Skip to main content

Paper Reviews by AI

2024

RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation
·3747 words·18 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Question Answering ๐Ÿข Renmin University of China
RetroLLM: ๊ฒ€์ƒ‰๊ณผ ์ƒ์„ฑ์„ ํ†ตํ•ฉํ•œ RAG ์‹œ์Šคํ…œ
Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models
·3489 words·17 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Computer Vision Image Generation ๐Ÿข Inha University
์‹ค์‹œ๊ฐ„ ์ด๋ฏธ์ง€ ๋ณดํ˜ธ, ๋”ฅํŽ˜์ดํฌ ๋Œ€๋น„์ฑ….
MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes
·2949 words·14 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Computer Vision 3D Vision ๐Ÿข Peking University
MOVIS๋Š” ์‹ค๋‚ด ์žฅ๋ฉด์— ๋Œ€ํ•œ ๋ฉ€ํ‹ฐ-๊ฐ์ฒด novel view synthesis์—์„œ ๊ตฌ์กฐ์  ์ธ์‹์„ ํ–ฅ์ƒ์‹œ์ผœ ์ผ๊ด€์„ฑ ์žˆ๊ณ  ์‚ฌ์‹ค์ ์ธ novel view๋ฅผ ์ƒ์„ฑํ•ฉ๋‹ˆ๋‹ค.
MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization
·2262 words·11 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Machine Learning Reinforcement Learning ๐Ÿข ETH Zurich
์ •๋ณด ์ด๋“์œผ๋กœ ๊ฐ•ํ™” ํ•™์Šต ํƒ์ƒ‰์„ ๊ฐ•ํ™”.
Just a Simple Transformation is Enough for Data Protection in Vertical Federated Learning
·2263 words·11 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Machine Learning Federated Learning ๐Ÿข MIPT
๊ฐ„๋‹จํ•œ ๋ณ€ํ™˜๋งŒ์œผ๋กœ ์ˆ˜์ง ์—ฐํ•ฉ ํ•™์Šต์—์„œ ๋ฐ์ดํ„ฐ ๋ณดํ˜ธ ๊ฐ€๋Šฅ.
IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations
·3273 words·16 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Computer Vision 3D Vision ๐Ÿข Chinese University of Hong Kong
IDArb: Decomposition under varied lights.
GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training
·2232 words·11 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Multimodal Learning Vision-Language Models ๐Ÿข Shanghai Jiao Tong University
GeoX: MLLM๋ณด๋‹ค ๋›ฐ์–ด๋‚œ ๊ธฐํ•˜ํ•™์  ๋ฌธ์ œ ํ•ด๊ฒฐ์‚ฌ!
ColorFlow: Retrieval-Augmented Image Sequence Colorization
·2273 words·11 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Computer Vision Image Generation ๐Ÿข Tsinghua University
๋งŒํ™” ์ฑ„์ƒ‰ ์ž๋™ํ™”: ColorFlow๋Š” ID ์ผ๊ด€์„ฑ์„ ์œ ์ง€ํ•˜๋ฉด์„œ ํ‘๋ฐฑ ๋งŒํ™” ์‹œํ€€์Šค๋ฅผ ์ฑ„์ƒ‰ํ•ฉ๋‹ˆ๋‹ค.
Causal Diffusion Transformers for Generative Modeling
·4953 words·24 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Computer Vision Image Generation ๐Ÿข ByteDance Research
CausalFusion์€ ํ™•์‚ฐ ๋ฐ ์ž๊ธฐ ํšŒ๊ท€ ๋ชจ๋ธ์„ ๊ฒฐํ•ฉํ•˜์—ฌ ์ƒ์„ฑ ๋ชจ๋ธ๋ง์—์„œ ์ตœ์ฒจ๋‹จ ๊ฒฐ๊ณผ๋ฅผ ๋‹ฌ์„ฑํ•˜๊ณ  ์ƒˆ๋กœ์šด ๊ธฐ๋Šฅ์„ ๊ฐ€๋Šฅํ•˜๊ฒŒ ํ•ฉ๋‹ˆ๋‹ค.
VividFace: A Diffusion-Based Hybrid Framework for High-Fidelity Video Face Swapping
·1707 words·9 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Computer Vision Image Generation ๐Ÿข CUHK MMLab
VividFace: ์ฒซ ๋ฒˆ์งธ ํ™•์‚ฐ ๊ธฐ๋ฐ˜ ๋น„๋””์˜ค ์–ผ๊ตด ๋ฐ”๊พธ๊ธฐ ํ”„๋ ˆ์ž„์›Œํฌ๋กœ ๊ณ ์ถฉ์‹ค๋„ ๊ฒฐ๊ณผ ์ œ๊ณต.
Smaller Language Models Are Better Instruction Evolvers
