VisInteract: Interactive Text-to-Visualization for Imperfect Queries, NeurIPS 2026 Spotlight
Researchers from Hong Kong Polytechnic University and ByteDance propose VisInteract, a new paradigm for dynamic interactive text-to-visualization that handles imperfect user queries. They introduce VisInteract-Bench, a benchmark acknowledging ambiguous, incomplete, or erroneous inputs, and Vis-MCTS, a Monte Carlo tree search-based method that branches and backtracks between data retrieval, chart generation, and clarification. The work was accepted as a Spotlight paper at NeurIPS 2026 (292 out of 30,709 submissions).
Coverage timeline
机器之心机器之心
本文作者分别来自香港理工大学以及字节跳动。共同第一作者许文鑫、卢锦伟来自香港理工大学。许文鑫是香港理工大学博士生,指导老师为张晨教授与魏骁勇教授。 数据要让人看懂,通常得先从数据库里查出来,再画成图。文本到可视化(Text-to-Vis)做的就是这件事:用户说出想看什么,系统去库里查询,再用图表把需要的数据展示出来。 你可能会觉得,现在的大模型已经非常强,这不过是小菜一碟。模型强是强,可需求得说清楚。通常,大多数用户没法一次把自己的需求表达完整。比如「把 2025 年 top-5 产品的月度营收画出来,按地区拆开」,听着已经很具体,可 top-5 按销售额还是按销量、退款算不算、数据库里到底有没有 2025 年的数据,这些都还没定。只出一次图,系统不会问,只会自己默默选定一种解释。 所以,要得到与用户真实意图相匹配的数据可视化,往往需要模型与用户进行多轮交互:缺的补上,含糊的问清,说错的改掉,一步步落到真正想看的那张图。这也是这项工作的研究背景。从适用性上看,这个场景要解决的是真实业务里的查数与出图。文生图在大模型里已经研究得很多,而企业用户有大量数据存在数据库里,要通过交互尽快把该看的内容锁定,这个意义会更大。 一旦把「需求往往说不完全」当成前提,现有研究就会同时碰到两个挑战。第一,现有基准数据集大多假设查询已经说清,而且很难评估开放的可视化输出,也就是同一句话,往往有不止一种合理画法。第二,现有方法还没法通过动态交互,主动把用户的真实意图问回来。查询不完美时,Text-to-Vis 更接近一种交互式的意图找回,而不只是一次出图。 针对这两个挑战,研究团队提出了 VisInteract 。这是一种面向不完美查询的动态交互式 Text-to-Vis 新范式。为了实现这种范式,团队发布了评测基准 VisInteract-Bench ,承认输入可以含糊、信息缺失甚至说错;同时提出基于蒙特卡洛树搜索的方法 Vis-MCTS ,让系统在查数、画图和追问之间分叉与回退,把真实意图问回来。 目前,该工作已被 NeurIPS 2026 接收为 Spotlight(292/30709 投稿)。 论文标题: VisInteract: Towards Dynamic Interactive Text-to-Visualization under Imperfect Queries 论文

Related stories
FAME: Flow-Driven Multi-Anchor Exploration for Active 3D Mapping Accepted as NeurIPS 2026 Spotlight
Researchers from Tianjin University and Hefei University of Technology proposed FAME, a flow-driven multi-anchor exploration method for open-environment active 3D mapping. Unlike traditional methods that predict a single exploration goal, FAME uses Conditional Flow Matching to generate multiple possible goals, combined with path planning, exploration mode clustering, and hierarchical selection. The paper was accepted as a Spotlight at NeurIPS 2026, with 292 out of 7,900 accepted papers selected for this distinction.
1 reports · 1 sources

NV-CoT: Multimodal LLMs Predict Continuous Coordinates for Visual Chain-of-Thought, NeurIPS 2026 Oral
Researchers from NTU, USTC, NUS, and Microsoft propose NV-CoT (Numerical Visual Chain-of-Thought), a method that lets multimodal LLMs directly predict continuous numerical coordinates for region selection instead of generating bounding boxes as text tokens. The work, accepted as a NeurIPS 2026 Oral (top 0.4%), supports supervised fine-tuning and reinforcement learning, addressing mismatches between token-level training and spatial error.
1 reports · 1 sources

Pitt Researchers Uncover 3D Scene Topology in VLM Latent Spaces
University of Pittsburgh researchers analyzed the latent representations of vision-language models (VLMs) and found that intermediate layers encode spatial structures such as rings, grids, and random layouts, corresponding to 3D scene topology. Their paper, accepted as a NeurIPS 2026 spotlight, introduces methods to separate spatial signals from appearance attributes in high-dimensional activations.
1 reports · 1 sources

Xiaohongshu and Fudan propose DR-Rubric for open-ended RL at NeurIPS 2026
Researchers from Xiaohongshu and Fudan University presented DR-Rubric (Deep Research as Rubric), a method accepted at NeurIPS 2026 that generates fine-grained scoring rubrics for open-ended reinforcement learning by first conducting deep research on the task. The approach, which has been used in Xiaohongshu's business, achieves competitive results on six benchmarks using only 1000 RL data per round. The paper and code are publicly available.
1 reports · 1 sources

News updates every hour. Subscribe in your RSS reader to get new stories automatically.
Subscribe