Paulson

Pnaomi's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 7 papers about 18 hours ago

Defeating Prompt Injections by Design

Paper • 2503.18813 • Published 1 day ago • 14

MagicComp: Training-free Dual-Phase Refinement for Compositional Video Generation

Paper • 2503.14428 • Published 7 days ago • 7

Reasoning to Learn from Latent Thoughts

Paper • 2503.18866 • Published 1 day ago • 8

AlphaSpace: Enabling Robotic Actions through Semantic Tokenization and Symbolic Reasoning

Paper • 2503.18769 • Published 1 day ago • 6

AgentRxiv: Towards Collaborative Autonomous Research

Paper • 2503.18102 • Published 2 days ago • 14

Judge Anything: MLLM as a Judge Across Any Modality

Paper • 2503.17489 • Published 4 days ago • 16

Position: Interactive Generative Video as Next-Generation Game Engine

Paper • 2503.17359 • Published 4 days ago • 53

upvoted 9 papers 1 day ago

Implicit Bias-Like Patterns in Reasoning Models

Paper • 2503.11572 • Published 11 days ago • 6

PVChat: Personalized Video Chat with One-Shot Learning

Paper • 2503.17069 • Published 5 days ago • 7

TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting

Paper • 2503.17032 • Published 5 days ago • 17

FastCuRL: Curriculum Reinforcement Learning with Progressive Context Extension for Efficient Training R1-like Reasoning Models

Paper • 2503.17287 • Published 4 days ago • 8

Modifying Large Language Model Post-Training for Diverse Creative Writing

Paper • 2503.17126 • Published 4 days ago • 26

OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement

Paper • 2503.17352 • Published 4 days ago • 20

RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints

Paper • 2503.16408 • Published 5 days ago • 36

MARS: A Multi-Agent Framework Incorporating Socratic Guidance for Automated Prompt Optimization

Paper • 2503.16874 • Published 5 days ago • 41

MAPS: A Multi-Agent Framework Based on Big Seven Personality and Socratic Guidance for Multimodal Scientific Problem Solving

Paper • 2503.16905 • Published 5 days ago • 50

upvoted 4 papers 4 days ago

UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?

Paper • 2503.09949 • Published 13 days ago • 4

AIMI: Leveraging Future Knowledge and Personalization in Sparse Event Forecasting for Treatment Adherence

Paper • 2503.16091 • Published 6 days ago • 1

Agents Play Thousands of 3D Video Games

Paper • 2503.13356 • Published 8 days ago • 8

See-Saw Modality Balance: See Gradient, and Sew Impaired Vision-Language Balance to Mitigate Dominant Modality Bias

Paper • 2503.13834 • Published 8 days ago • 5