AI研究論文デイリー

The Brittleness of AI-Generated Image Watermarking Techniques: Examining Their Robustness Against Visual Paraphrasing Attacks

Audio Match Cutting: Finding and Creating Matching Audio Transitions in Movies and Videos

MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning

RP1M: A Large-Scale Motion Dataset for Piano Playing with Bi-Manual Dexterous Robot Hands

PhysBERT: A Text Embedding Model for Physics Scientific Literature

NeCo: Improving DINOv2's spatial representations in 19 GPU hours with Patch Neighbor Consistency

Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model

MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding

Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model

Recent Surge in Public Interest in Transportation: Sentiment Analysis of Baidu Apollo Go Using Weibo Data

TableBench: A Comprehensive and Complex Benchmark for Table Question Answering

Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique

To Code, or Not To Code? Exploring Impact of Code in Pre-training

MambaEVT: Event Stream based Visual Object Tracking using State Space Model

ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining