arXiv AI
From Stages to States: Unified Iterative Reasoning for MLLMs
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jun 16
DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
arXiv:2606. 15160v1 Announce Type: cross Abstract: Reasoning capabilities of multimodal large language models (MLLMs) have improved considerably in recent years.
arXiv Machine Learning
Jun 25
SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical Reasoning
arXiv:2507. 16518v3 Announce Type: replace-cross Abstract: Recent advances in multimodal large language models (MLLMs) have shown impressive reasoning capabilities.
arXiv AI
Sep 28
Can Linguistic Reasoning Vectors Enhance Multimodal Reasoning Ability?
The paper introduces LIFT, a lightweight vector‑intervention technique that transfers reasoning capability from a base large language model (LLM) to a vision‑language model (VLM) without retraining the VLM backbone. LIFT defines Reasoning Vectors as differences in hidden states between a reasoning path with an explicit trace and a solver path without it, and injects these vectors into the VLM’s language‑side activations. Experiments on two VLMs across six reasoning benchmarks show that vectors derived from the base LLM consistently outperform those derived from the aligned VLM, indicating that the base LLM is a more effective source for recovering degraded reasoning. "whyItMatters":"The study demonstrates that a simple, frozen‑backbone intervention can partially restore reasoning abilities in multimodal models, highlighting the value of leveraging the original language model’s reasoning power."
arXiv Computer Vision
Sep 21
DRT: Dense Reasoning Trace for Efficient and Grounded Multimodal Reasoning
arXiv:2609.21675v1 Announce Type: new Abstract: Despite the remarkable progress in Multimodal Large Language Models (MLLMs), prevailing Chain-of-Thought (CoT) paradigms remain confined to the natural...
arXiv Machine Learning
Jul 2
VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning
arXiv:2511. 17731v2 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) prompting has proven remarkably effective for eliciting complex reasoning in large language models (LLMs).
arXiv AI
Aug 11
StructReward: Efficient Structured Process Rewards for Self-Correcting Multimodal Reasoning
arXiv:2608. 08326v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective approach for improving multimodal reasoning.