AI 연구 논문 데일리

Large Language Diffusion Models

The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks

Region-Adaptive Sampling for Diffusion Transformers

Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

MM-RLHF: The Next Step Forward in Multimodal LLM Alignment

DarwinLM: Evolutionary Structured Pruning of Large Language Models

ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generation

Diverse Inference and Verification for Advanced Reasoning

Precise Parameter Localization for Textual Generation in Diffusion Models

FoNE: Precise Single-Token Number Embeddings via Fourier Features

Small Models, Big Impact: Efficient Corpus and Graph-Based Adaptation of Small Multilingual Language Models for Low-Resource Languages

Selective Self-to-Supervised Fine-Tuning for Generalization in Large Language Models

AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting

We Can't Understand AI Using our Existing Vocabulary

Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding

STMA: A Spatio-Temporal Memory Agent for Long-Horizon Embodied Task Planning

V2V-LLM: Vehicle-to-Vehicle Cooperative Autonomous Driving with Multi-Modal Large Language Models

CLaMP 3: Universal Music Information Retrieval Across Unaligned Modalities and Unseen Languages

Agentic End-to-End De Novo Protein Design for Tailored Dynamics Using a Language Diffusion Model

MRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE Solvers

Jailbreaking to Jailbreak

Cluster and Predict Latents Patches for Improved Masked Image Modeling