Alexander Gambashidze

alexgambashidze's activity

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

New activity in deepseek-ai/DeepSeek-OCR 3 months ago

fixing hardcoded cuda() for cpu inference

❤️ 5

4

#21 opened 3 months ago by

alexgambashidze

updated a model 4 months ago

alexgambashidze/qwen1.5-m-310_baseline_5e6

Text Generation • 2B • Updated Sep 4, 2025 • 4

published a model 4 months ago

alexgambashidze/qwen1.5-m-310_baseline_5e6

Text Generation • 2B • Updated Sep 4, 2025 • 4

updated a model 4 months ago

alexgambashidze/qwen1.5-m-310_EXPERIMENTAL_5e6

Text Generation • 2B • Updated Sep 4, 2025 • 6

published a model 4 months ago

alexgambashidze/qwen1.5-m-310_EXPERIMENTAL_5e6

Text Generation • 2B • Updated Sep 4, 2025 • 6

updated a model 4 months ago

alexgambashidze/qwen1.5-m-200_EXPERIMENTAL

Text Generation • 2B • Updated Sep 3, 2025 • 4

published a model 4 months ago

alexgambashidze/qwen1.5-m-200_EXPERIMENTAL

Text Generation • 2B • Updated Sep 3, 2025 • 4

updated a model 4 months ago

alexgambashidze/qwen1.5-m-200

Text Generation • 2B • Updated Sep 2, 2025 • 5

published a model 4 months ago

alexgambashidze/qwen1.5-m-200

Text Generation • 2B • Updated Sep 2, 2025 • 5

updated a model 6 months ago

alexgambashidze/qwen2.5vl_image_preference_reasoner

8B • Updated Jul 2, 2025 • 10 • 1

authored a paper 6 months ago

Listener-Rewarded Thinking in VLMs for Image Preferences

Paper • 2506.22832 • Published Jun 28, 2025 • 23

upvoted a paper 6 months ago

Listener-Rewarded Thinking in VLMs for Image Preferences

Paper • 2506.22832 • Published Jun 28, 2025 • 23

commented a paper 6 months ago

Listener-Rewarded Thinking in VLMs for Image Preferences

Paper • 2506.22832 • Published Jun 28, 2025 • 23 •

1

published a model 6 months ago

alexgambashidze/qwen2.5vl_image_preference_reasoner

8B • Updated Jul 2, 2025 • 10 • 1

upvoted 2 papers 7 months ago

Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models

Paper • 2506.06395 • Published Jun 5, 2025 • 133

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts

Paper • 2506.05229 • Published Jun 5, 2025 • 38

upvoted a paper about 1 year ago

CLEAR: Character Unlearning in Textual and Visual Modalities

Paper • 2410.18057 • Published Oct 23, 2024 • 209

updated a model over 1 year ago

alexgambashidze/SDXL_NCP-DPO_v0.1

Updated Jun 29, 2024 • 11

New activity in alexgambashidze/SDXL_NCP-DPO_v0.1 over 1 year ago

train code

1

#4 opened over 1 year ago by

smallD

authored a paper over 1 year ago

Aligning Diffusion Models with Noise-Conditioned Perception

Paper • 2406.17636 • Published Jun 25, 2024 • 27