Tag: Multimodal Systems

All the articles with the tag "Multimodal Systems".

• Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model

  Published: 3 Jun, 2025 |  at  11:42 AM

  

  85.21 🤔

  本文通过ComPABench基准评估视觉-语言模型（VLMs）的组合推理能力，发现强化学习（RL）优于监督微调（SFT）在跨任务和分布外泛化中的表现，并提出RL-Ground方法显著提升多模态组合推理性能。

• Reverse Preference Optimization for Complex Instruction Following

  Published: 1 Jun, 2025 |  at  11:44 AM

  

  85.20 🤔

  本文提出逆向偏好优化（RPO）方法，通过动态反转指令中未满足的约束消除偏好对噪声，在多轮复杂指令跟随任务上显著优于DPO基线，并在70B模型上超越GPT-4o。

• Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL

  Published: 1 Jun, 2025 |  at  11:52 AM

  

  85.07 🤔

  本文提出PNLC方法，通过离线RL训练轻量级目标条件值函数辅助大型语言模型在多轮交互任务中进行高效长程规划，在性能和计算效率上显著优于现有RL微调和推理时搜索方法。

• Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models

  Published: 8 May, 2025 |  at  06:19 PM

  

  83.98 🤔

  This paper introduces a recursive summarization method to enhance long-term dialogue memory in LLMs, achieving marginal quantitative improvements and notable qualitative gains in consistency and coherence across multiple models and datasets.

• Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems

  Published: 12 May, 2025 |  at  11:20 AM

  

  82.89 🤔

  This paper introduces Recursive INference Scaling (RINS), a method that recursively applies a model block to exploit language's self-similarity, achieving significant performance gains in language and multimodal tasks under compute-matched conditions while offering inference flexibility through stochastic training and linear adapters.