Lj V. Miranda PRO

ljvmiranda921's activity

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

updated a collection 1 day ago

Human-LLM Hybrid Preferences

Collection

Resources for hybrid preferences research where we learn how to route preference instances for human vs. AI feedback • 4 items • Updated 1 day ago • 1

updated a dataset 1 day ago

ljvmiranda921/multipref

Viewer • Updated 1 day ago • 31.4k • 18

liked a Space 3 days ago

Running

10

Different Flops for Different Folks

🌌

10

A Review of the Actual Training Costs of AI

upvoted an article 3 days ago

view article

Article

Compute and Competition in AI: Different FlOPs for Different Folks

• 

Feb 12

•

14

liked a Space 9 days ago

Running

27

Bouquet

💐

27

Massively multilingual translation benchmark

liked a dataset about 1 month ago

masakhane/afrimgsm

Viewer • Updated May 26, 2025 • 4.9k • 1.14k • 9

updated a dataset about 1 month ago

ljvmiranda921/remedial-xsd-sft

Viewer • Updated Feb 17 • 300k • 24

published a dataset about 1 month ago

ljvmiranda921/remedial-xsd-sft

Viewer • Updated Feb 17 • 300k • 24

upvoted a collection about 1 month ago

Tiny Aya

Collection

Bridging Scale and Multilingual Depth • 10 items • Updated Feb 17 • 64

liked 2 models about 1 month ago

Infomaniak-AI/vllm-translategemma-27b-it

Image-Text-to-Text • 29B • Updated Jan 27 • 4.48k • 12

google/translategemma-27b-it

Image-Text-to-Text • Updated Jan 28 • 9.05k • 345

liked 4 datasets about 1 month ago

PrimeIntellect/SYNTHETIC-2-SFT-verified

Viewer • Updated Jul 10, 2025 • 105k • 95 • 8

allenai/Dolci-Think-RL-32B

Viewer • Updated Jan 5 • 102k • 313 • 25

allenai/Dolci-Think-RL-7B

Viewer • Updated Jan 5 • 102k • 2k • 16

openlanguagedata/flores_plus

Viewer • Updated 16 days ago • 893k • 22.7k • 118

upvoted a paper about 1 month ago

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Paper • 2601.22975 • Published Jan 30 • 110

updated a collection about 1 month ago

M-RewardBench (ACL 2025)

Collection

Evaluating Reward Models in Multilingual Settings • 2 items • Updated Feb 10

commentedon 🇵🇭 FilBench - Can LLMs Understand and Generate Filipino? about 1 month ago

view reply

Hey thanks! I'll open up a PR on this. But in the meantime here's the link: https://huggingface.co/spaces/filbench/filbench-leaderboard

updated a dataset 2 months ago

ljvmiranda921/rl-kalamang-R1

Viewer • Updated Jan 23 • 337 • 16