ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search
LLM self-training via process reward guided tree search.
Kaddo
New AI ToolsGuest Guru
AI ChatbotsAutomate guest messages on Airbnb, Booking.com, VRBO, or any OTA.
RecipioAI
Recipe Generators3DAiLY AI
Software DevelopmentFlexible Pricing Plans for Diverse Needs
R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
Incentivizing search capability in LLMs via reinforcement learning
BringOps
RecruitingRevolutionize DevOps & SRE Hiring with AI-Powered BringOps.
Cloud AI
Software DevelopmentExplore CouldAI's cutting-edge cloud-based AI platform offering scalable machine learning, natural language processing, and data analytics solutions for businesses.
Rubrics to Tokens: Token-Level Rewards for Instruction Following (April 2026)
Rubric-based RL with Token-Level Relevance Discriminator — solves credit assignment for instruction following by predicting which tokens satisfy specific constraints; fine-grained optimization
Launchpads
RecruitingRaspberry Pi ARM based bare metal examples
Controlla
Software DevelopmentMeet Controlla, the AI dashboard builder that turns business data into live, shareable insights—no spreadsheets or coding required.
RapidTextAI
Write Advance Articles using Multiple AI Models like GPT4, Gemini, Deepseek and grok.
LabEx.io
AI ChatbotsInteractive, hands-on learning platform for coding and technology.
Aasaan
Software DevelopmentLooking for an easy store management tool? Try Aasaan for its non-coding, SEO, APIs, and multiple interaction functionality.
Bappfy
Software DevelopmentWant to create a responsive app from your website without coding? Try Bappfy! This AI platform converts your website into an app in seconds, saving time.
Realtime OS on Embedded Systems
Hands-on Real-Time OS Education for Embedded Systems
Serverless Telegram bot
ChatGPT Telegram Bot, serverless on AWS Lambda
Vivgrid
Software DevelopmentBuild immersive worlds and production-grade AI agents—observe, orchestrate, and deploy globally with VivGrid.
Real-Time Bluetooth Networks - UTAustinX
Learn the design fundamentals of a real-time operating system (RTOS) and how to build a Bluetooth network in this hands-on project-based course.
RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning
Grounding Code LLMs in Execution Feedback
Equixly
Software DevelopmentEquixly Helps Users Improve Efficiency And Achieve More Through Intuitive, Powerful Features For Daily Work.
Reasoning Theater: Disentangling Model Beliefs from CoT (2026)
For simple tasks, the model's final answer is already decodable from early-layer activations before CoT generates a single token — CoT produces genuine belief change only on hard problems; probe-guided early-exit reduces token generation by 80% on simple tasks
Framedrop AI
Software DevelopmentAre you looking for an innovative AI-driven tool for extracting highlights from long videos? Look no further. Framedrop AI can help you enhance your reach.