Mwangi PRO

Benson's activity

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

upvoted a paper about 6 hours ago

Qwen3.5-Omni Technical Report

Paper • 2604.15804 • Published 4 days ago • 27

upvoted a paper 9 days ago

VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph

Paper • 2602.12735 • Published Feb 13 • 8

liked 2 models 10 days ago

google/tipsv2-l14

Zero-Shot Image Classification • Updated 6 days ago • 4.81k • 9

nvidia/Kimodo-SOMA-RP-v1.1

Updated 10 days ago • 744 • 9

liked a model 11 days ago

Qwen/Qwen3.5-397B-A17B

Image-Text-to-Text • 403B • Updated Mar 15 • 710k • • 1.46k

upvoted 2 papers 14 days ago

WAVE: Learning Unified & Versatile Audio-Visual Embeddings with Multimodal LLM

Paper • 2509.21990 • Published Sep 26, 2025 • 1

A Simple Baseline for Streaming Video Understanding

Paper • 2604.02317 • Published 19 days ago • 72

liked a model 15 days ago

tsinghua-ee/WAVE-7B

Updated Feb 11 • 130 • 2

upvoted 2 papers 20 days ago

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

Paper • 2603.27538 • Published 23 days ago • 144

PEARL: Personalized Streaming Video Understanding Model

Paper • 2603.20422 • Published Mar 20 • 40

upvoted a paper 21 days ago

Towards a Medical AI Scientist

Paper • 2603.28589 • Published 21 days ago • 89

liked a model 21 days ago

Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled

Image-Text-to-Text • 28B • Updated 15 days ago • 567k • 2.74k

liked a Space 21 days ago

Running

Agents

64

Qwen3.5 Omni Online Demo

📚

64

Chat with a multimodal AI using text, image, audio, or video

liked a model 22 days ago

internlm/Intern-S1-Pro

Image-Text-to-Text • Updated 22 days ago • 123k • 275

liked a dataset 30 days ago

nvidia/MMOU

Viewer • Updated 24 days ago • 15k • 1.76k • 15

liked a model about 1 month ago

syxbb/SAMA-14B

Video-to-Video • Updated 29 days ago • 20

upvoted 3 papers about 1 month ago

Multimodal OCR: Parse Anything from Documents

Paper • 2603.13032 • Published Mar 13 • 43

NLE: Non-autoregressive LLM-based ASR by Transcript Editing

Paper • 2603.08397 • Published Mar 9 • 22

MAISI-v2: Accelerated 3D High-Resolution Medical Image Synthesis with Rectified Flow and Region-specific Contrastive Loss

Paper • 2508.05772 • Published Aug 7, 2025 • 3

liked a model about 1 month ago

nvidia/NV-Generate-MR-Brain

Unconditional Image Generation • Updated 12 days ago • 315 • 16