# GEM-Occ: From Visual Geometry Evidence to Embodied Semantic Occupancy Memory

arXiv: https://arxiv.org/abs/2607.05543 · HTML: https://mlsanity.com/paper/2607.05543/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 21 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 18 of 18)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [Reinforcement Learning via Self-Distillation](https://mlsanity.com/paper/2601.20802/) (2026)
- [Agent Learning via Early Experience](https://mlsanity.com/paper/2510.08558/) (2025)
- [Expanding the Capabilities of Reinforcement Learning via Text Feedback](https://mlsanity.com/paper/2602.02482/) (2026)
- [WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback](https://mlsanity.com/paper/2408.15549/) (2024)
- [Safer-Instruct: Aligning Language Models with Automated Preference Data](https://mlsanity.com/paper/2311.08685/) (2023)
- [Cogito, Ergo Ludo: An Agent that Learns to Play by Reasoning and Planning](https://mlsanity.com/paper/2509.25052/) (2025)

## Built on by (most cited first, 3 of 3)

- [VGOcc: Learning Visual-Geometric Gaussians for Vision-Centric 3D Driving Occupancy Prediction](https://mlsanity.com/paper/2607.18078/) (2026)
- [Visual Geometry Foundation-Aware Gaussians for Single-Frame Surround-View Driving Reconstruction](https://mlsanity.com/paper/2608.10682/) (2026)
- [PanOVOcc: Panoramic Embodied Open-Vocabulary Occupancy Mapping with Long-term Spatial Voxel Memory](https://mlsanity.com/paper/2609.31716/) (2026)

## Abstract (arXiv)

Embodied agents exploring indoor environments require reliable semantic occupancy memory that persists across observations and revisits. Building such memory is challenging because each observation provides incomplete and uncertain geometric and semantic evidence. We introduce GEM-Occ, a Gaussian Evidence Memory framework that consolidates evidence accumulated over time into persistent semantic occupancy memory. Local predictions are converted into occupied semantic Gaussians and free-space ray evidence. Confidence- and visibility-aware causal updates integrate supporting observations, suppress occupancy contradicted by observed free space, and preserve previously observed structures through occlusion. A hierarchical memory organization supports continued mapping and efficient queries across connected indoor spaces. To evaluate this capability, we introduce HIOcc, a unified benchmark for embodied semantic occupancy memory. HIOcc establishes a shared semantic label space and evaluation framework spanning local prediction, room-level online mapping, and building-level mapping, while accommodating perspective and panoramic observations. Experiments on HIOcc demonstrate that GEM-Occ outperforms existing methods, enabling accurate semantic occupancy prediction and consistent online mapping across spatial scales with efficient memory usage and fast occupancy queries.