J C

dark-pen

10 3303 10329

AI & ML interests

None yet

Recent Activity

liked a model about 6 hours ago

Disty0/Z-Image-Turbo-SDNQ-uint4-svd-r32

reacted to gokaygokay's post with 🔥 about 6 hours ago

FlashPack: Lightning-Fast Model Loading for PyTorch https://github.com/fal-ai/flashpack FlashPack — a new, high-throughput file format and loading mechanism for PyTorch that makes model checkpoint I/O blazingly fast, even on systems without access to GPU Direct Storage (GDS). With FlashPack, loading any model can be 3–6× faster than with the current state-of-the-art methods like accelerate or the standard load_state_dict() and to() flow — all wrapped in a lightweight, pure-Python package that works anywhere.

liked a model about 6 hours ago

fal/Wan2.2-Animate-2-VAE-FlashPack

View all activity

Organizations

upvoted 5 papers about 6 hours ago

Marionette: Predicting World States, Rendering Geometry, Painting Appearance

Paper • 2608.14530 • Published 9 days ago • 33

DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder

Paper • 2509.25182 • Published Sep 29, 2025 • 40

VAR-3D: View-aware Auto-Regressive Model for Text-to-3D Generation via a 3D Tokenizer

Paper • 2602.13818 • Published Feb 14 • 1

One-Shot Refiner: Boosting Feed-forward Novel View Synthesis via One-Step Diffusion

Paper • 2601.14161 • Published Jan 20 • 1

OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder

Paper • 2603.16099 • Published Mar 17 • 3

upvoted a collection about 6 hours ago

3D Scene Generation

Collection

1 item • Updated Apr 22 • 1

upvoted a paper about 6 hours ago

Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion

Paper • 2506.08009 • Published Jun 9, 2025 • 32

upvoted a collection about 6 hours ago

Interactive Experience

Collection

6 items • Updated Jul 4, 2025 • 2

upvoted a paper about 7 hours ago

ARIG: Autoregressive Interactive Head Generation for Real-time Conversations

Paper • 2507.00472 • Published Jul 1, 2025 • 12

upvoted a collection about 7 hours ago

WildRayZer

Collection

Checkpoints and Data Release for WildRayZer: Self-supervised Large View Synthesis in Dynamic Environments (CVPR 2026 Highlight) • 3 items • Updated Apr 17 • 1

upvoted 2 papers about 7 hours ago

RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning

Paper • 2510.02240 • Published Oct 2, 2025 • 19

OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding

Paper • 2507.07984 • Published Jul 10, 2025 • 44

upvoted 3 collections about 7 hours ago

upvoted a paper about 7 hours ago

Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps

Paper • 2505.18675 • Published May 24, 2025 • 29

upvoted 4 papers about 9 hours ago

Representation over Routing: Diagnosing Temporal Routing Pathologies in Multi-Timescale PPO

Paper • 2604.13517 • Published May 30 • 6

LightCrafter: PBR-Conditioned Video Diffusion Refinement for Controllable and Consistent Relighting

Paper • 2607.08016 • Published Jul 15 • 1

EvReflection: Event-Driven Micro-Dynamics for Reflection Removal

Paper • 2608.06184 • Published 17 days ago • 1

AutoAWG: Adverse Weather Generation with Adaptive Multi-Controls for Automotive Videos

Paper • 2604.18993 • Published Apr 21 • 1

J C

AI & ML interests

Recent Activity

Organizations

dark-pen's activity