paper-with-me

홈 › Papers

StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning

2026-07-01 · Yuan Qing, Chengzhi Mao, Boqing Gong arxiv

Large Vision-Language Models (LVLMs) rely extensively on Visual Instruction Tuning (VIT) to elicit their multimodal reasoning capabilities. However, we find a discrepancy: VIT often packs multiple language tasks about the same image for conversational, multi-turn training, whereas existing benchmarks evaluate LVLMs in isolated, single-turn scenarios. The models can suffer from visual attention decay and contextual overfitting during multi-turn training, making it hard for them to realize their full potential in the mismatched test phase. To close the gap, we propose learning with Stochastic Turn Depth (StochasT), which stochastically groups language tasks for the same image into clusters of varying sizes (turn depth) while preserving their organic order. Hence, while StochasT draws on Dropout and stochastic depth for ResNets, it does not actually drop anything to maximize the utility of the training data. Furthermore, we introduce a challenging, benchmark-agnostic evaluation mechanism based on the Balanced Latin Square to measure LVLMs' robustness under varying contextual dependencies. Extensive experiments demonstrate that StochasT effectively grants LVLMs strong, harmonized capabilities for both single-turn and multi-turn use cases.

📄 PDF Abstract BibTeX arXiv:2607.00465

Code (0)

등록된 구현이 없습니다.

Tasks

Multimodal Reasoning

Similar Papers 제목 키워드 기반

Kyle's Model with Stochastic Liquidity

2022-04-23 · Ibrahim Ekren, Brad Mostowski, Gordan Žitković

We construct an equilibrium for the continuous time Kyle's model with stochastic liquidity, a general distribution of the fundamental price, and correlated stock and volatility dynamics. For distributions with positive s…

model

ContextualLVLM-Agent: A Holistic Framework for Multi-Turn Visually-Grounded Dialogue and Complex Instruction Following

2025-08-21 · Seungmin Han, Haeun Kwon, Ji-jun Park, Taeyang Yoon arxiv

Despite significant advancements in Large Language Models (LLMs) and Large Vision-Language Models (LVLMs), current models still face substantial challenges in handling complex, multi-turn, and visually-grounded tasks tha…

Instruction Following

Perfecting Depth: Uncertainty-Aware Enhancement of Metric Depth

2025-06-05 · Jinyoung Jun, Lei Chu, Jiahao Li, Yan Lu 외

We propose a novel two-stage framework for sensor depth enhancement, called Perfecting Depth. This framework leverages the stochastic nature of diffusion models to automatically detect unreliable depth regions while pres…

Autonomous Driving

You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments

2022-05-31 · Keiran Paster, Sheila Mcilraith, Jimmy Ba

Recently, methods such as Decision Transformer that reduce reinforcement learning to a prediction task and solve it via supervised learning (RvS) have become popular due to their simplicity, robustness to hyperparameters…

Offline RLPlaying the Game of 2048

Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues

2024-04-17 · Jiao Ou, Jiayu Wu, Che Liu, Fuzheng Zhang 외

Aligning large language models (LLMs) with human expectations requires high-quality instructional dialogues, which usually require instructions that are diverse and in-depth. Existing methods leverage two LLMs to interac…