MM-OptBench is a solver-grounded benchmark showing current multimodal LLMs reach at most 52% pass@1 on generating correct optimization models from text-plus-visual problem specifications.
hub
MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning
23 Pith papers cite this work. Polarity classification is still indexing.
23
Pith papers citing it
abstract
DeepSeek R1, and o1 have demonstrated powerful reasoning capabilities in the text domain through stable large-scale reinforcement learning. To enable broader applications, some works have attempted to transfer these capabilities to multimodal reasoning. However, these efforts have been limited by the limited difficulty of selected tasks and relatively small training scales, making it challenging to demonstrate strong multimodal reasoning abilities. To address this gap, we introduce the MMK12 dataset and MM-EUREKA with 7B and 32B parameters. The former is a high-quality multimodal mathematics reasoning dataset featuring diverse knowledge domains with human-verified answers and solution processes. The latter is a multimodal model employing rule-based reinforcement learning on MMK12, utilizing online filtering and two-stage training strategy to enhance training stability. MM-EUREKA demonstrates remarkable performance gains in multimodal mathematical reasoning, outperforming previous powerful models like InternVL2.5-78B or InternVL2.5-38B-MPO. In particular, MM-EUREKA achieves competitive or superior performance compared to both open-source and closed-source models, and trails slightly behind o1 in multidisciplinary reasoning tasks. We open-source our complete pipeline to foster further research in this area. We release all our codes, models, data, etc. at https://github.com/ModalMinds/MM-EUREKA
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
S1-VL combines structured scientific reasoning with iterative image manipulation via code execution to reach state-of-the-art results on visual and scientific reasoning benchmarks.
RAPO uses an information-theoretic lower bound on visual gain to select high-entropy reflection anchors and optimizes a chain-masked KL surrogate, delivering gains over baselines on reasoning benchmarks across LVLM backbones.
SeePhys Pro benchmark reveals multimodal models degrade on physics reasoning as information transfers from text to images, with blind training improvements often stemming from textual cues rather than visual evidence.
CGC improves fine-grained multi-image understanding in MLLMs by constructing contrastive training instances from existing single-image annotations and adding a rule-based spatial reward, achieving SOTA on MIG-Bench and VLM2-Bench with transfer gains to other multimodal tasks.
DeepEyes uses reinforcement learning to teach vision-language models active perception and image-based thinking, yielding gains on perception, reasoning, grounding, and hallucination benchmarks.
Data curation alone raises VLM accuracy by more than 11 points on average across many benchmarks while cutting required training compute by up to 87 times.
MM-Eureka models trained via rule-based RL on the new MMK12 dataset achieve competitive or superior multimodal mathematical reasoning performance compared to models like InternVL2.5-78B while trailing slightly behind o1.
RadThinking releases a large longitudinal CT VQA dataset stratified into foundation perception questions, single-rule reasoning questions, and compositional multi-step chains grounded in clinical reporting standards for cancer screening.
PVM adds a parallel branch to LVLMs that directly supplies visual embeddings to prevent attention decay over long generated sequences, yielding accuracy gains on reasoning tasks with minimal overhead.
CharTide decouples chart-to-code data into three perspectives and uses inquiry-driven RL with atomic QA verification to let smaller VLMs surpass GPT-4o on chart-to-code tasks.
SSL-R1 reformulates visual SSL tasks into verifiable puzzles to supply rewards for RL post-training of MLLMs, yielding gains on multimodal benchmarks without external supervision.
VL-Calibration is a reinforcement learning method that separates visual and reasoning confidence in LVLMs via intrinsic visual certainty estimation to improve calibration and accuracy.
VGPO introduces visual attention compensation and dual-grained advantage re-weighting to reinforce visual focus in VLMs, yielding better activation and performance on multimodal reasoning tasks.
Saliency-R1 uses a novel saliency map technique and GRPO with human bounding-box overlap as reward to improve VLM reasoning faithfulness and interpretability.
InternVL3.5 advances open-source multimodal models with Cascade RL for +16% reasoning gains and ViR for 4x inference speedup, with the 241B model reaching SOTA among open-source MLLMs on multimodal, reasoning, and agentic tasks.
VLM-R1 applies R1-style RL using rule-based rewards on visual tasks with clear ground truth to achieve competitive performance and superior generalization over SFT in vision-language models.
A co-evolving proposer-critic RL framework improves GUI grounding accuracy by letting the model critique its own proposals rendered on screenshots.
DT2IT-MRM proposes a debiased preference construction pipeline, T2I data reformulation, and iterative training to curate multimodal preference data, achieving SOTA on VL-RewardBench, Multimodal RewardBench, and MM-RLHF-RewardBench.
DocSeeker improves long-document understanding in MLLMs via a two-stage training process that combines supervised fine-tuning from distilled data with evidence-aware group relative policy optimization and memory-efficient resolution allocation.
SignReasoner decomposes traffic signs into functional structure units and uses a two-stage VLM post-training pipeline to achieve state-of-the-art compositional reasoning on a new benchmark.
Multimodal reasoning models hallucinate at high-entropy cognitive bifurcation points due to loss of visual semantic anchoring, and the V-STAR training paradigm with HVAR rewards and FRM reflection mitigates this by reinforcing visual attention.
The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.
citing papers explorer
-
20/20 Vision Language Models: A Prescription for Better VLMs through Data Curation Alone
Data curation alone raises VLM accuracy by more than 11 points on average across many benchmarks while cutting required training compute by up to 87 times.
-
Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding
A co-evolving proposer-critic RL framework improves GUI grounding accuracy by letting the model critique its own proposals rendered on screenshots.