61 82 201

Asankhaya Sharma

codelion

http://asankhaya.github.io/

AI & ML interests

AI/ML, Dev Tools and Application Security

Recent Activity

reacted to their post with 👍 3 days ago

🧬 Hey everyone! Just released **OpenEvolve** - an open-source implementation of Google DeepMind's AlphaEvolve system. It's an evolutionary coding agent that uses LLMs to discover and optimize algorithms. I successfully replicated DeepMind's results on circle packing (99.97% match!) and evolved a random search into a simulated annealing algorithm. ✨ Key features: - Evolves entire codebases (not just single functions) - Works with any OpenAI-compatible API - LLM ensemble approach for better results - Multi-objective optimization 👉 Check it out: GitHub: https://github.com/codelion/openevolve Blog post: https://huggingface.co/blog/codelion/openevolve Would love to hear your thoughts or answer any questions about it!

upvoted a paper 3 days ago

Chain-of-Model Learning for Language Model

reacted to their post with ❤️ 3 days ago

View all activity

Organizations

codelion's activity

upvoted a paper 3 days ago

Chain-of-Model Learning for Language Model

Paper • 2505.11820 • Published 7 days ago • 105

upvoted an article 4 days ago

Article

OpenEvolve: An Open Source Implementation of Google DeepMind's AlphaEvolve

•

4 days ago

• 11

upvoted an article 7 days ago

Article

Introducing Pivotal Token Search (PTS): Targeting Critical Decision Points in LLM Training

•

7 days ago

• 4

upvoted a paper 8 days ago

Phi-4 Technical Report

Paper • 2412.08905 • Published Dec 12, 2024 • 118

upvoted a collection 10 days ago

Pivotal Token Search

Collection

Pivotal Token Search (PTS) identifies tokens in a language model's generation that significantly impact the probability of success • 9 items • Updated 10 days ago • 3

upvoted 2 papers 11 days ago

Learning from Peers in Reasoning Models

Paper • 2505.07787 • Published 12 days ago • 44

Scalable Chain of Thoughts via Elastic Reasoning

Paper • 2505.05315 • Published 16 days ago • 24

upvoted a paper 16 days ago

ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Paper • 2505.04588 • Published 17 days ago • 63

upvoted a paper 17 days ago

Absolute Zero: Reinforced Self-play Reasoning with Zero Data

Paper • 2505.03335 • Published 18 days ago • 157

upvoted a paper 21 days ago

A Survey of Interactive Generative Video

Paper • 2504.21853 • Published 24 days ago • 45

upvoted 2 papers 23 days ago

Phi-4-Mini-Reasoning: Exploring the Limits of Small Reasoning Language Models in Math

Paper • 2504.21233 • Published 24 days ago • 43

WebThinker: Empowering Large Reasoning Models with Deep Research Capability

Paper • 2504.21776 • Published 24 days ago • 53

upvoted 3 papers 24 days ago

UniversalRAG: Retrieval-Augmented Generation over Multiple Corpora with Diverse Modalities and Granularities

Paper • 2504.20734 • Published 25 days ago • 61

Reinforcement Learning for Reasoning in Large Language Models with One Training Example

Paper • 2504.20571 • Published 25 days ago • 91

ReasonIR: Training Retrievers for Reasoning Tasks

Paper • 2504.20595 • Published 25 days ago • 52

upvoted a paper 26 days ago

Towards Understanding Camera Motions in Any Video

Paper • 2504.15376 • Published Apr 21 • 155

upvoted a paper 29 days ago

Step1X-Edit: A Practical Framework for General Image Editing

Paper • 2504.17761 • Published 30 days ago • 88

upvoted 3 papers about 1 month ago

VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models

Paper • 2504.15279 • Published Apr 21 • 74

LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities

Paper • 2504.16078 • Published Apr 22 • 20

TTRL: Test-Time Reinforcement Learning

Paper • 2504.16084 • Published Apr 22 • 108