.

#Review #Financial Recommendation #Conversational AI #Large Language Models #Utility-Grounded Evaluation #Behavioral Finance #Stock Recommendation #Longitudinal Benchmark #Inverse Optimization

2026년 2월 24일

[논문리뷰] Communication-Inspired Tokenization for Structured Image Representations

arXiv에 게시된 'Communication-Inspired Tokenization for Structured Image Representations' 논문에 대한 자세한 리뷰입니다.

#Review #Image Tokenization #Structured Representation #Attentive Encoding #Flow Matching #Semantic Alignment #Compositional Generalization #Transformer Architecture

2026년 2월 24일

[논문리뷰] Aletheia tackles FirstProof autonomously

arXiv에 게시된 'Aletheia tackles FirstProof autonomously' 논문에 대한 자세한 리뷰입니다.

#Review #Mathematics Research Agent #Autonomous Problem Solving #FirstProof Challenge #Gemini 3 Deep Think #Mathematical Proof Generation #Human-AI Interaction #Deep Learning

2026년 2월 24일

[논문리뷰] Adaptive Text Anonymization: Learning Privacy-Utility Trade-offs via Prompt Optimization

arXiv에 게시된 'Adaptive Text Anonymization: Learning Privacy-Utility Trade-offs via Prompt Optimization' 논문에 대한 자세한 리뷰입니다.

#Review #Text Anonymization #Large Language Models #Prompt Optimization #Privacy-Utility Trade-offs #Evolutionary Algorithms #Multi-objective Optimization #Data Privacy

2026년 2월 24일

[논문리뷰] tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction

Zhiqin Chen이 arXiv에 게시한 'tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction' 논문에 대한 자세한 리뷰입니다.

#Review #3D Reconstruction #Test-Time Training (TTT)#Autoregressive Modeling #Long-Context #Gaussian Splatting #Neural Radiance Fields #Large Reconstruction Models

2026년 2월 23일

[논문리뷰] VLANeXt: Recipes for Building Strong VLA Models

arXiv에 게시된 'VLANeXt: Recipes for Building Strong VLA Models' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action Models #Robotics #Imitation Learning #Foundation Models #Ablation Study #Generalization #LIBERO Benchmark #Time-Series Forecasting

2026년 2월 23일

[논문리뷰] TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics

arXiv에 게시된 'TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics' 논문에 대한 자세한 리뷰입니다.

#Review #Robotics #Reward Modeling #Vision-Language Models #Zero-Shot Learning #Token Probabilities #Progress Estimation #Behavior Cloning #Manipulation

2026년 2월 23일

[논문리뷰] SkillOrchestra: Learning to Route Agents via Skill Transfer

arXiv에 게시된 'SkillOrchestra: Learning to Route Agents via Skill Transfer' 논문에 대한 자세한 리뷰입니다.

#Review #Agent Orchestration #Skill Transfer #LLM Routing #Performance-Cost Trade-off #Routing Collapse #Multi-turn Dialogue #Skill Handbook #Reinforcement Learning

2026년 2월 23일

[논문리뷰] SimVLA: A Simple VLA Baseline for Robotic Manipulation

arXiv에 게시된 'SimVLA: A Simple VLA Baseline for Robotic Manipulation' 논문에 대한 자세한 리뷰입니다.

#Review #Robotic Manipulation #Vision-Language-Action (VLA) Models #Baseline Model #Modular Design #Flow Matching #Zero-Shot Generalization #Standardized Training #Efficiency

2026년 2월 23일

[논문리뷰] SenTSR-Bench: Thinking with Injected Knowledge for Time-Series Reasoning

Haotian Lin이 arXiv에 게시한 'SenTSR-Bench: Thinking with Injected Knowledge for Time-Series Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #Time-Series Reasoning #Knowledge Injection #Large Language Models (LLMs)#Reinforcement Learning (RL)#Diagnostic AI #Multimodal AI #SenTSR-Bench

2026년 2월 23일

[논문리뷰] RoboCurate: Harnessing Diversity with Action-Verified Neural Trajectory for Robot Learning

arXiv에 게시된 'RoboCurate: Harnessing Diversity with Action-Verified Neural Trajectory for Robot Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Robot Learning #Synthetic Data Generation #Action Verification #Neural Trajectory #Video Generative Models #Imitation Learning #Data Diversity

2026년 2월 23일

[논문리뷰] Nacrith: Neural Lossless Compression via Ensemble Context Modeling and High-Precision CDF Coding

robtacconelli이 arXiv에 게시한 'Nacrith: Neural Lossless Compression via Ensemble Context Modeling and High-Precision CDF Coding' 논문에 대한 자세한 리뷰입니다.

#Review #Lossless Compression #Neural Compression #Language Models #Arithmetic Coding #Context Mixing #Ensemble Prediction #CDF Quantization #GPU Acceleration

2026년 2월 23일

[논문리뷰] Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device

arXiv에 게시된 'Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal AI #Vision-Language Models #Diffusion Models #Mobile Devices #Edge Computing #Model Efficiency #Unified Architecture #Real-time Inference

2026년 2월 23일

[논문리뷰] ManCAR: Manifold-Constrained Latent Reasoning with Adaptive Test-Time Computation for Sequential Recommendation

arXiv에 게시된 'ManCAR: Manifold-Constrained Latent Reasoning with Adaptive Test-Time Computation for Sequential Recommendation' 논문에 대한 자세한 리뷰입니다.

#Review #Sequential Recommendation #Latent Reasoning #Manifold Constraint #Adaptive Computation #Graph Neural Networks #Variational Inference #Teacher Scheduling #Drift Prevention

2026년 2월 23일

[논문리뷰] Learning Cross-View Object Correspondence via Cycle-Consistent Mask Prediction

Hongyang Wei이 arXiv에 게시한 'Learning Cross-View Object Correspondence via Cycle-Consistent Mask Prediction' 논문에 대한 자세한 리뷰입니다.

#Review #Cross-View Correspondence #Object Segmentation #Cycle-Consistency #Test-Time Training #Vision Foundation Models #Self-Supervision #Egocentric-Exocentric

2026년 2월 23일

[논문리뷰] Large Causal Models for Temporal Causal Discovery

Dario Simionato이 arXiv에 게시한 'Large Causal Models for Temporal Causal Discovery' 논문에 대한 자세한 리뷰입니다.

#Review #Causal Discovery #Temporal Models #Foundation Models #Transformer Architecture #Zero-shot Learning #Time-series Data #Scalability #Multi-dataset Pretraining

2026년 2월 23일

[논문리뷰] K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model

Ion Stoica이 arXiv에 게시한 'K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model' 논문에 대한 자세한 리뷰입니다.

#Review #LLM #GPU Kernel Optimization #Code Generation #World Model #Evolutionary Search #Program Synthesis #High-Performance Computing

2026년 2월 23일