Can Linguistic Reasoning Vectors Enhance Multimodal Reasoning Ability?

arXiv:2609.31140 · cs.AI · Submitted 2026-09-25 · Read on arXiv

cs.AI

Submitted: 2026-09-25

Updated: 2026-09-25

Terminology

• Benchmark — 42× in this paper · explained in 2 episodes
• Adaptation — 36× in this paper · explained in 1 episode
• Alignment — 23× in this paper · explained in 1 episode
• Trace — 19× in this paper · explained in 2 episodes
• Accuracy — 17× in this paper · explained in 1 episode
• Multimodal Reasoning — 14× in this paper · explained in 5 episodes
• Steering — 10× in this paper · explained in 2 episodes
• Instruction Tuning — 4× in this paper · explained in 2 episodes
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• Reasoning Traces — 3× in this paper · explained in 3 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• In-Context Learning — 2× in this paper · explained in 4 episodes
• Vision-Language Models (VLMs) — 2× in this paper · explained in 6 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Activation Addition — 1× in this paper · explained in 1 episode
• Activation Steering — 1× in this paper · explained in 4 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Department of Motor Vehicles — 1× in this paper
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Multimodal Inputs — 1× in this paper · explained in 2 episodes
• Representation Engineering — 1× in this paper · explained in 2 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• Qwen2.5-VL Technical Report
• Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging
• Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
• Training Verifiers to Solve Math Word Problems
• Virgo: A Preliminary Exploration on Reproducing o1-like MLLM
• Towards a Unified View of Parameter-Efficient Transfer Learning
• Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
• Editing Models with Task Arithmetic
• When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
• In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
• MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
• Steering Llama 2 via Contrastive Activation Addition
• Function Vectors in Large Language Models
• Steering Language Models With Activation Engineering
• Self-Consistency Improves Chain of Thought Reasoning in Language Models
• Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning
• Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search
• Multimodal Chain-of-Thought Reasoning in Language Models
• Least-to-Most Prompting Enables Complex Reasoning in Large Language Models
• MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection