Devpost
Participate in our public hackathons
Devpost for Teams
Access your company's private hackathons
Grow your developer ecosystem and promote your platform
Drive innovation, collaboration, and retention within your organization
By use case
Blog
Insights into hackathon planning and participation
Customer stories
Inspiration from peers and other industry leaders
Planning guides
Best practices for planning online and in-person hackathons
Webinars & events
Upcoming events and on-demand recordings
Help desk
Common questions and support documentation
Sort by:
AI-generated image detection that stays accurate even after compression, blur, and cropping
An autonomous recommender-systems research agent that plans, tests, evaluates, and documents evidence-driven model improvements.
An autonomous agent that runs its own ML experiments—feature engineering, loss tuning, hyperparameter search—to beat baseline short-video recommenders, no human in the loop.
A detector that stress-tests its own answers, so you know which ones to trust.
An autonomous ML agent powered by Gemini that independently architectures, debugs, and tunes PyTorch recommendation models, successfully beating the ByteDance baseline with zero human intervention.
Better ranking, one experiment at a time.
Not just keyword matching, it's a shopping assistant that understands intent, remembers context, and asks the right question at the right time
Robust Detection of AI‑Generated Images Under Real‑World Transformations
A fully autonomous machine learning engineer agent with the ability to self heal, analyze, evaluate and make improvements.
Conversational shopping copilot with a focus on accessibility-aware retrieval and ranking.
Comparing how small multimodal models (SigLIP) and Vision Language Models (Qwen) perform on detecting AIGC
A CLIP-based AI-image detector, rigorously stress-tested for robustness to real-world compression, blur, noise and cross-generator shift — failure modes measured, not hidden!
Backend middleware that redacts sensitive runtime data while preserving clear, structured Agent Run evidence.
glhf
My submission for the 2026 TikTok Techjam "4. Shopping Copilot: AI Conversational Search and Recommendations". This was mostly generated by LLMs, aiming to understand how LLMs fare at such a problem
Autonomous ML Research Agent for Recommender Systems
Same outputs, 7.1x faster: hand-tuned Triton kernels and CUDA graphs for Transformers on a Tesla T4.
We gave an AI agent a dataset and a scoring rule without hints. It proposed, coded, and tested its own recommender models, which beat the official baseline entirely on its own.
An LLM-driven agent that runs the ML research loop without a human in it: propose a hypothesis, write a complete training script, execute it in a sandbox, score it, reflect on the result, repeat.
AgentGuard, a Glass Box span tree
A shopping agent that knows the difference between browsing and buying - and asks smarter questions because of it.
From vague shopping intent to relevant, constraint-aware product recommendations—fast, explainable, and privacy-friendly.
An autonomous recommender research agent that safely proposes, tests, and audits model improvements inside an isolated sandbox.
"Conversational search that tightens with every clue, and never asks a question it already knows the answer to."
