AI研究論文デイリー

2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining

VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control

CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings

LTX-Video: Realtime Video Latent Diffusion

VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM

Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

ProgCo: Program Helps Self-Correction of Large Language Models

MLLM-as-a-Judge for Image Safety without Human Labeling

MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models

A3: Android Agent Arena for Mobile GUI Agents

Unifying Specialized Visual Encoders for Video Language Models

Dynamic Scaling of Unit Tests for Code Reward Modeling

Nested Attention: Semantic-aware Attention Values for Concept Personalization

SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration

MapQaTor: A System for Efficient Annotation of Map Query Datasets

Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing

Population Aware Diffusion for Time Series Generation

Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding

SeFAR: Semi-supervised Fine-grained Action Recognition with Temporal Perturbation and Learning Stabilization