GWM (Gaussian World Models)
https://gaussian-world-model.github.io/
Encodes scene into 3D Gaussian Splat representations via 3D VAE; latent Diffusion Transformer predicts future Gaussian Splat states conditioned on robot actions. 3D scene representation persists across time steps as structural scene memory rather than flat features.
Stale · Verified 2026-10-28 · fresh as of 2026-10-28 · 24 cited facts, 0 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- 3D Gaussian Splatting latent world model vendor fix
- Tier
- T3
- Created
- 2025-08-25 (GWM: Towards Scalable Gaussian World Models for Robotic Manipulation; arxiv 2508.17600 submitted Aug 25, 2025; v2 Sep 17, 2025) paper fix
- Latest release
- not applicable — not OSS fix
- Pricing
- searched not found fix
- Funding
- searched not found fix
- Freshness
- 2026-10-28 fix
- Layer
- agent-infra repo fix
- Licensing
- open-source repo fix
Memory taxonomy
- storage
- parametric
- retrieval
- parametric-recall
- persistence
- session
- update
- overwrite
- unit
- scene-graph
- governance
- inspectable
- conflict
- overwrite
When to use
Optimised for: real-time perception + spatial reasoning + multi-modal sensor fusion
Anti-fit: not for non-embodied / non-physical use cases
Pros & cons
Pros
Efficient world-model representation using Gaussian distributions over states.
Cons
Research-stage; expressiveness limited by Gaussian assumption.
Claims & capabilities
ICCV 2025. Action-conditioned 3D video prediction; visual representation learning for imitation; neural simulator for model-based RL.
Technical surface
- API surface
- not applicable — research paper
- Backend storage
- not applicable — research paper
- Deployment
- searched not found
- Embedding model
- not applicable — research paper
- Multi-tenancy
- not applicable — research paper
- MCP
- not applicable — research paper, no deployed product
- A2A
- not applicable — research paper, no deployed product
- OpenTelemetry
- not applicable — research paper, no deployed product
Alternatives to GWM (Gaussian World Models) → live options ranked by shared design, licence, hosting and MCP support
Similar systems
Other vertical / domain-specific ai memory in the catalog, ranked by inbound references.
- Inworld AI T1
Formerly an NPC character engine with named Long-Term Memory; now sells realtime voice models (TTS-2, STT-1, speech-to-speech) and OpenAI-compatible open-model inference. Character/NPC memory is no longer the headline product.
- NVIDIA ReMEmbR T3
Builds long-horizon memory by captioning video segments with VILA, storing captions with timestamps + 3D position coordinates in MilvusDB. At query time, LLM iterates retrieval across text, time, and position modalities. Deployed on Nova Carter robot (Jetson Orin).
- Abridge T1
Clinician-assist ambient documentation. Source mapping: every AI-generated summary element traced back to the source utterance. Audit-and-trust layer over episodic memory. Built on proprietary 1.5M+ medical-encounter dataset.
- ASAPP GenerativeAgent T1
Treats memory as first-class architecture. Captures the digital footprint of every interaction; retrieves preference and history at engagement time. Public example: airline knowing a frequent flyer wants aisle seats with her son — preference-aware, not just history-lookup.
- BenevolentAI T1
Taken private: merged into Osaka Holdings (renamed BenevolentAI S.A.) and delisted from Euronext Amsterdam 2025-03-13. Target identification / drug repurposing / mechanism tracing. 85+ data sources, petabyte-scale, rebuilt every few weeks. Wet-lab results re-enter the graph and shift downstream predictions — institutional experimental memory closing a feedback loop. As of Oct 2026 benevolent.com leads with Qor, powered by BenevolentAI, a life-science intelligence service for biopharma decision makers and consultancies. Qor (qor.one) is a continuously updated decision-intelligence service built on BenevolentAI's knowledge graph and reasoning methods: it tracks evidence on an asset or indication (competitive position, rival readouts, comparable deals), source-verifies each claim and flags when an earlier conclusion stops holding. It targets biotech teams and life-science consultancies.
- Causaly T1
Agentic AI platform for life sciences: orchestrated scientific agents over a curated biomedical knowledge graph (plus Bio Graph and Pipeline Graph), an evidence-retrieval system and an enterprise data fabric over literature, trials and patents.
Sources (23 cited facts, 0 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is 3D Gaussian Splatting latent world model vendor
- What it does & what's distinct Encodes scene into 3D Gaussian Splat representations via 3D VAE; latent Diffusion Transf… vendor
- Claims / benefits ICCV 2025. Action-conditioned 3D video prediction; visual representation learning for im… vendor
- Modalities vision + sensor vendor
- Created 2025-08-25 (GWM: Towards Scalable Gaussian World Models for Robotic Manipulation; arxiv … paper
- License MIT repo
- GitHub Gaussian-World-Model/gaussianwm — ~143 stars, last commit 2025-10 repo
- Memory volume / scale no scale claim (research; ICCV 2025) vendor
- Performance GWM: gaussian world models for driving — PSNR / FID over GAIA baseline (project page) vendor
- Code/weights release Paper (ICCV 2025, arXiv 2508.17600) + partial code release (training code, WIP; no GWM w… vendor
- Versioning model-version semantics (policy checkpoints) vendor
- Contradiction handling always overwrite (last-write-wins) vendor
- Forgetting policy episode-based memory; long-term memory module retains landmarks; episodic memory pruned … vendor
- Validated verticals robotics (humanoid, manipulation), autonomous-driving, embodied AI research vendor
- Time to running weeks-to-months (custom robot/vehicle integration) or research-only code release vendor
- Anti-fit not for non-embodied / non-physical use cases vendor
- Optimised for real-time perception + spatial reasoning + multi-modal sensor fusion vendor
- Adjacent infrastructure requires robot / vehicle hardware + sensor stack vendor
- Pros Efficient world-model representation using Gaussian distributions over states. vendor
- Cons Research-stage; expressiveness limited by Gaussian assumption. vendor
- Project & sources project page vendor
- licensing-bucket open-source repo
- taxonomy-three-layer-rollup agent-infra repo
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)