AI研究論文デイリー

MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?

LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages

Associative Recurrent Memory Transformer

Learning Action and Reasoning-Centric Image Editing from Videos and Simulations

ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation

Evaluating Language Model Context Windows: A "Working Memory" Test and Inference-time Correction

UltraEdit: Instruction-based Fine-Grained Image Editing at Scale

Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images

InverseCoder: Unleashing the Power of Instruction-Tuned Code LLMs with Inverse-Instruct

Compositional Video Generation as Flow Equalization

Multi-Object Hallucination in Vision-Language Models

PAS: Data-Efficient Plug-and-Play Prompt Augmentation System

Training Task Experts through Retrieval Based Distillation

Understanding Visual Feature Reliance through the Lens of Complexity

PartCraft: Crafting Creative Objects by Parts

LLMAEL: Large Language Models are Good Context Augmenters for Entity Linking

ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models