VisInteract: NeurIPS Spotlight reframes text-to-visualization as multi-turn intent retrieval
jiqizhixin · x · 2026-10-14
- Hong Kong Polytechnic University researchers (co-first authors Wenxin Xu, Jinwei Lu) present VisInteract, a NeurIPS 2026 Spotlight paper that reframes text-to-visualization as interactive intent retrieval rather than one-shot chart generation.
- Existing systems silently pick one interpretation of ambiguous queries (top-5 by sales or units? refunds counted? does 2025 data even exist?) and output a plausible-looking but wrong chart.
- VisInteract engages in dynamic multi-turn interaction: filling gaps, clarifying ambiguity, correcting errors, and proactively asking users, converging step by step on the chart they actually want.
More from Research
- 654 Real-World Failures: First Large-Scale Study Maps How RAG Configuration Issues Break Systems — _reachsumit · 2026-10-14
- ReMaRk Cuts GRPO Responder Noise in LLM Recommenders, Reaching Parity With 25–53% of Training Steps — _reachsumit · 2026-10-14
- Disney+ details DRanker transformer ranker, driving 1% engagement and 0.5% DAU lift — _reachsumit · 2026-10-14
- Math Papers Pile On OpenAI's Quasi-Riemann Proof, One Declares 'No AI Used' — LucaAmb · 2026-10-14
- Netflix compares autoregressive beam search vs multi-token prediction for LLM recommender Semantic IDs — _reachsumit · 2026-10-14
- Alibaba proposes UniSGR-V2, anticipating continuous target-side features in generative recommendation — _reachsumit · 2026-10-14