AI
New AI that keeps creativity: DPWriter LLMs trained with reinforcement learning often play it safe, shrinking the variety of their stories. DPWriter flips the script by planning before writing. It breaks generation into semi-structured steps, then uses Diverse Planning Branching to explore multiple, intentionally different routes. A group-aware diversity reward
AI
What if AI could think with pictures? Omni-R1 is a new multimodal AI that doesn’t just “talk through” problems—it draws its intermediate steps. Instead of relying on one fixed reasoning style, it unifies many skills (like zooming into regions, pointing to objects, or marking paths) by generating small
ReinforcementLearning
Curious how the algorithms that learn to play games can also steer quantum devices? This beginner-friendly tutorial walks you from classical reinforcement learning (RL) basics to quantum RL, showing how these ideas power practical tasks in quantum control. What makes it different: * Plain-English explanations that connect math to intuition. * Step-by-step,
AI
Designing particle detectors is complex and slow. A new study tests whether large language models (LLMs) can help—by proposing complete detector layouts from simple prompts, which are then scored by the same simulators used for reinforcement learning (RL). * What they tried: Feed LLMs task constraints and summaries of past
Robotics
Humanoid robots aren’t just walking anymore—they’re vaulting, dive‑rolling, and navigating messy ground like a traceur. “Deep Whole‑body Parkour” blends two worlds: smart footstep planning and full‑body skill tracking, so a single policy uses what it sees to coordinate hands, feet, and torso on uneven
AI
TowerMind is a new, lightweight tower-defense game environment for testing AI agents, especially large language models (LLMs), on planning and decision-making. * Low compute cost and easy to run * Multimodal observations: pixels, text, and structured game state * Customizable levels and rules * Built-in tests for model hallucination The authors create five benchmark
AI
Personalized AI you can read, edit, and take anywhere Most AI systems hide your preferences in opaque vectors. This work makes them plain English instead. Your "profile" becomes a short text summary the model can use across apps and tasks. * Interpretable: you can see and revise what the
AI
Smarter AI means knowing when to think harder LLMs can improve by thinking longer, but they rarely know how much thinking a task really needs. ROI-Reasoning trains models to plan their effort under a hard token budget, like students managing time on an exam. * Meta-Cognitive Fine-Tuning: Before answering, the model
AI
AI assistants that click, type, and navigate apps need practice worlds — but real, trainable web environments are scarce. InfiniteWeb changes that by automatically generating realistic, multi-page websites at scale so GUI agents can learn real tasks, not toy demos. How it works * Unified specs: A single blueprint ties pages, flows,
AI
LLMs can learn to reason—without task verifiers Many real-world problems don’t have automatic checkers to grade answers, even though we have lots of expert solutions. RARO (Relativistic Adversarial Reasoning Optimization) shows how to train reasoning skills from those examples alone. How it works: * A policy (the model) tries
AI
Large models are powerful, but solving deep, multi-step problems is pricey. ToolOrchestra trains a small “orchestrator” that decides which tools to use, when, and how—like a smart project manager for AI. It uses reinforcement learning with rewards for outcomes, efficiency, and user preferences. The result: an 8B Orchestrator that
AI
Small model, big wins Large language models are great generalists, but really tough, multi-step problems still strain both brains and budgets. ToolOrchestra flips the script: instead of one giant model, a small “orchestrator” coordinates other models and specialized tools. Trained with reinforcement learning that rewards outcomes, efficiency, and user preferences,