Demian L. P.

very-cooluser's activity

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

upvoted a paper 19 days ago

SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models

Paper • 2609.05533 • Published 28 days ago • 15

upvoted 2 papers 26 days ago

Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development

Paper • 2608.13417 • Published Aug 13 • 59

Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving

Paper • 2609.00111 • Published about 1 month ago • 315

upvoted a collection about 2 months ago

🤏 Smol-Data

Collection

Tried and tested mixes for strong pretraining. Inspired by https://huggingface.co/blog/codelion/optimal-dataset-mixing • 14 items • Updated Mar 2 • 21

upvoted a paper about 2 months ago

UEmbed: Unified Sparse and Dense Multimodal Embeddings

Paper • 2608.02583 • Published Aug 3 • 52

upvoted 6 papers 3 months ago

Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System

Paper • 2606.18112 • Published Jun 18 • 30

The Verification Horizon: No Silver Bullet for Coding Agent Rewards

Paper • 2606.26300 • Published Jun 24 • 53

Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation

Paper • 2606.26907 • Published Jun 25 • 55

Native Active Perception as Reasoning for Omni-Modal Understanding

Paper • 2606.19341 • Published Jun 17 • 21

Rethinking the Role of Efficient Attention in Hybrid Architectures

Paper • 2606.15378 • Published Jun 13 • 21

Qwen-Image-2.0-RL Technical Report

Paper • 2606.27608 • Published Jun 25 • 55

upvoted 4 papers 4 months ago

Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation

Paper • 2606.17030 • Published Jun 15 • 48

OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization

Paper • 2605.21226 • Published May 20 • 6

SAME: A Semantically-Aligned Music Autoencoder

Paper • 2605.18613 • Published May 18 • 4

Measuring Maximum Activations in Open Large Language Models

Paper • 2605.15572 • Published May 15 • 17

upvoted 2 articles 5 months ago

view article

Article

Training-Free Reasoning at 88.89% on GPQA Diamond: How Darwin Family Hit Frontier Scores Without a Single Gradient Step

• 

FINAL-Bench

•

May 15

• 18

view article

Article

Vocabulary-Augmented Prompting for Sango — Production African Language AI Without a Parallel Corpus

• 

MEYNG

•

May 13

• 2

upvoted a paper 5 months ago

Qwen-Image-2.0 Technical Report

Paper • 2605.10730 • Published May 11 • 120

upvoted a collection 7 months ago

Qwen3-VL

Collection

37 items • Updated Dec 31, 2025 • 782

upvoted a paper 8 months ago

Qwen3-TTS Technical Report

Paper • 2601.15621 • Published Jan 22 • 80