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:
Ask smarter, not more: a shopping agent that finds one hidden product among 50,000 in ~3 turns. Achieves 82% technical score on a public data set, offline with zero LLM calls.
An autonomous AI research agent that builds, tests, and optimizes recommender systems, with auditable evidence for every decision.
The hardest AI image to catch is the one the internet has already changed. GLowCLIP fuses global context and local forensic traces to detect it after compression, blur, crop, and noise.
Can you tell if an image was made by AI?Real or Fake (ROF) is a model that looks for AI-generated images, even when they've been blurred, resized, cropped, or heavily compressed.
TrueSight helps human reviewers assess whether an image may be AI-generated—and whether that prediction is stable, by stress-testing results under common image transformations.
automate evaluate
Search Made Smarter
From conversation to the right product—precise and fast.
AURA doesn't just tune a recommender — it proves it: a firewalled, fully logged search that beat the FM baseline by +0.0039 with zero human input and zero API spend.
TrueFrame detects AI-generated images by fusing CLIP visual embeddings with FFT frequency signals, improving robustness to compression, blur, resizing, noise, colour shifts, and cropping.
Mercury helps you find the correct product through a conversation. It asks useful questions, remembers what matters and adapts when your preferences change without making you repeat everything again.
Ro-BustAI is a robust AI-image detector combining spatial & frequency analysis to distinguish real from synthetic content, maintaining reliable detection even after real world image transformations
0.6075 vs the official 0.6016 baseline on KuaiRand-Pure — ~7× seed noise, CPU-only, inside one 300s budget — produced autonomously: 5 iterations to convergence, 0 manual interventions.
An end-to-end short-video recommendation pipeline that combines LLM embeddings with tabular features using SENet-DeepFM architecture and dynamic hybrid loss.
TAISP is back with a brand new invention
CamTrace-6M fuses frozen CLIP semantics with camera-pipeline residuals to detect AI-generated images after JPEG compression, blur, resizing, noise, colour changes, and cropping.
TacoRank: an autonomous AI research team that plans, codes, breaks, recovers, and learns — beating a short-video ranking baseline while you sleep.
Filter on nothing. Score on everything.
An AI research engineer that improves recommender models while you sleep.
In today's day and age, can you still tell the difference between real and AI-generated images? We strive to build a robust AI-image detector that survives compression, cropping and filters
Autonomous ML agent - Zero human intervention
Robust Detection of AI-Generated Images Under Real-World Transformations.
CompassCart is an offline AI product-search agent using a versioned ledger, hybrid retrieval, and adaptive reranking. It asks only high-gain questions and guarantees 10 sanitized, valid catalog IDs.
Afterimage detects AI-generated images after the platform has compressed, blurred and resized them — cutting accuracy loss under real-world post-processing from 15.7 points to 2.5.