AI 연구 논문 데일리

MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs

DataComp-LM: In search of the next generation of training sets for language models

mDPO: Conditional Preference Optimization for Multimodal Large Language Models

THEANINE: Revisiting Memory Management in Long-term Conversations with Timeline-augmented Response Generation

MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers

How Do Large Language Models Acquire Factual Knowledge During Pretraining?

VideoLLM-online: Online Video Large Language Model for Streaming Video

A Simple and Effective L_2 Norm-Based Strategy for KV Cache Compression

Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models

MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens

GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities

LLaNA: Large Language and NeRF Assistant

From Pixels to Prose: A Large Dataset of Dense Image Captions

WPO: Enhancing RLHF with Weighted Preference Optimization

In-Context Editing: Learning Knowledge from Self-Induced Distributions

Pandora: Towards General World Model with Natural Language Actions and Video States

WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences

L4GM: Large 4D Gaussian Reconstruction Model

Unifying Multimodal Retrieval via Document Screenshot Embedding

Task Me Anything

Vid3D: Synthesis of Dynamic 3D Scenes using 2D Video Diffusion

Just How Flexible are Neural Networks in Practice?

Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning

Evaluating Open Language Models Across Task Types, Application Domains, and Reasoning Types: An In-Depth Experimental Analysis

Breaking the Attention Bottleneck

HiddenTables & PyQTax: A Cooperative Game and Dataset For TableQA to Ensure Scale and Data Privacy Across a Myriad of Taxonomies

CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training

Consistency^2: Consistent and Fast 3D Painting with Latent Consistency Models

Deep Bayesian Active Learning for Preference Modeling in Large Language Models