Author: insights

1. The Landscape of Agentic Reinforcement Learning for LLMs: A Survey 🔑 Keywords: Agentic reinforcement learning, Large language models, POMDPs, Decision-making agents, […]

1. PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning 🔑 Keywords: PVPO, computational cost, data pre-sampling, reinforcement learning, State-Of-The-Art (SOTA) 💡 Category: […]

1. R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning 🔑 Keywords: auto-thinking, multimodal large language models, bi-mode […]

1. Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning 🔑 Keywords: Reward Hacking, GRPO, Text-to-Image Generation, Preference Fitting, Semantic Consistency […]

1. Beyond Transcription: Mechanistic Interpretability in ASR 🔑 Keywords: Interpretability methods, ASR, logit lens, semantic biases, repetition hallucinations 💡 Category: Foundations of […]

1. AgentFly: Fine-tuning LLM Agents without Fine-tuning LLMs 🔑 Keywords: Memory-augmented Markov Decision Process (M-MDP), Neural case-selection policy, Episodic memory, Continuous learning […]

1. Intern-S1: A Scientific Multimodal Foundation Model 🔑 Keywords: Multimodal Mixture-of-Experts, reinforcement learning, scientific domains, open-source models, Artificial General Intelligence 💡 Category: […]

1. From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models 🔑 Keywords: FinCDM, AI Native, Large Language […]

1. Ovis2.5 Technical Report 🔑 Keywords: AI Native, Vision Transformer, Multimodal Reasoning, Native-Resolution, Thinking Mode 💡 Category: Multi-Modal Learning 🌟 Research Objective: […]

1. SSRL: Self-Search Reinforcement Learning 🔑 Keywords: LLMs, Self-Search, Self-Search RL, Reinforcement Learning 💡 Category: Reinforcement Learning 🌟 Research Objective: – To […]

1. We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning 🔑 Keywords: MLLMs, mathematical reasoning, reinforcement learning, knowledge system, AI-generated […]

1. Story2Board: A Training-Free Approach for Expressive Storyboard Generation 🔑 Keywords: Story2Board, consistency framework, AI-generated summary, diffusion models, Scene Diversity 💡 Category: […]