arXiv Computation and Language November 4, 2026 By T N Rickesh, Pranav Vinodh, Sowmya Kamath S

Fewer Tokens, More Answers: Verifiable-Reward Tuning of an Ornith-Style VLM for Multi-View Driving QA

Read the original on arXiv Computation and Language →

The paper reports on a verifiable‑reward tuning approach applied to an Ornith‑style vision‑language model for multi‑view driving question answering. Using a 256‑token limit, the GRPO method raises answer extraction from 78.25 % to 90.25 % and accuracy from 55.50 % to 63.75 %. On a larger 2,511‑question set, the tuned pipeline cuts average token usage from 108.6 to 47.1, though the accuracy improvement is not statistically significant.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Jun 2

ThinkSwitch: Context Distillation with LoRA and Weight Interpolation for Specific-Purpose Reasoning Tasks

arXiv:2606. 01080v1 Announce Type: cross Abstract: Large language models often improve on difficult tasks by spending inference-time compute on a reasoning trace before producing the final answer.

By Dhruv Saini, Rohan Pandey

llms fine-tuning efficiency

arXiv AI

Jul 17

Just Keep Prompting: Evaluating Repetitive Socratic Prompting in VLMs

arXiv:2607. 14099v1 Announce Type: cross Abstract: Deploying Vision-Language Models (VLMs) in real-world settings requires not only strong visual reasoning but also stability under sustained conversational pressure.

By Shayda Moezzi, Bishoy Galoaa, Lorena Genua, Taskin Padir, Sarah Ostadabbas

llms nlp multimodal benchmarks safety

arXiv AI

Oct 7

When to Rethink: Learning Multi-Perspective Self-Verification for Vision-Language Models

The paper introduces MOTIVE, a multi-view self-verification framework for vision-language models that evaluates candidate answers from complementary perspectives and learns a reliability score aligned with correctness. By using this score to decide whether to accept an answer or trigger history-guided rethinking, MOTIVE improves reliability and efficiency compared to existing self-verification and self-correction methods. Extensive experiments on diverse multimodal benchmarks and VLM backbones show consistent performance gains and reduced unnecessary reasoning turns.

By Ziquan Zhu, Hanruo Zhu, Si-Yuan Lu, Morris Yu-Chao Huang, Yicheng Lin, Wei Han, Tianlong Chen, Mingyuan Wu, Hanchao Yu, Gaojie Jin, Lu Liu, Bo Sun, Tianjin Huang

llms multimodal benchmarks

arXiv AI

Jun 11

ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward

arXiv:2606. 11209v1 Announce Type: cross Abstract: Visual question answering increasingly requires multi-step reasoning.

By Jingpei Wu, Xiao Han, Weixiang Shen, Boer Zhang, Zifeng Ding, Volker Tresp

llms nlp reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Jun 10

V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions

arXiv:2512. 11995v2 Announce Type: replace-cross Abstract: While many vision-language models (VLMs) are developed to answer well-defined, straightforward questions with highly specified targets, as in most benchmarks, they often struggle in practice with complex open-ended tasks, which usually require multiple rounds of exploration and reasoning in the visual space.

By Chenrui Fan, Yijun Liang, Shweta Bhardwaj, Kwesi Cobbina, Ming Li, Tianyi Zhou

llms multimodal benchmarks

arXiv AI

Jul 20

Ask Twice, Look Twice: Prompt Echoing Resolves the Question-First Paradox in Vision-Language Models

arXiv:2607. 15565v1 Announce Type: cross Abstract: Where should the question go in a vision-language model (VLM) prompt: before the image or after it?

By Rakshanda Hassan Abhinandan, John Galeotti, Deva Ramanan, Gautam Rajendrakumar Gare

llms nlp fine-tuning multimodal benchmarks

One email a morning, machine-written

Related stories

ThinkSwitch: Context Distillation with LoRA and Weight Interpolation for Specific-Purpose Reasoning Tasks

Just Keep Prompting: Evaluating Repetitive Socratic Prompting in VLMs

When to Rethink: Learning Multi-Perspective Self-Verification for Vision-Language Models

ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward

V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions

Ask Twice, Look Twice: Prompt Echoing Resolves the Question-First Paradox in Vision-Language Models