Review

[논문리뷰] Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Harsh Raj이 arXiv에 게시한 'Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces' 논문에 대한 자세한 리뷰입니다.

#Review #AI Agents #LLM Evaluation #Benchmarking #Command Line Interface #Software Engineering #Realistic Tasks #Error Analysis

2026년 1월 22일

[논문리뷰] Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model

arXiv에 게시된 'Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model' 논문에 대한 자세한 리뷰입니다.

#Review #Code Diffusion Models #Large Language Models #Continual Pretraining #Code Generation #Code Editing #Masked Language Models #Code Reasoning

2026년 1월 22일

[논문리뷰] Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders

arXiv에 게시된 'Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Image Generation #Diffusion Models #Representation Autoencoder #Latent Space #Large-Scale Models #Unified Models #Noise Scheduling

2026년 1월 22일

[논문리뷰] SAMTok: Representing Any Mask with Two Words

arXiv에 게시된 'SAMTok: Representing Any Mask with Two Words' 논문에 대한 자세한 리뷰입니다.

#Review #Mask Tokenization #Multimodal LLMs #Pixel-wise Vision-Language #Reinforcement Learning #Segmentation Anything Model #Discrete Representation

2026년 1월 22일

[논문리뷰] Rethinking Composed Image Retrieval Evaluation: A Fine-Grained Benchmark from Image Editing

Dingkun Long이 arXiv에 게시한 'Rethinking Composed Image Retrieval Evaluation: A Fine-Grained Benchmark from Image Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Composed Image Retrieval #Fine-Grained Evaluation #Image Editing #Benchmark #Multimodal LLM #Synthetic Data #Compositional Reasoning

2026년 1월 22일

[논문리뷰] Qwen3-TTS Technical Report

arXiv에 게시된 'Qwen3-TTS Technical Report' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Speech (TTS)#Multilingual #Voice Cloning #Controllable Speech #Streaming #Speech Tokenization #Language Models #Low-latency

2026년 1월 22일

[논문리뷰] OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation

arXiv에 게시된 'OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Unified Visual Encoder #Image Understanding #Image Generation #VAE #Vision Transformer #Multimodal Learning #Reconstruction #Contrastive Learning

2026년 1월 22일

[논문리뷰] Numba-Accelerated 2D Diffusion-Limited Aggregation: Implementation and Fractal Characterization

arXiv에 게시된 'Numba-Accelerated 2D Diffusion-Limited Aggregation: Implementation and Fractal Characterization' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion-Limited Aggregation #Fractal Dimension #Numba #JIT Compilation #Monte Carlo Simulation #Pattern Formation #Laplacian Growth #Non-equilibrium Statistical Mechanics

2026년 1월 22일

[논문리뷰] Learning to Discover at Test Time

arXiv에 게시된 'Learning to Discover at Test Time' 논문에 대한 자세한 리뷰입니다.

#Review #Test-Time Training #Reinforcement Learning #Scientific Discovery #LLM Optimization #GPU Kernel Engineering #Algorithm Design #Single-Cell Analysis

2026년 1월 22일

[논문리뷰] LLM-in-Sandbox Elicits General Agentic Intelligence

arXiv에 게시된 'LLM-in-Sandbox Elicits General Agentic Intelligence' 논문에 대한 자세한 리뷰입니다.

#Review #LLM-in-Sandbox #Agentic Intelligence #Code Sandbox #Reinforcement Learning #Generalization #Tool Use #Multi-Modal Generation #Long-Context Processing

2026년 1월 22일

[논문리뷰] HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

arXiv에 게시된 'HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding' 논문에 대한 자세한 리뷰입니다.

#Review #Streaming Video Understanding #KV Cache Management #Hierarchical Memory #MLLMs #Low Latency #Training-free #Memory Efficiency

2026년 1월 22일

[논문리뷰] EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience

Linsen Guo이 arXiv에 게시한 'EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience' 논문에 대한 자세한 리뷰입니다.

#Review #Computer Use Agent #Synthetic Experience #Evolutionary Learning #Reinforcement Learning #Direct Preference Optimization #GUI Automation #Scalable Infrastructure #Verifiable Synthesis

2026년 1월 22일

[논문리뷰] Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning

arXiv에 게시된 'Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning' 논문에 대한 자세한 리뷰입니다.

#Review #Video Models #Visuomotor Control #Robot Policy #Fine-tuning #Diffusion Models #World Models #Model-based Planning #Imitation Learning

2026년 1월 22일

[논문리뷰] BayesianVLA: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries

arXiv에 게시된 'BayesianVLA: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action Models #Bayesian Decomposition #Latent Action Queries #Information Collapse #OOD Generalization #Robot Manipulation #Pointwise Mutual Information

2026년 1월 22일

[논문리뷰] ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion

arXiv에 게시된 'ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion' 논문에 대한 자세한 리뷰입니다.

#Review #3D Mesh Generation #Animated 3D Models #Temporal Diffusion #Video-to-4D #Deep Learning #Generative Models #Topology Consistency

2026년 1월 22일

[논문리뷰] 360Anything: Geometry-Free Lifting of Images and Videos to 360°

arXiv에 게시된 '360Anything: Geometry-Free Lifting of Images and Videos to 360°' 논문에 대한 자세한 리뷰입니다.

#Review #Panorama Generation #Diffusion Transformers #Geometry-Free Learning #Latent Encoding #Seam Artifacts #Camera Pose Estimation #Video Outpainting

2026년 1월 22일

[논문리뷰] sangkuriang: A pseudo-spectral Python library for Korteweg-de Vries soliton simulation

arXiv에 게시된 'sangkuriang: A pseudo-spectral Python library for Korteweg-de Vries soliton simulation' 논문에 대한 자세한 리뷰입니다.

#Review #Nonlinear Wave Physics #Soliton Simulation #Korteweg-de Vries Equation #Pseudo-spectral Methods #Adaptive Time Integration #Python Library #Computational Physics

2026년 1월 21일

[논문리뷰] XR: Cross-Modal Agents for Composed Image Retrieval

arXiv에 게시된 'XR: Cross-Modal Agents for Composed Image Retrieval' 논문에 대한 자세한 리뷰입니다.

#Review #Composed Image Retrieval #Cross-Modal Agents #Multimodal Reasoning #Training-free Framework #Information Retrieval #Agentic AI #Progressive Retrieval

2026년 1월 21일

[논문리뷰] Typhoon OCR: Open Vision-Language Model For Thai Document Extraction

arXiv에 게시된 'Typhoon OCR: Open Vision-Language Model For Thai Document Extraction' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language Model #OCR #Thai Language Processing #Document Understanding #Low-Resource Language #Data Synthesis #Fine-tuning #Layout Analysis

2026년 1월 21일

[논문리뷰] Typhoon ASR Real-time: FastConformer-Transducer for Thai Automatic Speech Recognition

arXiv에 게시된 'Typhoon ASR Real-time: FastConformer-Transducer for Thai Automatic Speech Recognition' 논문에 대한 자세한 리뷰입니다.

#Review #Thai ASR #Real-time Speech Recognition #FastConformer-Transducer #Low-latency #Text Normalization #Dialect Adaptation #Data Curation #Streaming ASR

2026년 1월 21일