Skip to main content

Paper Reviews by AI

2024

Multi-LLM Text Summarization
·2623 words·13 mins· loading · loading
AI Generated πŸ€— Daily Papers Natural Language Processing Text Summarization 🏒 UC Santa Cruz
λ‹€μˆ˜μ˜ κ±°λŒ€ μ–Έμ–΄ λͺ¨λΈ(LLM)을 ν™œμš©ν•œ ν˜μ‹ μ μΈ μž₯λ¬Έ μš”μ•½ ν”„λ ˆμž„μ›Œν¬κ°€ μ œμ‹œλ˜μ–΄ μš”μ•½ ν’ˆμ§ˆμ„ μ΅œλŒ€ 3λ°° ν–₯μƒμ‹œμΌ°μŠ΅λ‹ˆλ‹€!
MotiF: Making Text Count in Image Animation with Motion Focal Loss
·2819 words·14 mins· loading · loading
AI Generated πŸ€— Daily Papers Computer Vision Video Understanding 🏒 Brown University
MotiF: μ›€μ§μž„μ— μ΄ˆμ μ„ 맞좘 손싀 ν•¨μˆ˜λ‘œ ν…μŠ€νŠΈ 기반 이미지 μ• λ‹ˆλ©”μ΄μ…˜ κ°œμ„ 
Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning
·4085 words·20 mins· loading · loading
AI Generated πŸ€— Daily Papers Natural Language Processing Large Language Models 🏒 Microsoft Research
λŒ€κ·œλͺ¨ μ–Έμ–΄ λͺ¨λΈλ“€μ˜ 앙상블을 톡해 λ³΅μž‘ν•œ μΆ”λ‘  문제λ₯Ό λ”μš± 효과적으둜 ν•΄κ²°ν•˜λŠ” μƒˆλ‘œμš΄ ν”„λ ˆμž„μ›Œν¬, LE-MCTSλ₯Ό μ œμ•ˆν•©λ‹ˆλ‹€!
CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up
·3581 words·17 mins· loading · loading
AI Generated πŸ€— Daily Papers Computer Vision Image Generation 🏒 National University of Singapore
CLEAR: μ„ ν˜•ν™”λœ μ–΄ν…μ…˜μœΌλ‘œ 고해상도 이미지 생성 속도λ₯Ό 획기적으둜 높이닀!
UIP2P: Unsupervised Instruction-based Image Editing via Cycle Edit Consistency
·2616 words·13 mins· loading · loading
AI Generated πŸ€— Daily Papers Computer Vision Image Generation 🏒 ETH Zurich
비지도 ν•™μŠ΅ 기반 μˆœν™˜ νŽΈμ§‘ 일관성(CEC) ν™œμš©, μ§€μ‹œμ–΄ 기반 이미지 νŽΈμ§‘μ˜ μƒˆλ‘œμš΄ 지평을 μ—΄λ‹€!
TOMG-Bench: Evaluating LLMs on Text-based Open Molecule Generation
·3930 words·19 mins· loading · loading
AI Generated πŸ€— Daily Papers Natural Language Processing Large Language Models 🏒 Hong Kong Polytechnic University
TOMG-Bench: LLM 기반 μ˜€ν”ˆ λΆ„μž 생성 벀치마크 μ œμ‹œ! 25개 LLM 평가 및 μƒˆλ‘œμš΄ instruction tuning 데이터셋 OpenMolIns 곡개둜, μ˜€ν”ˆμ†ŒμŠ€ LLM의 μ„±λŠ₯ ν–₯상 및 λΆ„μž 발견의 μƒˆλ‘œμš΄ κ°€λŠ₯μ„± μ œμ‹œ!
Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
·1340 words·7 mins· loading · loading
AI Generated πŸ€— Daily Papers Multimodal Learning Multimodal Generation 🏒 University of Illinois Urbana-Champaign
κ³ ν’ˆμ§ˆ λΉ„λ””μ˜€-μ˜€λ””μ˜€ 합성을 μœ„ν•œ ν˜μ‹ μ μΈ 닀쀑 λͺ¨λ“œ 쑰인트 ν•™μŠ΅ ν”„λ ˆμž„μ›Œν¬ MMAudio μ œμ•ˆ!
RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response
·2295 words·11 mins· loading · loading
AI Generated πŸ€— Daily Papers Natural Language Processing Large Language Models 🏒 Peking University
ROBUSTFTλŠ” 작음이 ν¬ν•¨λœ 응닡 μ•„λž˜μ—μ„œ λŒ€κ·œλͺ¨ μ–Έμ–΄ λͺ¨λΈμ˜ κ°•κ±΄ν•œ 지도 ν•™μŠ΅ λ―Έμ„Έ 쑰정을 μœ„ν•œ ν”„λ ˆμž„μ›Œν¬λ‘œ, 작음 감지 및 μž¬λΌλ²¨λ§μ„ 톡해 ν•˜λ₯˜ μž‘μ—… μ„±λŠ₯을 ν–₯μƒμ‹œν‚΅λ‹ˆλ‹€.
ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing
·4863 words·23 mins· loading · loading
AI Generated πŸ€— Daily Papers Natural Language Processing Large Language Models 🏒 Tsinghua University
ReLU λΌμš°νŒ…μ„ μ‚¬μš©ν•˜λŠ” μ™„μ „ λ―ΈλΆ„ κ°€λŠ₯ν•œ MoE μ•„ν‚€ν…μ²˜ ReMoEλ₯Ό 톡해 λŒ€κ·œλͺ¨ μ–Έμ–΄ λͺ¨λΈμ˜ ν™•μž₯μ„±κ³Ό νš¨μœ¨μ„±μ„ 획기적으둜 κ°œμ„ ν–ˆμŠ΅λ‹ˆλ‹€!
Progressive Multimodal Reasoning via Active Retrieval
·2635 words·13 mins· loading · loading
AI Generated πŸ€— Daily Papers Multimodal Learning Multimodal Reasoning 🏒 Gaoling School of Artificial Intelligence, Renmin University of China
AR-MCTS: λŠ₯동적 검색과 λͺ¬ν…Œ μΉ΄λ₯Όλ‘œ 트리 νƒμƒ‰μœΌλ‘œ λ©€ν‹°λͺ¨λ‹¬ μΆ”λ‘  ν–₯상
Parallelized Autoregressive Visual Generation
·3557 words·17 mins· loading · loading
AI Generated πŸ€— Daily Papers Computer Vision Image Generation 🏒 Peking University
λ³Έ μ—°κ΅¬λŠ” 토큰 μ˜μ‘΄μ„±μ„ κ³ λ €ν•œ 병렬화 μ „λž΅μ„ 톡해 μžλ™ νšŒκ·€ μ‹œκ°μ  μƒμ„±μ˜ 속도λ₯Ό μ΅œλŒ€ 9.5λ°°κΉŒμ§€ ν–₯μƒμ‹œμΌ°μŠ΅λ‹ˆλ‹€.
Outcome-Refining Process Supervision for Code Generation
·2498 words·12 mins· loading · loading
AI Generated πŸ€— Daily Papers Natural Language Processing Large Language Models 🏒 Peking University
λ³΅μž‘ν•œ μ•Œκ³ λ¦¬μ¦˜ 좔둠이 ν•„μš”ν•œ μ½”λ“œ 생성 κ³Όμ œμ—μ„œ 기쑴의 ν•œκ³„λ₯Ό κ·Ήλ³΅ν•˜λŠ” μƒˆλ‘œμš΄ 방법둠, Outcome-Refining Process Supervision (ORPS) μ œμ‹œ
MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design
·2237 words·11 mins· loading · loading
AI Generated πŸ€— Daily Papers Natural Language Processing Large Language Models 🏒 Microsoft Research
MixLLM: 좜λ ₯ νŠΉμ§• κ°„μ˜ μ „μ—­ ν˜Όν•© 정밀도 μ–‘μžν™”μ™€ 고효율 μ‹œμŠ€ν…œ 섀계λ₯Ό 톡해 LLM의 정확도와 νš¨μœ¨μ„±μ„ λ™μ‹œμ— ν–₯μƒμ‹œν‚€λŠ” 획기적인 μ–‘μžν™” 방법
MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval
·2165 words·11 mins· loading · loading
AI Generated πŸ€— Daily Papers Multimodal Learning Vision-Language Models 🏒 Hong Kong University of Science and Technology
MegaPairsλŠ” VLMκ³Ό 곡개 도메인 이미지λ₯Ό ν™œμš©, 2600만 개 μ΄μƒμ˜ κ³ ν’ˆμ§ˆ 닀쀑 λͺ¨λ‹¬ ν•™μŠ΅ 데이터λ₯Ό μƒμ„±ν•˜μ—¬ λ²”μš© 닀쀑 λͺ¨λ‹¬ 검색 μ„±λŠ₯을 획기적으둜 ν–₯μƒμ‹œμΌ°μŠ΅λ‹ˆλ‹€.
LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Gaps
·7524 words·36 mins· loading · loading
AI Generated πŸ€— Daily Papers Natural Language Processing Large Language Models 🏒 TU Darmstadt
M-ALERTλŠ” λ‹€κ΅­μ–΄ LLM의 μ•ˆμ „μ„±μ„ ν‰κ°€ν•˜κΈ° μœ„ν•œ μƒˆλ‘œμš΄ λ²€μΉ˜λ§ˆν¬μž…λ‹ˆλ‹€. μ˜μ–΄, ν”„λž‘μŠ€μ–΄, 독일어, μ΄νƒˆλ¦¬μ•„μ–΄, μŠ€νŽ˜μΈμ–΄ 5개 μ–Έμ–΄μ˜ 75,000개 ν”„λ‘¬ν”„νŠΈλ₯Ό ν¬ν•¨ν•˜λ©°, λ‹€μ–‘ν•œ μ–Έμ–΄ 및 λ²”μ£Όμ—μ„œ LLM의 μ•ˆμ „μ„± 뢈일치λ₯Ό λ°ν˜€λƒˆμŠ΅λ‹ˆλ‹€.
LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis
·2184 words·11 mins· loading · loading
AI Generated πŸ€— Daily Papers Computer Vision Image Generation 🏒 Hong Kong University of Science and Technology
LeviTor: μ‚¬μš©μžμ˜ κ°„νŽΈν•œ 3D ꢀ적 μž…λ ₯만으둜 사싀적인 λΉ„λ””μ˜€ 합성이 κ°€λŠ₯ν•œ ν˜μ‹ μ μΈ λͺ¨λΈ!
IDOL: Instant Photorealistic 3D Human Creation from a Single Image
·2450 words·12 mins· loading · loading
AI Generated πŸ€— Daily Papers Computer Vision 3D Vision 🏒 Tencent
단일 μ΄λ―Έμ§€μ—μ„œ μ΄ˆκ³ μ†, κ³ ν’ˆμ§ˆ, μ• λ‹ˆλ©”μ΄μ…˜ κ°€λŠ₯ν•œ 3D 아바타λ₯Ό μƒμ„±ν•˜λŠ” IDOL λͺ¨λΈ μ œμ‹œ!
How to Synthesize Text Data without Model Collapse?
·5005 words·24 mins· loading · loading
AI Generated πŸ€— Daily Papers Natural Language Processing Large Language Models 🏒 Tsinghua University
ν•©μ„± 데이터 기반 μ–Έμ–΄ λͺ¨λΈ ν•™μŠ΅μ˜ λΆ•κ΄΄ 문제 ν•΄κ²°: 토큰 νŽΈμ§‘ 기법 μ œμ‹œ!
Flowing from Words to Pixels: A Framework for Cross-Modality Evolution
·2904 words·14 mins· loading · loading
AI Generated πŸ€— Daily Papers Multimodal Learning Vision-Language Models 🏒 GenAI, Meta
CrossFlow: λͺ¨λ‹¬λ¦¬ν‹° κ°„ 직접적 λ³€ν™˜ κ°€λŠ₯ν•œ ν˜μ‹ μ  ν”„λ ˆμž„μ›Œν¬!
Fietje: An open, efficient LLM for Dutch
·2556 words·12 mins· loading · loading
AI Generated πŸ€— Daily Papers Natural Language Processing Large Language Models 🏒 KU Leuven
Fietje: μ˜€ν”ˆμ†ŒμŠ€ μ†Œν˜• λ„€λœλž€λ“œμ–΄ LLM 곡개!