ArXiv TLDR

Fei Ma

3 papers · Latest:

Human-Computer Interaction

MER 2026: From Discriminative Emotion Recognition to Generative Emotion Understanding

MER2026 expands emotion understanding challenges from discriminative recognition to generative analysis, introducing new tasks and multimodal approaches.

2604.19417
Computer Vision

PLAF: Pixel-wise Language-Aligned Feature Extraction for Efficient 3D Scene Understanding

PLAF introduces a pixel-wise language-aligned feature extraction framework for efficient and accurate open-vocabulary 3D scene understanding.

2604.15770
Computer Vision

LottieGPT: Tokenizing Vector Animation for Autoregressive Generation

LottieGPT is the first framework that tokenizes and autoregressively generates editable vector animations from prompts using a new tokenizer and large dataset.

2604.11792

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.