Selen Su

selensu's activity

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

upvoted a paper 7 days ago

Wave Forcing: Towards Speed-of-Light Streaming Video Generation

Paper • 2611.00859 • Published 10 days ago • 128

upvoted a paper 13 days ago

Work Agents: Systems, Capabilities, and Optimization

Paper • 2610.35845 • Published 15 days ago • 115

upvoted 3 papers 20 days ago

Embodied Task Agents Can Perform Fine Manipulation through Tactile In-Context Learning

Paper • 2610.27613 • Published 21 days ago • 24

Truncate or Not? A Scaling Study of Looped Transformers with Truncated Backpropagation

Paper • 2610.26030 • Published 21 days ago • 33

HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs

Paper • 2610.26770 • Published 22 days ago • 33

upvoted a paper 22 days ago

Execution Before Memory: Diagnosing Memory Failures in Video World Models

Paper • 2610.23542 • Published 25 days ago • 28

upvoted a paper 24 days ago

Can World and Action Modeling Benefit Each Other under Unified Causal Training?

Paper • 2610.21095 • Published 26 days ago • 29

upvoted a paper 26 days ago

Video-Arena: A Scalable Agentic Video Benchmark for Spatiotemporal Capability

Paper • 2610.14158 • Published Oct 9 • 12

upvoted a paper 27 days ago

Multics: Generative Multi-Player World Model with Hierarchical Communication

Paper • 2610.17201 • Published 29 days ago • 57

upvoted a paper about 1 month ago

Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness

Paper • 2610.08621 • Published Oct 6 • 69

upvoted 4 papers about 2 months ago

SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers

Paper • 2609.01343 • Published Sep 1 • 63

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

Paper • 2609.19969 • Published Sep 17 • 205

SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models

Paper • 2609.02886 • Published Sep 2 • 114

Omni-Streaming Thinking

Paper • 2609.15128 • Published Sep 14 • 22

upvoted 3 papers 2 months ago

OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining

Paper • 2609.07398 • Published Sep 7 • 70

AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing

Paper • 2609.08936 • Published Sep 8 • 137

What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents

Paper • 2608.27260 • Published Aug 27 • 72

upvoted 3 papers 3 months ago

Unlocking the Potential of Image Editing via Concept Scaling and Dense Supervision

Paper • 2608.16812 • Published Aug 17 • 53

Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion

Paper • 2608.19567 • Published Aug 20 • 34

ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Models

Paper • 2608.14022 • Published Aug 14 • 19