Daily Papers of 2025-01-06

1. EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation 45 upvotes, #1 of 2025-01-06
2. VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction 36 upvotes, #2 of 2025-01-06
3. Virgo: A Preliminary Exploration on Reproducing o1-like MLLM 30 upvotes, #3 of 2025-01-06
4. VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation 18 upvotes, #4 of 2025-01-06
5. SDPO: Segment-Level Direct Preference Optimization for Social Agents 18 upvotes, #4 of 2025-01-06
6. Graph Generative Pre-trained Transformer 17 upvotes, #6 of 2025-01-06
7. LUSIFER: Language Universal Space Integration for Enhanced Multilingual Embeddings with Large Language Models 12 upvotes, #7 of 2025-01-06
8. BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery 6 upvotes, #8 of 2025-01-06

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.