paper-with-me

Papers

FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies

2026-05-26 · Xintong Hu, Xuhong Huang, Jinyu Zhang, Yutong Yao, Yuchong Sun, Qiuyue Wang, Mingsheng Li, Sicheng Xie, Yitao Liu, Junhao Chen, Yixuan Chen, Yingming Zheng, Shuai Bai, Tao Yu arxiv

Vision-Language-Action (VLA) models are increasingly expected to not only complete robot tasks, but also follow human instructions about how those tasks should be executed. However, existing robot datasets usually pair trajectories with coarse goal-level language, leaving execution-critical details such as active arm, approach direction, and contact region unspecified. This limits steerable policy learning and robotic video understanding. We introduce FineVLA, an open framework for action-aligned fine-grained VLA supervision. The framework includes: (1) a data construction tool that unifies 972,247 trajectories across 85K tasks from 10 open-source robot datasets and builds FineVLA-Data, a human-verified dataset of 47,159 fine-grained trajectories; (2) a held-out benchmark with 500 videos, 11,631 atomic facts, and 1,030 VQA questions; (3) a robotics-specialized VLM annotator for scalable fine-grained annotation; and (4) a steerable VLA policy trained with controlled mixtures of fine-grained and raw goal-level instructions. Our experiments yield three findings. First, fine-grained supervision does not sacrifice goal-level success: FG-only improves over Raw-only by +1.4 to +8.1 success-rate points across settings. Second, fine-grained and raw instructions are complementary, following a consistent inverted-U trend peaking at FG:Raw = 1:2 to 1:1. The best mixed setting reaches 86.8%/82.5% in RoboTwin simulation and 62.7/100 in real-world dual-arm manipulation (vs. 49.9 Raw-only). Third, fine-grained supervision improves steerable control: the largest real-world gains appear on pose (+23), color (+18), and approach direction (+18)--factors where goal-level instructions provide no guidance. Overall, fine-grained language should augment goal-level instructions: specifying how to execute alongside what to achieve. Project page: https://finevla.xlang.ai/

📄 PDF Abstract BibTeX arXiv:2605.27284

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuning

2026-04-20 · Tuan Van Vo, Tan Q. Nguyen, Khang Nguyen, Nhat Xuan Tran 외 arxiv

Vision-Language-Action (VLA) models have gained much attention from the research community thanks to their strength in translating multimodal observations with linguistic instructions into desired robotic actions. Despit…

Multimodal Reasoning

Steerable Pluralism: Pluralistic Alignment via Few-Shot Comparative Regression

2025-08-11 · Jadie Adams, Brian Hu, Emily Veenhuis, David Joy 외 arxiv

Large language models (LLMs) are currently aligned using techniques such as reinforcement learning from human feedback (RLHF). However, these methods use scalar rewards that can only reflect user preferences on average. …

Reinforcement Learning

SUMFORU: An LLM-Based Review Summarization Framework for Personalized Purchase Decision Support

2025-12-12 · Yuming Feng, Xinrui Jiang arxiv

Online product reviews contain rich but noisy signals that overwhelm users and hinder effective decision-making. Existing LLM-based summarizers remain generic and fail to account for individual preferences, limiting thei…

Knowledge DistillationReinforcement Learning

Generating Vision-Language Navigation Instructions Incorporated Fine-Grained Alignment Annotations

2025-06-10 · Yibo Cui, Liang Xie, Yu Zhao, Jiawei Sun 외

Vision-Language Navigation (VLN) enables intelligent agents to navigate environments by integrating visual perception and natural language instructions, yet faces significant challenges due to the scarcity of fine-graine…

cross-modal alignmentNavigateVision-Language Navigation

FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets

2023-07-20 · Seonghyeon Ye, Doyoung Kim, Sungdong Kim, Hyeonbin Hwang 외

Evaluation of Large Language Models (LLMs) is challenging because instruction-following necessitates alignment with human values and the required set of skills varies depending on the instruction. However, previous studi…

Instruction FollowingLanguage Model EvaluationLanguage ModelingLanguage Modelling