xziayro

xziayro's activity

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

upvoted 2 papers 1 day ago

Align Then Reason: A Multimodal Lip-Sync Judge for Dubbing

Paper • 2610.00825 • Published 4 days ago • 11

4Director: Controlling Video World Models with Rigid 3D Geometry

Paper • 2610.02160 • Published 3 days ago • 27

upvoted 4 papers 2 days ago

Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification

Paper • 2607.24027 • Published Jul 27 • 40

Pretraining Transformers with Quantized Softmax in Attention

Paper • 2609.33591 • Published 7 days ago • 6

LongLive-Plug: Once-for-All Distillation for Video Generation

Paper • 2609.38154 • Published 5 days ago • 36

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Paper • 2609.39982 • Published 4 days ago • 111

upvoted a paper 5 days ago

MassAlloc Attention: Let Attention Allocate Its Own Compute

Paper • 2609.32712 • Published 8 days ago • 75

upvoted 3 papers 6 days ago

TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations

Paper • 2609.30222 • Published 10 days ago • 13

Block Sparse Attention with Log-Linear Complexity

Paper • 2609.31093 • Published 9 days ago • 30

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Paper • 2609.31620 • Published 9 days ago • 159

upvoted a paper 10 days ago

JEV-as-a-Judge: Accept When Confident, Escalate When Unsure

Paper • 2609.26550 • Published 12 days ago • 42

upvoted 2 papers 13 days ago

MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup

Paper • 2609.15126 • Published 20 days ago • 12

Paint-Anything: Unified Any-Color Control for Image Generation and Editing

Paper • 2609.20816 • Published 17 days ago • 57

upvoted 2 papers 14 days ago

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

Paper • 2609.20744 • Published 17 days ago • 53

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published 17 days ago • 200

upvoted a paper 16 days ago

JEPA-Anything: Learning Predictive Models across Different Worlds

Paper • 2609.20800 • Published 17 days ago • 75

upvoted 2 papers 17 days ago

VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention

Paper • 2609.15810 • Published 20 days ago • 51

Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction

Paper • 2609.13285 • Published 26 days ago • 82

upvoted an article 18 days ago

view article

Article

Profiling in PyTorch (Part 3): Attention is all you profile

• 
• 
• +2

ariG23498, sergiopaniego, sayakpaul, ror

•

Jul 10

• 50

upvoted a paper 19 days ago

Atria Dawn: The Dawn of Agentic Superintelligence

Paper • 2609.15818 • Published 20 days ago • 434