Sara Tahir

sara-ta's activity

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

upvoted a paper about 3 hours ago

PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing

Paper • 2609.23784 • Published 9 days ago • 12

upvoted 2 papers about 23 hours ago

Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms

Paper • 2609.23658 • Published 9 days ago • 30

Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings

Paper • 2609.25165 • Published 8 days ago • 74

upvoted a paper 3 days ago

RULER: Instance-aware Rubric Rewards for SVG Generation

Paper • 2609.25270 • Published 8 days ago • 101

upvoted a paper 5 days ago

Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation

Paper • 2609.19122 • Published 12 days ago • 5

upvoted 2 papers 6 days ago

Srijika: OpenType-Layout-Reusing Font Restyling for Nine Indic Scripts

Paper • 2609.05661 • Published 25 days ago • 41

Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation

Paper • 2609.20744 • Published 12 days ago • 53

upvoted a paper 7 days ago

The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction

Paper • 2609.18063 • Published 13 days ago • 19

upvoted 2 papers 8 days ago

LynnReal-Omni: Native multi-modal Video Generation for Agentic Visual Workflows

Paper • 2609.15863 • Published 15 days ago • 56

Disentangling Representation Evolution in Transformers through Directional Decomposition

Paper • 2609.15975 • Published 15 days ago • 9

upvoted 2 papers 9 days ago

BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender

Paper • 2609.15478 • Published 15 days ago • 34

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

Paper • 2609.14857 • Published 15 days ago • 214