Candidate-Expanding Routing with Permutation-Stabilized Experts for Mixed-Format Medical VQA

• URL: http://arxiv.org/abs/2609.00959v1
• Date: Tue, 01 Sep 2026 09:18:19 GMT
• Title: Candidate-Expanding Routing with Permutation-Stabilized Experts for Mixed-Format Medical VQA
• Abstract summary: Mixed-format medical visual question answering (VQA) requires stable option selection and machine-readable free-text output.<n>We address both challenges with an answer-text memory, a permutation--stabilized expert, and a sparse candidate- expanding router.
• Score: 2.313903538324245
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Mixed-format medical visual question answering (VQA) requires stable option selection and machine-readable free-text output. The two formats fail differently: multiple-choice predictions can change with option symbols or positions, while clinically plausible open answers can fail automated evaluation when serialization is malformed. We address both challenges with an answer-text memory, a permutation-stabilized vision--language expert, and a sparse candidate- expanding router. The cyclic schedule follows prior work; our contribution is to make expert top-2 a routable candidate alongside memory and expert top-1. On a 1,403-case retrospective internal analysis, this expansion improves a matched binary router from 88.95% to 91.73% (+2.78 percentage points; 95% CI 1.57--3.99), with 56 rescued errors and 17 regressions. Oracle coverage rises from 90.31% to 96.15%, and the final submitted configuration reaches 92.23% on the same retrospective split. For open questions, strict generation and deterministic guards produce 475/475 schema- valid participant-facing outputs without repair, retry, or hard-gate failure. Visual ablations reveal substantial textual dependence. Candidate expansion supplies the principal controlled routing gain; open-path evidence establishes output-contract validity rather than clinical correctness in medical use or deployment.

Related papers

• Option-Aware Retrieval and Task-Specific VLM Adaptation for Medical VQA [0.0611737116137921]
  We describe our submission to the MedReason 2026 challenge, covering multiple-choice (MCQ) and open-ended (OE) medical visual question answering (VQA)<n>Our first finding is that MCQ retrieval must compare answer emphsemantics rather than answer labels.<n>Our second finding attributes the submitted system's accuracy: holding the task-specific MCQ Low-Rank Adaptation (LoRA) adapter fixed and varying the number (k) of in-prompt retrieved examples changes accuracy by at most one case.
  arXiv  Detail & Related papers  (2026-09-14T13:17:42Z)
• MedQA-MM: Shortcuts Behind Medical Visual Reasoning [45.333881843709804]
  A benchmark score credits final answers, but not the route by which an item can be answered.<n>In medical multimodal multiple-choice questions (MCQs), this distinction matters because a correct answer can be supported by the intended image finding.<n>Here, a route is an observable input path that can support answer selection, not a claim about the model's hidden cognition.
  arXiv  Detail & Related papers  (2026-09-03T01:40:19Z)
• Case2Flow: Bridging Patient Cases and Guideline Flowcharts through Multimodal Retrieval [65.99409194536337]
  Case2Flow is a task designed to retrieve the most relevant guideline flowchart for a given patient case.<n> FlowAtlas is a curated corpus of 202 flowcharts extracted from 2,080 medical guidelines.<n> CRISP is a training-free scoring method that sharpens late-interaction retrieval by suppressing uninformative patches.
  arXiv  Detail & Related papers  (2026-08-26T21:27:22Z)
• Disagree to Explore, Agree to Commit: Routing-Guided Test-Time Scaling for Software Agents [60.650808962786364]
  We study whether native MoE router traces can guide steering and selection without an external judge or selection-time test execution.<n>Our analysis shows that routing provides a robust behavioral role signal; token-granular readouts and decision-matched comparison sets turn it into effective control.<n>We evaluate on SWE-bench Verified using open-weight sparse MoE agents across scales and reasoning-effort settings.
  arXiv  Detail & Related papers  (2026-08-23T03:07:03Z)
• Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary [0.0]
  Can a language model read the quality of its ongoing computation?<n>Can an external intervention turn that readout into better outcomes?<n>We test both questions in a frozen 2.6B looped transformer, Ouro-RLTT.
  arXiv  Detail & Related papers  (2026-07-20T22:40:36Z)
• Know Before You Fetch: Calibrated Retrieval-Budget Allocation for Retrieval-Augmented Generation [10.60293484295824]
  We formulate adaptive RAG as calibrated retrieval-budget allocation.<n>We calibrate sequence log-probability and prefix-logit uncertainty signals into probabilities of correctness.<n>For sequence log-probability, ECE drops from 0.275 to 0.062 on TriviaQA, 0.643 to 0.009 on NQ, and 0.711 to 0.031 on MS MARCO.
  arXiv  Detail & Related papers  (2026-06-29T08:36:33Z)
• Efficient Visual Pointing for Embodied AI:Agent-Driven Data Synthesis, Cross-Block Attention, and Iterative Correction [55.11480729304395]
  We describe our PointArena 2026 solution, which achieves 77.2% overall accuracy and ranks second on the benchmark.<n>The ap proach targets three failure modes. First, agent-driven syn thesis builds large semantic and anchor-relative candidate pools.<n>Second, a determinis tic steerable-data pipeline creates a verified 10,000-sample main set, plus reserve samples, using masks, templates, and path verification.
  arXiv  Detail & Related papers  (2026-06-29T06:39:03Z)
• Automated Proving of Shannon-Type Entropy Inequalities via Fine-Tuned Language Models and Guided Tree Search [50.16356451328644]
  Proving Shannon-type entropy inequalities is a fundamental task in information theory.<n>We investigate whether small-scale large language models, fine-tuned on atomic proof steps, can automate this process.<n>We show that GPT-5.5 solves 1.7% samples under zero-shot prompting while Psitip solves 33.3% samples.
  arXiv  Detail & Related papers  (2026-06-04T05:43:12Z)
• Agri-CPJ: A Training-Free Explainable Framework for Agricultural Pest Diagnosis Using Caption-Prompt-Judge and LLM-as-a-Judge [40.23111543895404]
  This paper describes Agri-CPJ (Caption-Prompt-Judge), a training-free few-shot framework in which a large vision-language model first generates a structured morphological caption.<n>Two candidate responses are then generated from complementary viewpoints, and an LLM judge selects the stronger one based on domain-specific criteria.<n>On CDDMBench, pairing GPT-5-Nano with GPT-5-mini-generated captions yields textbf+22.7 pp in disease classification and textbf+19.5 points in QA score over no-caption baselines.
  arXiv  Detail & Related papers  (2026-04-26T13:33:45Z)
• Improving Selective Visual Question Answering by Learning from Your Peers [74.20167944693424]
  Visual Question Answering (VQA) models can have difficulties abstaining from answering when they are wrong. We propose Learning from Your Peers (LYP) approach for training multimodal selection functions for making abstention decisions. Our approach uses predictions from models trained on distinct subsets of the training data as targets for optimizing a Selective VQA model.
  arXiv  Detail & Related papers  (2023-06-14T21:22:01Z)
• Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly [100.60560477391732]
  We promote a problem formulation for reliable visual question answering (VQA) We analyze both their coverage, the portion of questions answered, and risk, the error on that portion. We find that although the best performing models achieve over 71% accuracy on the VQA v2 dataset, introducing the option to abstain limits them to answering less than 8% of the questions to achieve a low risk of error (i.e., 1%) This motivates us to utilize a multimodal selection function to directly estimate the correctness of the predicted answers, which we show can triple the coverage from, for example, 5.0% to 16.7% at
  arXiv  Detail & Related papers  (2022-04-28T16:51:27Z)

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.