free-bit

free-bit's activity

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

upvoted 2 papers 25 days ago

On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability

Paper • 2608.30320 • Published 26 days ago • 63

PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback

Paper • 2608.30241 • Published 26 days ago • 12

upvoted 6 papers 26 days ago

Luce: Relightable Gaussians for 3D Asset Generation

Paper • 2608.23943 • Published Aug 25 • 16

Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video Diffusion

Paper • 2608.26794 • Published about 1 month ago • 17

Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090

Paper • 2608.27370 • Published about 1 month ago • 40

ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL

Paper • 2608.28476 • Published 29 days ago • 28

Agentic Artifact Creation: Systems, Evaluation, Principles, and Opportunities

Paper • 2608.28122 • Published 29 days ago • 66

LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering

Paper • 2608.28281 • Published 29 days ago • 99

upvoted 2 articles 26 days ago

view article

Article

🪆 Introduction to Matryoshka Embedding Models

• 
• 
• +1

tomaarsen, Xenova, osanseviero

•

Feb 23, 2024

• 220

view article

Article

How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with Code

• 

nielsr

•

Aug 21

• 32

upvoted 5 papers 26 days ago

Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding

Paper • 2608.28192 • Published 29 days ago • 17

Paint What You See: Benchmarking Dexterous Visual Tool Use in Multimodal Agents

Paper • 2608.25417 • Published Aug 26 • 19

Video Generative Models as Geometry Learner

Paper • 2608.28549 • Published 29 days ago • 15

Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction

Paper • 2608.27529 • Published about 1 month ago • 32

Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning

Paper • 2608.27549 • Published about 1 month ago • 49

upvoted 5 papers 29 days ago

The Embedder's Dilemma: LLMs Are Better, but at What Cost?

Paper • 2608.12875 • Published Aug 13 • 16

EXIMO: VLM Guided Exploration of VLA Policies

Paper • 2608.19891 • Published Aug 20 • 16

WithEveryone: Unified Planning and Identity Grounding for Group Image Generation

Paper • 2608.20336 • Published Aug 20 • 42

4DAnyone: Create Anyone in 4D from a Casual Monocular Video

Paper • 2608.20335 • Published Aug 20 • 85

Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence

Paper • 2608.21156 • Published Aug 21 • 63