…Shaokai Ye , , , , , Abstract A balanced reinforcement learning framework for image captioning that jointly optimizes correctness, coverage, and linguistic quality while improving performance over existing methods. AI-generated summary Image captioning is one…
…Hanyu Wang , , , , Abstract SkillGrad is a gradient-descent-inspired framework that optimizes agent skills through trajectory-level loss evidence and text-based gradients, enhancing skill reliability and performance in specialized domains. AI…
…A Unified Recipe for Evolutionary Kernel Optimization (2026) GPU-Accelerated Optimization of Transformer-Based Neural Networks for Real-Time Inference (2026) CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance…
…Scaling Agentic Reasoning via Exploration-Aware Policy Optimization Published on May 12 Submitted by Xingyuan Hua on May 14 Tsinghua University Authors: Xingyuan Hua , , Abstract Agents use variational inference to evaluate exploratory…
…Diverse Parallel Exploration Policy Optimization for LLM-based Agents (2026) GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning (2026) FIPO: Eliciting Deep Reasoning with Future-KL…
…Bingda Tang , Yuhui Zhang , , , , Abstract Researchers developed a novel method called Variational GRPO that improves text-to-image synthesis by combining ELBO-based surrogates with Group Relative Policy Optimization, achieving faster and…
…Their coordinated integration leads to stable and consistently strong performance across diverse problem landscapes. Work focuses on improving the efficiency and robustness of distributed black box optimization in multi-agent systems. Potential…
…We propose ROMA, an RL fine-tuning framework that modifies the optimization dynamics to reinforce reasoning against visual degradation while preserving clean-input performance. A dual-forward-pass strategy uses teacher forcing…
…An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe (2026) CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels (2026) Please…
…Yunho Choi , Jongwon Lim , , , , Abstract POISE enables stable and efficient policy optimization for large reasoning models by estimating baselines using internal model signals, reducing computational overhead while maintaining performance comparable to existing…