221 553 420

Adina Yakefu

AdinaY

AI & ML interests

None yet

Recent Activity

upvoted a paper about 20 hours ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

reacted to lin-tan's post with 🔥 1 day ago

🚀 Excited to share that our paper, "SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Models", has been accepted to #ICRA2025! 🔗 Preprint: https://arxiv.org/pdf/2409.19471 We introduce SELP (Safe Efficient LLM Planner), a novel approach for generating plans that adhere to user-specified constraints while optimizing for time-efficient execution. By leveraging linear temporal logic (LTL) to interpret natural language commands, SELP effectively handles complex commands and long-horizon tasks. 🤖 💡SELP presents three key insights: 1️⃣ Equivalence Voting: Ensures robust translations from natural language instructions into LTL specifications. 2️⃣ Constrained Decoding: Uses the generated LTL formula to guide the autoregressive inference of plans, ensuring the generated plans conform to the LTL. 3️⃣ Domain-Specific Fine-Tuning: Customizes LLMs for specific robotic tasks, boosting both safety and efficiency. 📊 Experiment: Our experiments demonstrate SELP’s effectiveness and generalizability across diverse tasks. In drone navigation, SELP outperforms state-of-the-art LLM planners by 10.8% in safety rate and by 19.8% in plan efficiency. For robot manipulation, SELP achieves a 20.4% improvement in safety rate. @yiwu @jiang719 #ICRA2025 #LLM #Robotics #Agent #LLMPlanner

reacted to their post with 🔥 1 day ago

Xwen 🔥 a series of open models based on Qwen2.5 models, developed by a brilliant research team of PhD students from the Chinese community. https://huggingface.co/collections/shenzhi-wang/xwen-chat-679e30ab1f4b90cfa7dbc49e ✨ 7B/72B ✨ Apache 2.0 ✨ Xwen-72B-Chat outperformed DeepSeek V3 on Arena Hard Auto

View all activity

Organizations

AdinaY's activity

liked a model 2 days ago

deepseek-ai/deepseek-vl2-tiny

Image-Text-to-Text • Updated Dec 18, 2024 • 46.5k • 105

liked a Space 2 days ago

191

Chat with DeepSeek-VL2-small

🌍

liked a Space 10 days ago

449

Qwen2.5 Max Demo

🐢

Send messages for chatbot responses

liked 2 models 10 days ago

m-a-p/YuE-s1-7B-anneal-zh-cot

Text Generation • Updated 8 days ago • 734 • 25

m-a-p/YuE-s1-7B-anneal-en-cot

Text Generation • Updated 8 days ago • 28.1k • 348

liked 2 models 11 days ago

deepseek-ai/Janus-Pro-7B

Any-to-Any • Updated 6 days ago • 248k • 2.7k

deepseek-ai/Janus-Pro-1B

Any-to-Any • Updated 6 days ago • 71.6k • 336

liked 2 models 12 days ago

Qwen/Qwen2.5-14B-Instruct-1M

Text Generation • Updated 9 days ago • 14.6k • 225

BlinkDL/rwkv-7-world

Text Generation • Updated 7 days ago • 62

liked 2 models 14 days ago

tencent/Hunyuan-7B-Instruct

Text Generation • Updated 14 days ago • 327 • 39

baichuan-inc/Baichuan-M1-14B-Base

Updated 13 days ago • 198 • 18

liked 3 Spaces 15 days ago

134

VideoLLaMA2

🎥

Media understanding

Open Agent Leaderboard

🥇

Open Agent Leaderboard

250

3D Arena

🏢

Generate a 3D leaderboard by voting

liked a model 16 days ago

bytedance-research/UI-TARS-72B-DPO

Image-Text-to-Text • Updated 13 days ago • 9.96k • 77

liked a Space 17 days ago

1.34k

Hunyuan3D-2.0

🌍

Text-to-3D and Image-to-3D Generation

liked a dataset 17 days ago

KwaiVGI/GameFactory-Dataset

Updated 23 days ago • 180 • 9

liked a model 17 days ago

tencent/Hunyuan3D-2

Image-to-3D • Updated 4 days ago • 43.4k • 806

liked a dataset 18 days ago

hithink-ai/MME-Finance

Viewer • Updated 16 days ago • 402 • 89 • 7

liked a model 18 days ago

deepseek-ai/DeepSeek-R1-Zero

Text Generation • Updated 6 days ago • 26.5k • 728