Mary Perez

MaryPerez's activity

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

liked a model about 19 hours ago

orcarouter/Qwen3.8-27B-Uncensored-MLX

Image-Text-to-Text • 5B • Updated 1 day ago • 34.9k • 871

upvoted a paper 2 days ago

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

Paper • 2608.17426 • Published 5 days ago • 155

liked a model 3 days ago

Qwen/Qwen3.8-27B-FP8

Image-Text-to-Text • 28B • Updated 8 days ago • 2.31M • 662

upvoted a paper 5 days ago

Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination

Paper • 2608.14391 • Published 9 days ago • 277

upvoted a paper 6 days ago

TailBooster: A Dual-Layer Generative Framework for Extreme Value Augmentation with Operational Validity Enforcement

Paper • 2608.11951 • Published 11 days ago • 9

upvoted a paper 7 days ago

Mitigating Gender Bias in English to Romanian Machine Translation

Paper • 2608.08606 • Published 14 days ago • 9

upvoted a paper 9 days ago

OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution

Paper • 2608.00677 • Published 22 days ago • 261

upvoted a paper 10 days ago

SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information

Paper • 2608.10692 • Published 12 days ago • 12

liked a model 13 days ago

LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V9-GGUF

Image-Text-to-Text • 35B • Updated 4 days ago • 998k • 540

upvoted a paper 15 days ago

Interpretable MEG Decoding of Perceived Speech: Cortical Sources and the Stimulus Features That Drive Retrieval

Paper • 2608.01481 • Published 21 days ago • 71

liked a model 16 days ago

mistralai/Shieldstral-1.0-3B

4B • Updated 17 days ago • 17.4k • 254

upvoted 2 papers 18 days ago

GROVE: Growing and Reasoning over Temporally Stratified Memory from Streaming Video Experience

Paper • 2608.02392 • Published 20 days ago • 15

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks

Paper • 2608.02023 • Published 20 days ago • 156

liked a model 18 days ago

Comfy-Org/MiniMax-H3

Updated about 15 hours ago • 16.8M • 1.5k

upvoted a paper 20 days ago

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

Paper • 2607.23802 • Published 28 days ago • 106

liked a model 20 days ago

unsloth/DeepSeek-V4-Flash-0731-GGUF

284B • Updated 16 days ago • 372k • 714