Mwangi

Benson's activity

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

upvoted 2 papers 4 days ago

We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning

Paper • 2508.10433 • Published 5 days ago • 140

ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing

Paper • 2508.10881 • Published 5 days ago • 49

upvoted a collection 5 days ago

DINOv3

Collection

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated 4 days ago • 168

upvoted 2 papers 5 days ago

Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory

Paper • 2508.09736 • Published 6 days ago • 48

Story2Board: A Training-Free Approach for Expressive Storyboard Generation

Paper • 2508.09983 • Published 6 days ago • 61

upvoted a paper 6 days ago

WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent

Paper • 2508.05748 • Published 12 days ago • 112

upvoted a paper 7 days ago

WideSearch: Benchmarking Agentic Broad Info-Seeking

Paper • 2508.07999 • Published 8 days ago • 102

upvoted a paper 11 days ago

Marco-Voice Technical Report

Paper • 2508.02038 • Published 15 days ago • 15

upvoted a paper 14 days ago

Qwen-Image Technical Report

Paper • 2508.02324 • Published 15 days ago • 193

upvoted a paper 27 days ago

EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge

Paper • 2505.23009 • Published May 29 • 18

upvoted a paper 28 days ago

TokensGen: Harnessing Condensed Tokens for Long Video Generation

Paper • 2507.15728 • Published 29 days ago • 7

upvoted a collection 29 days ago

🌀 Bytedance Papers

Collection

18 items • Updated 22 days ago • 4

upvoted a changelog about 1 month ago

view changelog

Changelog

Inference Providers now fully support OpenAI-compatible API

Jul 18

• 79

upvoted a paper about 1 month ago

VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

Paper • 2211.14758 • Published Nov 27, 2022 • 2

upvoted an article about 1 month ago

view article

Article

Unlocking Healthcare AI: I'm Releasing State-of-the-Art Medical Models for Free. Forever.

By •

Jul 16

• 133

upvoted 2 papers about 1 month ago

Neural-Driven Image Editing

Paper • 2507.05397 • Published Jul 7 • 26

PresentAgent: Multimodal Agent for Presentation Video Generation

Paper • 2507.04036 • Published Jul 5 • 10

upvoted a collection about 2 months ago

Speech-To-Text

Collection

https://kyutai.org/next/stt • 6 items • Updated Jun 19 • 12

upvoted a paper about 2 months ago

SciArena: An Open Evaluation Platform for Foundation Models in Scientific Literature Tasks

Paper • 2507.01001 • Published Jul 1 • 45

upvoted a paper 3 months ago

UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning

Paper • 2505.14231 • Published May 20 • 53