Phi-4-reasoning-vision-15B Technical Report

• URL: http://arxiv.org/abs/2603.03975v1
• Date: Wed, 04 Mar 2026 12:16:53 GMT
• Title: Phi-4-reasoning-vision-15B Technical Report
• Authors: Jyoti Aneja, Michael Harrison, Neel Joshi, Tyler LaBonte, John Langford, Eduardo Salinas,
• Abstract summary: We present Phi-4-reasoning-vision-15B, a compact open-weight multimodal reasoning model.<n>We share the motivations, design choices, experiments, and learnings that informed its development.
• Score: 9.716062019697967
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Phi-4-reasoning-vision-15B, a compact open-weight multimodal reasoning model, and share the motivations, design choices, experiments, and learnings that informed its development. Our goal is to contribute practical insight to the research community on building smaller, efficient multimodal reasoning models and to share the result of these learnings as an open-weight model that is good at common vision and language tasks and excels at scientific and mathematical reasoning and understanding user interfaces. Our contributions include demonstrating that careful architecture choices and rigorous data curation enable smaller, open-weight multimodal models to achieve competitive performance with significantly less training and inference-time compute and tokens. The most substantial improvements come from systematic filtering, error correction, and synthetic augmentation -- reinforcing that data quality remains the primary lever for model performance. Systematic ablations show that high-resolution, dynamic-resolution encoders yield consistent improvements, as accurate perception is a prerequisite for high-quality reasoning. Finally, a hybrid mix of reasoning and non-reasoning data with explicit mode tokens allows a single model to deliver fast direct answers for simpler tasks and chain-of-thought reasoning for complex problems.

Related papers

• Information Capacity: Evaluating the Efficiency of Large Language Models via Text Compression [53.39128997308138]
  We introduce information capacity, a measure of model efficiency based on text compression performance.<n> Empirical evaluations on mainstream open-source models show that models of varying sizes within a series exhibit consistent information capacity.<n>A distinctive feature of information capacity is that it incorporates tokenizer efficiency, which affects both input and output token counts.
  arXiv  Detail & Related papers  (2025-11-11T10:07:32Z)
• Debate, Reflect, and Distill: Multi-Agent Feedback with Tree-Structured Preference Optimization for Efficient Language Model Enhancement [43.532921045069365]
  Large Language Models (LLMs) continue to set new standards in knowledge-intensive and complex reasoning tasks.<n>Current techniques, such as static knowledge distillation, resource-intensive reinforcement learning from human feedback, or limited self-reflection to yield substantial and lasting performance gains.<n>We present a novel Reflect and Debate (D&R) framework that orchestrates multi-turn debates between smaller models and stronger teacher models, eliciting actionable feedback.
  arXiv  Detail & Related papers  (2025-06-04T03:52:20Z)
• MindGYM: What Matters in Question Synthesis for Thinking-Centric Fine-Tuning? [51.85759493254735]
  MindGYM is a structured and scalable framework for question synthesis.<n>It infuses high-level reasoning objectives to shape the model's synthesis behavior.<n>It composes more complex multi-hop questions based on QA seeds for deeper reasoning.
  arXiv  Detail & Related papers  (2025-03-12T16:03:03Z)
• SDRT: Enhance Vision-Language Models by Self-Distillation with Diverse Reasoning Traces [11.462550020102935]
  We propose a novel self-distillation framework for Vision-Language Models.<n>We employ a prompt library tailored to visual reasoning tasks to generate diverse in-context questions.<n>We then utilize a two-step reasoning procedure to derive reasoning-guided responses.<n>These responses are then used for self-distillation, enabling the model to internalize the reasoning process.
  arXiv  Detail & Related papers  (2025-03-03T17:24:42Z)
• Causality can systematically address the monsters under the bench(marks) [64.36592889550431]
  Benchmarks are plagued by various biases, artifacts, or leakage.<n>Models may behave unreliably due to poorly explored failure modes.<n> causality offers an ideal framework to systematically address these challenges.
  arXiv  Detail & Related papers  (2025-02-07T17:01:37Z)
• Can foundation models actively gather information in interactive environments to test hypotheses? [43.42688356541211]
  Foundation models excel at single-turn reasoning but struggle with multi-turn exploration in dynamic environments.<n>We evaluated these models on their ability to learn from experience, adapt, and gather information.
  arXiv  Detail & Related papers  (2024-12-09T12:27:21Z)
• Patience Is The Key to Large Language Model Reasoning [0.0]
  We propose a simple method by encouraging models to adopt a more patient reasoning style.<n>We generate detailed reasoning processes as positive examples and simple answers as negative examples, thereby training the model to favor thoroughness in its responses.<n>Our results demonstrate a performance increase of up to 2.1% on GSM8k with training just on a lightweight dataset.
  arXiv  Detail & Related papers  (2024-11-20T07:20:48Z)
• Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training [49.3242278912771]
  Multimodal reasoning is a challenging task that requires models to reason across multiple modalities to answer questions. Existing approaches have made progress by incorporating language and visual modalities into a two-stage reasoning framework. We propose MC-CoT, a self-consistency training strategy that generates multiple rationales and answers, subsequently selecting the most accurate through a voting process.
  arXiv  Detail & Related papers  (2023-11-23T17:09:48Z)
• Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering [63.87200781247364]
  Correlation Information Bottleneck (CIB) seeks a tradeoff between compression and redundancy in representations. We derive a tight theoretical upper bound for the mutual information between multimodal inputs and representations.
  arXiv  Detail & Related papers  (2022-09-14T22:04:10Z)
• Rethinking Self-Supervision Objectives for Generalizable Coherence Modeling [8.329870357145927]
  Coherence evaluation of machine generated text is one of the principal applications of coherence models that needs to be investigated. We explore training data and self-supervision objectives that result in a model that generalizes well across tasks. We show empirically that increasing the density of negative samples improves the basic model, and using a global negative queue further improves and stabilizes the model while training with hard negative samples.
  arXiv  Detail & Related papers  (2021-10-14T07:44:14Z)
• Enhancing Dialogue Generation via Multi-Level Contrastive Learning [57.005432249952406]
  We propose a multi-level contrastive learning paradigm to model the fine-grained quality of the responses with respect to the query. A Rank-aware (RC) network is designed to construct the multi-level contrastive optimization objectives. We build a Knowledge Inference (KI) component to capture the keyword knowledge from the reference during training and exploit such information to encourage the generation of informative words.
  arXiv  Detail & Related papers  (2020-09-19T02:41:04Z)

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.