L

TaidanaHito's activity

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

upvoted 9 papers 2 days ago

Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs

Paper • 2610.27103 • Published 9 days ago • 40

Learning the 4D World through Point Trajectory Forecasting

Paper • 2610.28594 • Published 8 days ago • 53

Focused Omni-Modal GUI Agents

Paper • 2610.26203 • Published 9 days ago • 231

Language Models Learn to Improve Language Models

Paper • 2610.23344 • Published 12 days ago • 23

Entertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or Literally

Paper • 2610.21204 • Published 13 days ago • 23

DeLoop: Repeated Actions as Self-Supervision for Long-Horizon Agents

Paper • 2610.19376 • Published 14 days ago • 34

F2G-Pose: Geometry-Aware Foundation Feature Lifting for Direct RGB-D Category-Level Object Pose Estimation

Paper • 2610.31623 • Published 6 days ago • 22

AgentVQA: A Unified Benchmark for Agentic Visual Understanding

Paper • 2610.31494 • Published 6 days ago • 25

IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems

Paper • 2610.30949 • Published 6 days ago • 107

upvoted a collection 3 days ago

Innovator-VL

Collection

A Multimodal Large Language Model for Scientific Discovery • 9 items • Updated Mar 5 • 7

upvoted a paper 4 days ago

Innovator-VL: A Multimodal Large Language Model for Scientific Discovery

Paper • 2601.19325 • Published Jan 27 • 86

upvoted a collection 9 days ago

Bonsai-Auxiliary

Collection

8 items • Updated Jun 4 • 19

upvoted an article about 1 month ago

view article

Article

Fine-Tune XLSR-Wav2Vec2 for low-resource ASR with 🤗 Transformers

• 

patrickvonplaten

•

Nov 15, 2021

• 44

upvoted 2 papers about 1 month ago

Scaling Speech Technology to 1,000+ Languages

Paper • 2305.13516 • Published May 22, 2023 • 13

Mellum2 Technical Report

Paper • 2605.31268 • Published May 29 • 60

upvoted a collection about 1 month ago

100 Coder/Programming - MOE, Reasoning, Reg, Imatrix, Fused.

Collection

Models (0.8B to 87B) in regular, "reasoning", "Brainstorm", MOE (1x to 8x / 128 experts), and expanded to create better and stronger code, faster. • 82 items • Updated 5 days ago • 73

upvoted 4 papers about 1 month ago

Sharp Monocular View Synthesis in Less Than a Second

Paper • 2512.10685 • Published Dec 11, 2025 • 31

FIRE3D: Feed-forward Interactive 3D Scene Reconstruction Within A Minute

Paper • 2609.08848 • Published Sep 8 • 1

MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction

Paper • 2604.27393 • Published Apr 30 • 71

MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe

Paper • 2509.18154 • Published Sep 16, 2025 • 64