Can Merging Text‑Only and Grounded Visual Reasoning Unlock Better Vision‑Language Models?

The paper introduces Mixture‑of‑Visual‑Thoughts (MoVT), a context‑adaptive reasoning paradigm that integrates pure‑text and visually‑grounded inference modes within a single model, and presents the two‑stage AdaVaR training framework with a novel AdaGRPO reinforcement‑learning algorithm to automatically select the optimal mode for each visual‑language task, achieving consistent gains across eight benchmarks and surpassing strong baselines including GPT‑4o.

AdaVaRMixture-of-Visual-ThoughtsReinforcement Learning

0 likes · 16 min read

Can Merging Text‑Only and Grounded Visual Reasoning Unlock Better Vision‑Language Models?

Kuaishou Tech

Nov 5, 2025 · Artificial Intelligence

How HiPO Gives LLMs a Smart Thinking Switch to Cut Costs and Boost Accuracy

This article explains the overthinking problem of large language models, introduces the HiPO framework with hybrid data cold‑start and reinforcement‑learning reward mechanisms that let models decide when to think deeply or answer directly, and shows experimental results demonstrating significant efficiency gains and accuracy improvements across multiple benchmarks.

Hybrid Policy OptimizationLLMReinforcement Learning

0 likes · 13 min read

How HiPO Gives LLMs a Smart Thinking Switch to Cut Costs and Boost Accuracy

Xiaohongshu Tech REDtech

Jun 19, 2025 · Artificial Intelligence

Can Adaptive Chain‑of‑Thought Learning Halve LLM Thinking Time?

The article introduces the Think When You Need (TWYN) method, a reinforcement‑learning approach that dynamically adapts chain‑of‑thought length, dramatically cuts redundant token generation in large language models, and maintains or improves accuracy across diverse reasoning benchmarks.

Chain-of-ThoughtReinforcement Learningadaptive inference

0 likes · 9 min read

Can Adaptive Chain‑of‑Thought Learning Halve LLM Thinking Time?

Baobao Algorithm Notes

May 26, 2025 · Artificial Intelligence

When Should Large Language Models Think? 10 Cutting‑Edge Strategies to Boost Reasoning Efficiency

This article reviews ten recent papers that tackle the over‑thinking problem in large language models by shortening chain‑of‑thought reasoning, introducing dynamic early‑exit, adaptive thinking triggers, and reinforcement‑learning‑based training, showing how models can maintain or improve accuracy while dramatically reducing token usage and latency.

AI researchModel Pruningadaptive inference

0 likes · 38 min read

When Should Large Language Models Think? 10 Cutting‑Edge Strategies to Boost Reasoning Efficiency