Test-Time Scaling for Small VLMs on Multilingual Visual MCQ
Test-time scaling (TTS) reliably improves reasoning in large language models, but whether it transfers to small open vision-language models remains unclear. We examine this on EXAMS-V, a multilingual visual multiple-choice benchmark, comparing self-consistency, describe-then-reason with PRM-guided beam search, and two post-hoc selectors across Qwen2.5-VL-7B-Instruct and Qwen3.5-4B. What matters is the conditions under which TTS runs, not the search or verification machinery. The largest factor is parseability: an early prompt format left many chains reasoning correctly yet never committing to an answer letter, which a standard answer cue and a guided repair step largely remove. A larger decoding budget removes the rest: raising the per-chain token limit from 1k to 2k recovers 3.7 pp, whereas sampling more chains (8 to 16) adds only 0.15 pp. Once chains have room to finish, elaborate methods contribute little: PRM-guided beam search trails plain self-consistency by 0.39 pp at over eight times the cost, and neither a training-free generative critic nor a trained multimodal PRM beats majority vote across both policies. The largest gain comes instead from the policy model itself (+11.4 pp). Our best configuration reaches 84.1% on the held-out ImageCLEF 2026 test split, ranking first on the Visual MCQ leaderboard.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
On Test-Time Scaling for Vision-Language Models
Test-time scaling is a paradigm where large models use additional compute at inference to achieve better performance, without changing model weights. While it has been widely studied for Large Language Models (LLMs), its…
Efficient Test-Time Scaling for Small Vision-Language Models
Small Vision-Language Models (VLMs) provide a computationally efficient alternative to larger models, at the cost of weaker generalization abilities and downstream task performance. These shortcomings could be addressed …
Computational EfficiencyTest-time AdaptationFlorenz: Scaling Laws for Systematic Generalization in Vision-Language Models
Cross-lingual transfer enables vision-language models (VLMs) to perform vision tasks in various languages with training data only in one language. Current approaches rely on large pre-trained multilingual language models…
Cross-Lingual TransferImage CaptioningLarge Language ModelMachine Translation+3Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned
Process Reward Models (PRMs) provide step-level supervision that improves the reliability of reasoning in large language models. While PRMs have been extensively studied in text-based domains, their extension to Vision L…
Multimodal ReasoningVisual GroundingLinguistic Generalizability of Test-Time Scaling in Mathematical Reasoning
Scaling pre-training compute has proven effective for achieving mulitlinguality, but does the same hold for test-time scaling? In this work, we introduce MCLM, a multilingual math benchmark featuring competition-level pr…
MathMathematical Reasoning