free-bit

free-bit's activity

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

upvoted a paper about 9 hours ago

Déjà View: Looping Transformers for Multi-View 3D Reconstruction

Paper • 2605.30215 • Published 6 days ago • 4

upvoted 3 papers about 14 hours ago

GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration

Paper • 2605.31039 • Published 5 days ago • 35

Mellum: Production-Grade in-IDE Contextual Code Completion with Multi-File Project Understanding

Paper • 2510.05788 • Published Oct 7, 2025 • 4

Mellum2 Technical Report

Paper • 2605.31268 • Published 5 days ago • 45

upvoted 5 papers 1 day ago

Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

Paper • 2401.10891 • Published Jan 19, 2024 • 64

Depth Anything V2

Paper • 2406.09414 • Published Jun 13, 2024 • 105

VGGT-Ω

Paper • 2605.15195 • Published 20 days ago • 3

Why Far Looks Up: Probing Spatial Representation in Vision-Language Models

Paper • 2605.30161 • Published 6 days ago • 57

Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

Paper • 2605.30280 • Published 6 days ago • 128

upvoted 10 papers 6 days ago

Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

Paper • 2605.28816 • Published 7 days ago • 416

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

Paper • 2605.28774 • Published 7 days ago • 85

DINOv2: Learning Robust Visual Features without Supervision

Paper • 2304.07193 • Published Apr 14, 2023 • 10

DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding

Paper • 2411.14347 • Published Nov 21, 2024 • 17

DINO-R1: Incentivizing Reasoning Capability in Vision Foundation Models

Paper • 2505.24025 • Published May 29, 2025 • 28

MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos

Paper • 2512.10881 • Published Dec 11, 2025 • 32

SAM3D: Segment Anything in 3D Scenes

Paper • 2306.03908 • Published Jun 6, 2023 • 2

MobileSAMv2: Faster Segment Anything to Everything

Paper • 2312.09579 • Published Dec 15, 2023 • 25

SAM 2: Segment Anything in Images and Videos

Paper • 2408.00714 • Published Aug 1, 2024 • 123

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Paper • 2509.13414 • Published Sep 16, 2025 • 3

upvoted a paper 7 days ago

LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence

Paper • 2605.25979 • Published 9 days ago • 27