alphaxiv - Robuta Search

https://github.com/alphaxiv/feedback GitHub - alphaXiv/feedback: Issue tracker for https://alphaxiv.org · GitHub Issue tracker for https://alphaxiv.org. Contribute to alphaXiv/feedback development by creating an account on GitHub. issue tracker github alphaxiv feedback https https://www.alphaxiv.org/?categories=%5B%22computer-science%22%5D&custom-categories=%5B%22agents%22%5D&organizations=%5B%22Anthropic%22%5D Explore | alphaXiv Discuss, discover, and read arXiv papers. Explore trending papers, see recent activity and discussions, and follow authors of arXiv papers on alphaXiv. explore alphaxiv https://www.alphaxiv.org/?custom-categories=%5B%22generative-models%22%5D&subcategories=%5B%22computer-vision-and-pattern-recognition%22%5D Explore | alphaXiv Discuss, discover, and read arXiv papers. Explore trending papers, see recent activity and discussions, and follow authors of arXiv papers on alphaXiv. explore alphaxiv https://www.alphaxiv.org/overview/2605.03413 Learning to Theorize the World from Observation | alphaXiv Researchers at KAIST introduced the Neural Theorizer (NEO), an AI system that learns to construct explicit, executable programs (theories) directly from ra the world learning observation alphaxiv https://www.alphaxiv.org/?organizations=%5B%22Tsinghua+University%22%5D Explore | alphaXiv Discuss, discover, and read arXiv papers. Explore trending papers, see recent activity and discussions, and follow authors of arXiv papers on alphaXiv. explore alphaxiv https://www.alphaxiv.org/?categories=%5B%22computer-science%22%5D&custom-categories=%5B%22agents%22%5D&subcategories=%5B%22robotics%22%5D Explore | alphaXiv Discuss, discover, and read arXiv papers. Explore trending papers, see recent activity and discussions, and follow authors of arXiv papers on alphaXiv. explore alphaxiv https://www.alphaxiv.org/?categories=%5B%22computer-science%22%5D&custom-categories=%5B%22agents%22%5D&subcategories=%5B%22artificial-intelligence%22%5D&organizations=%5B%22UCLA%22%5D Explore | alphaXiv Discuss, discover, and read arXiv papers. Explore trending papers, see recent activity and discussions, and follow authors of arXiv papers on alphaXiv. explore alphaxiv https://www.alphaxiv.org/overview/2605.03327 DGPO: Distribution Guided Policy Optimization for Fine Grained Credit Assignment | alphaXiv Researchers from Peking University, SJTU, and Tsinghua University developed Distribution-Guided Policy Optimization (DGPO), a critic-free reinforcement lea policy optimization distribution guided https://www.alphaxiv.org/?categories=%5B%22computer-science%22%5D&custom-categories=%5B%22agents%22%5D&subcategories=%5B%22artificial-intelligence%22%5D&organizations=%5B%22Anthropic%22%5D Explore | alphaXiv Discuss, discover, and read arXiv papers. Explore trending papers, see recent activity and discussions, and follow authors of arXiv papers on alphaXiv. explore alphaxiv https://www.alphaxiv.org/abs/2605.04045 Audio-Visual Intelligence in Large Foundation Models | alphaXiv View recent discussion. Abstract: Audio-Visual Intelligence (AVI) has emerged as a central frontier in artificial intelligence, bridging auditory and visual... audio visual foundation models intelligence large alphaxiv https://www.alphaxiv.org/?categories=%5B%22computer-science%22%5D&custom-categories=%5B%22agents%22%5D&subcategories=%5B%22artificial-intelligence%22%2C%22computer-vision-and-pattern-recognition%22%5D Explore | alphaXiv Discuss, discover, and read arXiv papers. Explore trending papers, see recent activity and discussions, and follow authors of arXiv papers on alphaXiv. explore alphaxiv https://www.alphaxiv.org/overview/2604.25917 Recursive Multi-Agent Systems | alphaXiv RecursiveMAS introduces a framework that integrates recursive computation into multi-agent systems, enabling agents to refine collaborative reasoning throu multi agent recursive systems alphaxiv https://www.alphaxiv.org/audio/2605.04984 Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers | alphaXiv View recent discussion. Abstract: Long-horizon LLM agents depend on intermediate information-gathering turns, yet training feedback is usually observed only at... https://www.alphaxiv.org/?categories=%5B%22computer-science%22%5D&custom-categories=%5B%22agents%22%5D&subcategories=%5B%22artificial-intelligence%22%5D Explore | alphaXiv Discuss, discover, and read arXiv papers. Explore trending papers, see recent activity and discussions, and follow authors of arXiv papers on alphaXiv. explore alphaxiv https://www.alphaxiv.org/about About Us | alphaXiv Open discussion directly on arXiv papers. Created by researchers who believe academia should be more open, accessible, and connected. us alphaxiv https://www.alphaxiv.org/?categories=%5B%22computer-science%22%5D&custom-categories=%5B%22agents%22%5D&subcategories=%5B%22artificial-intelligence%22%2C%22computer-vision-and-pattern-recognition%22%2C%22robotics%22%5D Explore | alphaXiv Discuss, discover, and read arXiv papers. Explore trending papers, see recent activity and discussions, and follow authors of arXiv papers on alphaXiv. explore alphaxiv https://www.alphaxiv.org/overview/2605.05185 OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents | alphaXiv OpenSearch-VL introduces an open-source recipe for training multimodal deep search agents, providing high-quality, openly available training data, a divers open recipe multimodal search opensearch vl https://www.alphaxiv.org/@george-yu Feng (George) Yu | alphaXiv Research Interests: Database Systems, Big Data, Blockchain, Quantum Computing feng george yu alphaxiv https://www.alphaxiv.org/?categories=%5B%22computer-science%22%5D&custom-categories=%5B%22agents%22%5D&subcategories=%5B%22artificial-intelligence%22%2C%22sound%22%5D Explore | alphaXiv Discuss, discover, and read arXiv papers. Explore trending papers, see recent activity and discussions, and follow authors of arXiv papers on alphaXiv. explore alphaxiv https://www.alphaxiv.org/abs/2605.02730 Perceptual Flow Network for Visually Grounded Reasoning | alphaXiv View recent discussion. Abstract: Despite the success of Large-Vision Language Models (LVLMs), general optimization objectives (e.g., standard MLE) fail to... perceptual flow network visually grounded https://www.alphaxiv.org/overview/2605.06388 Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models | alphaXiv A study on action-conditioned Latent Diffusion Models (LDMs) for robotics reveals that semantic-aligned latent spaces consistently outperform reconstructio https://www.alphaxiv.org/?categories=%5B%22computer-science%22%5D&custom-categories=%5B%22agent-based-systems%22%5D Explore | alphaXiv Discuss, discover, and read arXiv papers. Explore trending papers, see recent activity and discussions, and follow authors of arXiv papers on alphaXiv. explore alphaxiv https://www.alphaxiv.org/audio/2605.02730 Perceptual Flow Network for Visually Grounded Reasoning | alphaXiv View recent discussion. Abstract: Despite the success of Large-Vision Language Models (LVLMs), general optimization objectives (e.g., standard MLE) fail to... perceptual flow network visually grounded https://www.alphaxiv.org/audio/2605.06507 MARBLE: Multi-Aspect Reward Balance for Diffusion RL | alphaXiv View recent discussion. Abstract: Reinforcement learning fine-tuning has become the dominant approach for aligning diffusion models with human preferences.... marble multi aspect reward balance https://www.alphaxiv.org/abs/2605.03937 MiniMind-O Technical Report: An Open Small-Scale Speech-Native Omni Model | alphaXiv View recent discussion. Abstract: MiniMind-O is an open 0.1B-scale omni model built on the MiniMind language model. It accepts text, speech, and image inputs,... https://www.alphaxiv.org/abs/2605.06548 Continuous Latent Diffusion Language Model | alphaXiv View 1 comment: A very promising direction for next-generation AI. The idea of separating semantic structure from textual realization feels closer to how... latent diffusion language model continuous alphaxiv https://www.alphaxiv.org/overview/2605.03677 Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe | alphaXiv Researchers from Zhejiang University and Tencent introduce Uni-OPD, a unified on-policy distillation framework that enhances student exploration and teache https://www.alphaxiv.org/overview/2605.02087 Model Spec Midtraining: Improving How Alignment Training Generalizes | alphaXiv Model Spec Midtraining (MSM) introduces a two-stage training approach that first pre-trains language models on synthetic documents derived from a model spec improving alignment training alphaxiv https://www.alphaxiv.org/?categories=%5B%22computer-science%22%5D&custom-categories=%5B%22agents%22%5D&subcategories=%5B%22artificial-intelligence%22%2C%22computer-vision-and-pattern-recognition%22%5D&organizations=%5B%22National+University+of+Singapore%22%5D Explore | alphaXiv Discuss, discover, and read arXiv papers. Explore trending papers, see recent activity and discussions, and follow authors of arXiv papers on alphaXiv. explore alphaxiv https://www.alphaxiv.org/?categories=%5B%22computer-science%22%5D&sort=Hot Explore | alphaXiv Discuss, discover, and read arXiv papers. Explore trending papers, see recent activity and discussions, and follow authors of arXiv papers on alphaXiv. explore alphaxiv https://www.alphaxiv.org/?categories=%5B%22computer-science%22%5D&custom-categories=%5B%22agents%22%2C%22agentic-frameworks%22%5D Explore | alphaXiv Discuss, discover, and read arXiv papers. Explore trending papers, see recent activity and discussions, and follow authors of arXiv papers on alphaXiv. explore alphaxiv https://www.alphaxiv.org/signin Sign In | alphaXiv sign alphaxiv https://www.alphaxiv.org/audio/2604.04707v1 OpenWorldLib: A Unified Codebase and Definition of Advanced World Models | alphaXiv View recent discussion. Abstract: World models have garnered significant attention as a promising research direction in artificial intelligence, yet a clear... world models unified codebase https://www.alphaxiv.org/audio/2602.18432 SARAH: Spatially Aware Real-time Agentic Humans | alphaXiv View recent discussion. Abstract: As embodied agents become central to VR, telepresence, and digital human applications, their motion must go beyond... real time sarah aware agentic humans