·4310 words·21 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Beijing University of Posts and Telecommunications
์†Œํ˜• ์–ธ์–ด ๋ชจ๋ธ์ด ๋” ๋‚˜์€ ๋ช…๋ น ์ƒ์„ฑ์ž!
Reliable, Reproducible, and Really Fast Leaderboards with Evalica
·1243 words·6 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข JetBrains
Evalica: ๋ฒค์น˜๋งˆํ‚น์„ ์‰ฝ๊ณ  ๋น ๋ฅด๊ณ  ์‹ ๋ขฐํ•  ์ˆ˜ ์žˆ๊ฒŒ ๋งŒ๋“œ๋Š” ํˆดํ‚ท
GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs
·2657 words·13 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Computer Vision 3D Vision ๐Ÿข Hong Kong University of Science and Technology
GaussianProperty๋Š” LMM์„ ์‚ฌ์šฉํ•˜์—ฌ 3D ๊ฐ€์šฐ์‹œ์•ˆ์— ๋ฌผ๋ฆฌ์  ์†์„ฑ์„ ํ†ตํ•ฉํ•˜๋Š” ํ›ˆ๋ จ ์—†๋Š” ํ”„๋ ˆ์ž„์›Œํฌ๋กœ, ๋ฌผ๋ฆฌ ๊ธฐ๋ฐ˜ ์‹œ๋ฎฌ๋ ˆ์ด์…˜ ๋ฐ ๋กœ๋ด‡ ์ฅ๊ธฐ์™€ ๊ฐ™์€ ๋‹ค์šด์ŠคํŠธ๋ฆผ ์ž‘์—…์„ ๊ฐ€๋Šฅํ•˜๊ฒŒ ํ•ฉ๋‹ˆ๋‹ค.
DynamicScaler: Seamless and Scalable Video Generation for Panoramic Scenes
·1754 words·9 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Computer Vision Image Generation ๐Ÿข Google DeepMind
DynamicScaler๋Š” ํ…์ŠคํŠธ๋‚˜ ์ด๋ฏธ์ง€์—์„œ ๊ธด ๋Š๊น€ ์—†๋Š” ํŒŒ๋…ธ๋ผ๋งˆ ๋น„๋””์˜ค๋ฅผ ์ƒ์„ฑํ•˜๋ฉฐ, ํ•ด์ƒ๋„์™€ ์ข…ํšก๋น„์— ๊ด€๊ณ„์—†์ด ์ผ๊ด€๋œ ์›€์ง์ž„์„ ์œ ์ง€ํ•ฉ๋‹ˆ๋‹ค.
TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies
·2744 words·13 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers AI Applications Robotics ๐Ÿข Microsoft Research
TraceVLA: ๊ณผ๊ฑฐ์˜ ์›€์ง์ž„์„ ์‹œ๊ฐ์ ์œผ๋กœ ๋ณด์—ฌ์คŒ์œผ๋กœ์จ ๋กœ๋ด‡์˜ ์‹œ๊ณต๊ฐ„์  ์ธ์‹์„ ํ–ฅ์ƒ์‹œํ‚ต๋‹ˆ๋‹ค.
SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video
·3662 words·18 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Computer Vision 3D Vision ๐Ÿข KAIST
SplineGS: ์‹ค์‹œ๊ฐ„ ๋™์  3D ์žฅ๋ฉด์„ ์œ„ํ•œ ๊ฐ•๋ ฅํ•œ ๋ชจ์…˜ ์ ์‘ํ˜• ์Šคํ”Œ๋ผ์ธ.
SCBench: A KV Cache-Centric Analysis of Long-Context Methods
·4642 words·22 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Microsoft Corporation
SCBench๋Š” ๋ฉ€ํ‹ฐํ„ด ๋ฐ ๋ฉ€ํ‹ฐ๋ฆฌํ€˜์ŠคํŠธ ์‹œ๋‚˜๋ฆฌ์˜ค์—์„œ ์žฅ๋ฌธ ๋งฅ๋ฝ ๋ฉ”์„œ๋“œ๋ฅผ ํ‰๊ฐ€ํ•˜๋Š” ์ƒˆ๋กœ์šด ๋ฒค์น˜๋งˆํฌ์ž…๋‹ˆ๋‹ค.
RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning
·1911 words·9 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers AI Applications Robotics ๐Ÿข UC Berkeley
RLDG๋Š” ๊ฐ•ํ™” ํ•™์Šต์„ ํ†ตํ•ด ์ƒ์„ฑ๋œ ๊ณ ํ’ˆ์งˆ ๋ฐ์ดํ„ฐ๋กœ ๋ฒ”์šฉ ๋กœ๋ด‡ ์ •์ฑ…์˜ ์„ฑ๋Šฅ์„ ํ–ฅ์ƒ์‹œํ‚ค๋Š” ํš๊ธฐ์ ์ธ ๋ฐฉ๋ฒ•์ž…๋‹ˆ๋‹ค.
Prompt2Perturb (P2P): Text-Guided Diffusion-Based Adversarial Attacks on Breast Ultrasound Images
·1580 words·8 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Computer Vision Image Generation ๐Ÿข University of British Columbia
P2P: ํ…์ŠคํŠธ ๊ธฐ๋ฐ˜์˜ ์ƒˆ๋กœ์šด ์ ๋Œ€์  ๊ณต๊ฒฉ์œผ๋กœ ์˜๋ฃŒ ์˜์ƒ DNN์˜ ์ทจ์•ฝ์„ฑ ๊ณต๋žต
LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity
·3571 words·17 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Computer Vision Video Understanding ๐Ÿข Princeton University
LinGen: ๋ถ„ ๋‹จ์œ„ ๊ณ ํ•ด์ƒ๋„ ํ…์ŠคํŠธ-ํˆฌ-๋น„๋””์˜ค ์ƒ์„ฑ, ์„ ํ˜• ๊ณ„์‚ฐ ๋ณต์žก๋„๋กœ ํšจ์œจ์„ฑ ๊ทน๋Œ€ํ™”