Review

[논문리뷰] Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm

arXiv에 게시된 'Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Multimodal Reasoning #Temporal Understanding #Spatial Reasoning #Foundation Models #AI Benchmarking #In-Context Learning #Self-Consistency

2025년 11월 9일

[논문리뷰] The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms

Susumu Takeuchi이 arXiv에 게시한 'The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms' 논문에 대한 자세한 리뷰입니다.

#Review #Strong Lottery Ticket Hypothesis #Multi-Head Attention #Transformers #Neural Network Pruning #Overparameterization #Weight Initialization #Model Compression

2025년 11월 9일

[논문리뷰] Scaling Agent Learning via Experience Synthesis

arXiv에 게시된 'Scaling Agent Learning via Experience Synthesis' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #LLM Agents #Experience Synthesis #World Models #Curriculum Learning #Sim-to-Real Transfer #Web Agents

2025년 11월 9일

[논문리뷰] SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding

arXiv에 게시된 'SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding' 논문에 대한 자세한 리뷰입니다.

#Review #Spatial Reasoning #Video Understanding #Simulated Data #Instruction Tuning #Multimodal LLMs #Sim-to-Real Transfer #AI2-THOR

2025년 11월 9일

[논문리뷰] SAIL-RL: Guiding MLLMs in When and How to Think via Dual-Reward RL Tuning

arXiv에 게시된 'SAIL-RL: Guiding MLLMs in When and How to Think via Dual-Reward RL Tuning' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Large Language Models #Reinforcement Learning #Post-training #Reasoning #Dual-Reward System #Thinking Reward #Judging Reward #Hallucination Reduction

2025년 11월 9일

[논문리뷰] RDMA Point-to-Point Communication for LLM Systems

arXiv에 게시된 'RDMA Point-to-Point Communication for LLM Systems' 논문에 대한 자세한 리뷰입니다.

#Review #RDMA #LLM #Point-to-Point Communication #Disaggregated Inference #MoE Routing #KvCache #AWS EFA #NVIDIA ConnectX

2025년 11월 9일

[논문리뷰] NVIDIA Nemotron Nano V2 VL

arXiv에 게시된 'NVIDIA Nemotron Nano V2 VL' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language Model #Hybrid Architecture #Mamba-Transformer #Long-Context Understanding #Quantization #Efficient Inference #Document AI #Video AI

2025년 11월 9일

[논문리뷰] Learning Vision-Driven Reactive Soccer Skills for Humanoid Robots

arXiv에 게시된 'Learning Vision-Driven Reactive Soccer Skills for Humanoid Robots' 논문에 대한 자세한 리뷰입니다.

#Review #Humanoid Robot #Reinforcement Learning #RoboCup #Soccer Skills #Vision-Driven Control #Adversarial Motion Priors #Sim-to-Real #Perception-Action Coordination

2025년 11월 9일

[논문리뷰] How to Evaluate Speech Translation with Source-Aware Neural MT Metrics

Luisa Bentivogli이 arXiv에 게시한 'How to Evaluate Speech Translation with Source-Aware Neural MT Metrics' 논문에 대한 자세한 리뷰입니다.

#Review #Speech Translation #Neural MT Metrics #Source-Aware Evaluation #Automatic Speech Recognition (ASR)#Back-Translation (BT)#Cross-lingual Re-segmentation #COMET #MetricX

2025년 11월 9일

[논문리뷰] GUI-360: A Comprehensive Dataset and Benchmark for Computer-Using Agents

arXiv에 게시된 'GUI-360: A Comprehensive Dataset and Benchmark for Computer-Using Agents' 논문에 대한 자세한 리뷰입니다.

#Review #Computer-Using Agents #GUI Grounding #Screen Parsing #Action Prediction #Desktop Automation #Dataset #Benchmark #Multimodal Learning #LLM-augmented Data

2025년 11월 9일

[논문리뷰] EVTAR: End-to-End Try on with Additional Unpaired Visual Reference

arXiv에 게시된 'EVTAR: End-to-End Try on with Additional Unpaired Visual Reference' 논문에 대한 자세한 리뷰입니다.

