Review

[논문리뷰] Humanline: Online Alignment as Perceptual Loss

arXiv에 게시된 'Humanline: Online Alignment as Perceptual Loss' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Alignment #Online RLHF #Offline RLHF #Prospect Theory #Perceptual Loss #Human-Centric AI #Reinforcement Learning

2025년 10월 1일

[논문리뷰] Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents

arXiv에 게시된 'Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents' 논문에 대한 자세한 리뷰입니다.

#Review #GUI Agents #On-Device AI #Multimodal LLM #GUI Grounding #GUI Navigation #Reinforcement Learning #Supervised Fine-tuning #Synthetic Data

2025년 10월 1일

[논문리뷰] Estimating Time Series Foundation Model Transferability via In-Context Learning

Jun Qi이 arXiv에 게시한 'Estimating Time Series Foundation Model Transferability via In-Context Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Time Series Foundation Models #Transferability Estimation #In-Context Learning #Tabular Foundation Models #Model Selection #Entropy Profile #Meta-learning #Forecasting

2025년 10월 1일

[논문리뷰] EntroPE: Entropy-Guided Dynamic Patch Encoder for Time Series Forecasting

arXiv에 게시된 'EntroPE: Entropy-Guided Dynamic Patch Encoder for Time Series Forecasting' 논문에 대한 자세한 리뷰입니다.

#Review #Time Series Forecasting #Transformer #Dynamic Patching #Entropy #Predictive Uncertainty #Adaptive Encoding #Attention Mechanisms #Causal Transformer

2025년 10월 1일

[논문리뷰] Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local Attention

arXiv에 게시된 'Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local Attention' 논문에 대한 자세한 리뷰입니다.

#Review #Audio-Visual Speech Separation #Deep Learning #Efficiency #Discrete Lip Semantics #Global-Local Attention #Lightweight Models #VQ-VAE

2025년 10월 1일

[논문리뷰] DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively

arXiv에 게시된 'DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively' 논문에 대한 자세한 리뷰입니다.

#Review #AI Scientist #Autonomous Scientific Discovery #Bayesian Optimization #LLM-based Agents #SOTA-Surpassing #Findings Memory #Exploration-Exploitation

2025년 10월 1일

[논문리뷰] DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder

arXiv에 게시된 'DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Diffusion Models #Video Autoencoder #Deep Compression #Model Acceleration #Fine-tuning #Latent Space #Temporal Modeling

2025년 10월 1일

[논문리뷰] DA^2: Depth Anything in Any Direction

arXiv에 게시된 'DA^2: Depth Anything in Any Direction' 논문에 대한 자세한 리뷰입니다.

#Review #Panoramic Depth Estimation #Zero-shot Generalization #Data Curation #SphereViT #Spherical Geometry #360-degree Imaging #Vision Transformer

2025년 10월 1일

[논문리뷰] Context Is What You Need: The Maximum Effective Context Window for Real World Limits of LLMs

normanpaulsen이 arXiv에 게시한 'Context Is What You Need: The Maximum Effective Context Window for Real World Limits of LLMs' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models #Context Window #Effective Context Window #Model Performance #Hallucination Rates #RAG Systems #Token Limits

2025년 10월 1일

[논문리뷰] BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software

arXiv에 게시된 'BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Open-Source Software #Compilation #Benchmarking #Software Engineering #Error Resolution #Retrieval-Augmented Generation

2025년 10월 1일

[논문리뷰] Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective

arXiv에 게시된 'Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Large Language Models #Planning #Policy Gradient #Q-learning #Supervised Fine-Tuning #Diversity Collapse #Reward Hacking

2025년 10월 1일

[논문리뷰] Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models

arXiv에 게시된 'Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Process-Supervised RL #Large Language Models #Reasoning Models #Attention Mechanism #Efficient Exploration #Adaptive Sampling #Off-Policy Training

2025년 10월 1일

[논문리뷰] A Cartography of Open Collaboration in Open Source AI: Mapping Practices, Motivations, and Governance in 14 Open Large Language Model Projects

Jennifer Ding이 arXiv에 게시한 'A Cartography of Open Collaboration in Open Source AI: Mapping Practices, Motivations, and Governance in 14 Open Large Language Model Projects' 논문에 대한 자세한 리뷰입니다.

#Review #Open Source AI #LLM Development #Open Collaboration #Governance Models #Developer Motivations #Community Engagement #AI Ecosystem

2025년 10월 1일

[논문리뷰] Visual Jigsaw Post-Training Improves MLLMs

Lewei Lu이 arXiv에 게시한 'Visual Jigsaw Post-Training Improves MLLMs' 논문에 대한 자세한 리뷰입니다.

#Review #MLLMs #Post-training #Self-supervised Learning #Visual Understanding #Jigsaw Puzzles #RLVR #Multimodal Perception #Spatial Reasoning

2025년 9월 30일

[논문리뷰] StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs

Wei Jia이 arXiv에 게시한 'StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs' 논문에 대한 자세한 리뷰입니다.

#Review #Speech Tokenizer #Noise Robustness #Semantic Tokens #SpeechLLMs #Voting-LFQ #Consensus Training #Automatic Speech Recognition #Speech Synthesis

2025년 9월 30일

[논문리뷰] SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention

arXiv에 게시된 'SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Transformers #Sparse Attention #Linear Attention #Model Acceleration #Video Generation #Attention Mechanisms #Fine-tuning

2025년 9월 30일

[논문리뷰] SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer

arXiv에 게시된 'SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Diffusion Model #Linear Attention #Transformer #Long Video #Efficient Inference #Constant Memory #Low-Cost Training #RTX Deployment

2025년 9월 30일

[논문리뷰] RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark

Yuran Wang이 arXiv에 게시한 'RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark' 논문에 대한 자세한 리뷰입니다.

#Review #Unified Models #Multimodal AI #Benchmark #Capability Synergy #Visual Understanding #Image Generation #Dual-Evaluation Protocol

2025년 9월 30일

[논문리뷰] Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards

Binxing Jiao이 arXiv에 게시한 'Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #LLM Reasoning #Policy Valuation #Markov Decision Process #Diversity #Math Reasoning #Verifiable Rewards

2025년 9월 30일

[논문리뷰] OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing

Huanyu Zhang이 arXiv에 게시한 'OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Image Generation #Image Editing #Multimodal AI #Dataset #Instruction Following #Taxonomy #GPT-40

2025년 9월 30일