STELAR-VISION: Self-Topology-Aware Efficient Learning for Aligned Reasoning in Vision

• URL: http://arxiv.org/abs/2508.08688v1
• Date: Tue, 12 Aug 2025 07:27:50 GMT
• Title: STELAR-VISION: Self-Topology-Aware Efficient Learning for Aligned Reasoning in Vision
• Authors: Chen Li, Han Zhang, Zhantao Yang, Fangyi Chen, Zihan Wang, Anudeepsekhar Bolimera, Marios Savvides,
• Abstract summary: We introduce STELAR-Vision, a training framework for topology-aware reasoning.<n>At its core is TopoAug, a synthetic data pipeline that enriches training with diverse topological structures.<n>On MATH-V and VLM-S2H, STELAR-Vision improves accuracy by 9.7% over its base model and surpasses the larger Qwen2VL-72B-Instruct by 7.3%.
• Score: 24.162895928364062
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-language models (VLMs) have made significant strides in reasoning, yet they often struggle with complex multimodal tasks and tend to generate overly verbose outputs. A key limitation is their reliance on chain-of-thought (CoT) reasoning, despite many tasks benefiting from alternative topologies like trees or graphs. To address this, we introduce STELAR-Vision, a training framework for topology-aware reasoning. At its core is TopoAug, a synthetic data pipeline that enriches training with diverse topological structures. Using supervised fine-tuning and reinforcement learning, we post-train Qwen2VL models with both accuracy and efficiency in mind. Additionally, we propose Frugal Learning, which reduces output length with minimal accuracy loss. On MATH-V and VLM-S2H, STELAR-Vision improves accuracy by 9.7% over its base model and surpasses the larger Qwen2VL-72B-Instruct by 7.3%. On five out-of-distribution benchmarks, it outperforms Phi-4-Multimodal-Instruct by up to 28.4% and LLaMA-3.2-11B-Vision-Instruct by up to 13.2%, demonstrating strong generalization. Compared to Chain-Only training, our approach achieves 4.3% higher overall accuracy on in-distribution datasets and consistently outperforms across all OOD benchmarks. We have released datasets, and code will be available.

Related papers

• Teaching LLM to Reason: Reinforcement Learning from Algorithmic Problems without Code [76.80306464249217]
  We propose TeaR, which aims at teaching LLMs to reason better.<n>TeaR leverages careful data curation and reinforcement learning to guide models in discovering optimal reasoning paths through code-related tasks.<n>We conduct extensive experiments using two base models and three long-CoT distillation models, with model sizes ranging from 1.5 billion to 32 billion parameters, and across 17 benchmarks spanning Math, Knowledge, Code, and Logical Reasoning.
  arXiv  Detail & Related papers  (2025-07-10T07:34:05Z)
• One RL to See Them All: Visual Triple Unified Reinforcement Learning [92.90120580989839]
  We propose V-Triune, a Visual Triple Unified Reinforcement Learning system that enables visual reasoning and perception tasks within a single training pipeline.<n>V-Triune comprises triple complementary components: Sample-Level Datashelf (to unify diverse task inputs), Verifier-Level Reward (to deliver custom rewards via specialized verifiers).<n>We introduce a novel Dynamic IoU reward, which provides adaptive, progressive, and definite feedback for perception tasks handled by V-Triune.
  arXiv  Detail & Related papers  (2025-05-23T17:41:14Z)
• ViLBench: A Suite for Vision-Language Process Reward Modeling [25.565912785217822]
  This paper first benchmarks current vision large language models (VLLMs) as two types of reward models.<n>We introduce ViLBench, a vision-language benchmark designed to require intensive process reward signals.<n>We preliminarily showcase a promising pathway towards bridging the gap between general VLLMs and reward models.
  arXiv  Detail & Related papers  (2025-03-26T06:38:31Z)
• LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning [76.82159851648711]
  We propose a framework that dynamically improves the embedding model's representation learning for negative pairs.<n>LLaVE establishes stronger baselines that achieve state-of-the-art (SOTA) performance.<n>LLaVE can generalize to text-video retrieval tasks in a zero-shot manner and achieve strong performance.
  arXiv  Detail & Related papers  (2025-03-04T10:21:57Z)
• LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs [103.0226977561914]
  We propose a comprehensive framework for advancing step-by-step visual reasoning in large language models.<n>We introduce a visual reasoning benchmark specifically designed to evaluate multi-step reasoning tasks.<n>Second, we propose a novel metric that assesses visual reasoning quality at the granularity of individual steps.<n>Third, we present a new multimodal visual reasoning model, named LlamaV-o1, trained using a multi-step curriculum learning approach.
  arXiv  Detail & Related papers  (2025-01-10T18:59:51Z)
• VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models [66.56298924208319]
  Vision-language generative reward models (VL-GenRMs) play a crucial role in aligning and evaluating multimodal AI systems.<n>Current assessment methods primarily rely on AI-annotated preference labels from traditional tasks.<n>We introduce VL-RewardBench, a comprehensive benchmark spanning general multimodal queries, visual hallucination detection, and complex reasoning tasks.
  arXiv  Detail & Related papers  (2024-11-26T14:08:34Z)
• Improve Vision Language Model Chain-of-thought Reasoning [86.83335752119741]
  Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. We show that training VLM on short answers does not generalize well to reasoning tasks that require more detailed responses.
  arXiv  Detail & Related papers  (2024-10-21T17:00:06Z)
• Advancing LLM Reasoning Generalists with Preference Trees [119.57169648859707]
  We introduce Eurus, a suite of large language models (LLMs) optimized for reasoning. Eurus models achieve state-of-the-art results among open-source models on a diverse set of benchmarks.
  arXiv  Detail & Related papers  (2024-04-02T16:25:30Z)
• EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning [19.354515754130592]
  We introduce a distilling then pruning framework to compress large vision-language models into smaller, faster, and more accurate ones. We apply our framework to train EfficientVLM, a fast and accurate vision-language model consisting of 6 vision layers, 3 text layers, and 3 cross-modal fusion layers. EfficientVLM retains 98.4% performance of the teacher model and accelerates its inference speed by 2.2x.
  arXiv  Detail & Related papers  (2022-10-14T13:26:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.