Neural intel Pod

AI and Robotics

This academic paper explores ZeroTIR, a novel method for training Large Language Models (LLMs) to spontaneously use external tools, specifically Python code execution, for mathematical problem-solvin…

This academic paper critically re-evaluates the widespread belief that Reinforcement Learning with Verifiable Rewards (RLVR) enhances the fundamental reasoning capabilities of large language models (…

This document investigates how the quality of a reward model impacts the training efficiency of language models using Reinforcement Learning from Human Feedback (RLHF). It argues that while accuracy …

This document presents research on improving power grid management through reinforcement learning. The authors introduce a model-free approach using a masked action space that allows agents to learn …

This research presents LGTC-IPPO, a novel decentralized reinforcement learning approach designed for allocating diverse resources among multiple agents. The core innovation lies in its integration of…

This document details a reinforcement learning approach for enabling humanoid robots with multi-fingered hands to perform dexterous manipulation tasks based on visual input. The core challenges addre…

This document introduces µCODE, a novel approach for generating code iteratively based on execution feedback, departing from complex multi-turn reinforcement learning by leveraging the insight that c…

This pod introduces Confidence-Reward driven Preference Optimization (CRPO), a novel method for improving machine translation by more effectively selecting training data for large language models (LL…

This academic paper introduces MiCRo, a two-stage framework designed to improve how Large Language Models (LLMs) learn and adapt to diverse human preferences, moving beyond the traditional assumption…

This document introduces Prolonged Reinforcement Learning (ProRL), a new training method designed to significantly enhance the reasoning abilities of large language models. By implementing KL diverge…

This academic paper introduces PROXYTHINKER, a novel inference-time method designed to enhance the visual reasoning abilities of large vision-language models (LVLMs). Unlike computationally expensive…

This academic paper presents Open CaptchaWorld, a novel benchmark dataset designed to assess the ability of multimodal AI agents to solve complex, multi-step CAPTCHAs encountered in real-world online…

This document presents DexMachina, a novel curriculum-based reinforcement learning algorithm for functional retargeting in bimanual dexterous manipulation. The method focuses on teaching robot hands …

This work introduces a novel approach and a new benchmark for advancing embodied AI agents operating in 3D environments. The proposed model, 3DLLM-MEM, is designed with a dual-memory system, combinin…

This podcast offers a comprehensive overview of fine-tuning large language models (LLMs), exploring both foundational principles and advanced techniques. It details a seven-stage pipeline for fine-tu…

This document presents RENT, a novel method for improving the reasoning abilities of language models using unsupervised reinforcement learning. Instead of relying on external feedback or ground-truth…

This work examines the critical points of random neural networks, particularly as network depth increases in the infinite-width limit. The authors provide asymptotic formulas for the expected number …

This source introduces BAGEL, a large multimodal model designed for unified image understanding and generation. It discusses the model's Mixture-of-Transformer-Experts (MoT) architecture, highlightin…

This document introduces R1-Searcher++, a novel framework for Large Language Models (LLMs) designed to improve their ability to handle factual questions by strategically utilizing both their internal…