M2-Reasoning: Empowering MLLMs with Unified General and Spatial Reasoning
pith:57IYSYULopen to challenge →
read the original abstract
Recent advancements in Multimodal Large Language Models (MLLMs), particularly through Reinforcement Learning with Verifiable Rewards (RLVR), have significantly enhanced their reasoning abilities. However, a critical gap persists: these models struggle with dynamic spatial interactions, a capability essential for real-world applications. To bridge this gap, we introduce M2-Reasoning-7B, a model designed to excel in both general and spatial reasoning. Our approach integrates two key innovations: (1) a novel data pipeline that generates 294.2K high-quality data samples (168K for cold-start fine-tuning and 126.2K for RLVR), which feature logically coherent reasoning trajectories and have undergone comprehensive assessment; and (2) a dynamic multi-task training strategy with step-wise optimization to mitigate conflicts between data, and task-specific rewards for delivering tailored incentive signals. This combination of curated data and advanced training allows M2-Reasoning-7B to set a new state-of-the-art (SOTA) across 8 benchmarks, showcasing superior performance in both general and spatial reasoning domains.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
GeoLaux: A Benchmark for Evaluating MLLMs' Geometry Performance on Long-Step Problems Requiring Auxiliary Lines
GeoLaux is a new benchmark of 2186 long-step geometry problems requiring auxiliary lines, used to evaluate 23 MLLMs and reveal major drops in performance on complex tasks.
-
MHPR: Multidimensional Human Perception and Reasoning Benchmark for Large Vision-Languate Models
MHPR is a multidimensional benchmark for LVLM human-centric perception-reasoning with C-RD, SFT-D, RL-D, T-D data tiers and ACVG pipeline, showing training gains on Qwen2.5-VL-7B to near-parity with larger models.
-
Dual Tuning for Reasoning Efficacy-Driven Data Curation in Multimodal LLM Training
Dual Tuning is a data curation method that jointly scores training examples for benefit and for reasoning-gain to choose between reasoning and direct-answer post-training modes for multimodal LLMs.
-
Trust Region On-Policy Distillation
TrOPD stabilizes on-policy distillation for LLMs with trust-region learning, outlier estimation, and off-policy guidance, outperforming prior OPD methods on reasoning and code benchmarks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.