#Review #Virtual Try-on #Diffusion Models #End-to-End Learning #Reference Images #Unpaired Data #Flow Matching #Transformer Architecture #Generative AI

2025년 11월 9일

[논문리뷰] Contamination Detection for VLMs using Multi-Modal Semantic Perturbation

arXiv에 게시된 'Contamination Detection for VLMs using Multi-Modal Semantic Perturbation' 논문에 대한 자세한 리뷰입니다.

#Review #VLM Contamination #Test-set Leakage #Multi-modal Perturbation #Generative Models #Generalization #Model Memorization #VLMs

2025년 11월 9일

[논문리뷰] Cambrian-S: Towards Spatial Supersensing in Video

Zihao Yang이 arXiv에 게시한 'Cambrian-S: Towards Spatial Supersensing in Video' 논문에 대한 자세한 리뷰입니다.

#Review #Spatial Supersensing #Video Understanding #Multimodal LLMs #Predictive Sensing #Memory Management #Event Segmentation #VSI-SUPER #Instruction Tuning

2025년 11월 9일

[논문리뷰] Benchmark Designers Should 'Train on the Test Set' to Expose Exploitable Non-Visual Shortcuts

arXiv에 게시된 'Benchmark Designers Should 'Train on the Test Set' to Expose Exploitable Non-Visual Shortcuts' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal LLMs #Benchmark Design #Non-Visual Shortcuts #Test-Set Stress-Test #Bias Mitigation #Model Evaluation #Benchmark Robustness

2025년 11월 9일

[논문리뷰] UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions

arXiv에 게시된 'UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions' 논문에 대한 자세한 리뷰입니다.

#Review #Joint Audio-Video Generation #Cross-Modal Interaction #Diffusion Transformer #Face-Aware Modulation #Classifier-Free Guidance #Multimodal AI #Generative Models

2025년 11월 9일

[논문리뷰] The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute

arXiv에 게시된 'The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute' 논문에 대한 자세한 리뷰입니다.

#Review #Sequential Reasoning #Parallel Self-Consistency #Inverse-Entropy Voting #LLM Reasoning #Test-Time Scaling #Inference Optimization #Iterative Refinement #Error Correction

2025년 11월 9일

[논문리뷰] TabTune: A Unified Library for Inference and Fine-Tuning Tabular Foundation Models

arXiv에 게시된 'TabTune: A Unified Library for Inference and Fine-Tuning Tabular Foundation Models' 논문에 대한 자세한 리뷰입니다.

#Review #Tabular Foundation Models #Fine-Tuning #PEFT #Meta-Learning #Calibration #Fairness #Unified Library #Benchmarking

2025년 11월 9일

[논문리뷰] Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning

arXiv에 게시된 'Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Tabular Data #In-Context Learning #Multi-Scale Attention #Sparse Attention #Foundation Models #Perceiver Architecture

2025년 11월 9일

[논문리뷰] MME-CC: A Challenging Multi-Modal Evaluation Benchmark of Cognitive Capacity

arXiv에 게시된 'MME-CC: A Challenging Multi-Modal Evaluation Benchmark of Cognitive Capacity' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal LLMs #Benchmark #Cognitive Capacity #Visual Reasoning #MLLM Evaluation #Error Analysis #Chain-of-Thought

2025년 11월 9일

[논문리뷰] LiveTradeBench: Seeking Real-World Alpha with Large Language Models

Jiaxuan You이 arXiv에 게시한 'LiveTradeBench: Seeking Real-World Alpha with Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Evaluation #Live Trading #Portfolio Management #Financial AI #Prediction Markets #Real-World Uncertainty #Agent Benchmarking

2025년 11월 9일