AI 연구 논문 데일리

SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain

Integrating Large Language Models into a Tri-Modal Architecture for Automated Depression Classification

SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages

FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention

Theia: Distilling Diverse Vision Foundation Models for Robot Learning

MindSearch: Mimicking Human Minds Elicits Deep AI Searcher

MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains

Diffusion Feedback Helps CLIP See Better

Mixture of Nested Experts: Adaptive Processing of Visual Tokens

Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning

Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle

Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models

3D Question Answering for City Scene Understanding

ATHAR: A High-Quality and Diverse Dataset for Classical Arabic to English Translation

Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge

ImagiNet: A Multi-Content Dataset for Generalizable Synthetic Image Detection via Contrastive Learning

Sentiment Analysis of Lithuanian Online Reviews Using Large Language Models

Bridging the Gap: Studio-like Avatar Creation from a Monocular Phone Capture

WalkTheDog: Cross-Morphology Motion Alignment via Phase Manifolds

VolDoGer: LLM-assisted Datasets for Domain Generalization in Vision-Language Tasks

TAPTRv2: Attention-based Position Update Improves Tracking Any Point