https://quangminhdinh.github.io/garden/ Recent content in Garden on Quang Minh Dinh Hugo en-us Mon, 22 Jun 2026 00:00:00 +0000 https://quangminhdinh.github.io/garden/shared-channel-not-shared-world/ Mon, 22 Jun 2026 00:00:00 +0000 https://quangminhdinh.github.io/garden/shared-channel-not-shared-world/ Generative agents coordinate through language and memory, but they never share a world. That ceiling is the whole point. https://quangminhdinh.github.io/garden/world-in-a-grain-of-sand/ Mon, 22 Jun 2026 00:00:00 +0000 https://quangminhdinh.github.io/garden/world-in-a-grain-of-sand/ Blake's image, read through world models: the whole inferred from the detail, both as a design principle and as evidence the model worked. https://quangminhdinh.github.io/garden/why-royal-road-fascinates-me/ Mon, 22 Jun 2026 00:00:00 +0000 https://quangminhdinh.github.io/garden/why-royal-road-fascinates-me/ Legendary Moonlight Sculptor is one of my favorite novels, and the things that hooked me as a kid turned out to be my research. https://quangminhdinh.github.io/garden/stories-nobody-wrote/ Mon, 22 Jun 2026 00:00:00 +0000 https://quangminhdinh.github.io/garden/stories-nobody-wrote/ What makes the world feel infinite isn't more content, it's emergence: outcomes no designer anticipated, born from player-world synergy. https://quangminhdinh.github.io/garden/building-royal-road/ Mon, 22 Jun 2026 00:00:00 +0000 https://quangminhdinh.github.io/garden/building-royal-road/ Through a researcher's lens: the properties that make Royal Road great, how close today's LLM-driven games get, and the gap that remains. https://quangminhdinh.github.io/garden/action-space-as-discovery/ Mon, 22 Jun 2026 00:00:00 +0000 https://quangminhdinh.github.io/garden/action-space-as-discovery/ Text adventures let you guess at an open verb set; modern games hand you a closed one. The same tension shows up in agent action spaces. https://quangminhdinh.github.io/garden/shared-state-is-a-tiny-world-model/ Sun, 21 Jun 2026 00:00:00 +0000 https://quangminhdinh.github.io/garden/shared-state-is-a-tiny-world-model/ A multiplayer game restated my research agenda in miniature: two agents can only coordinate when they agree on one authoritative model of the world. https://quangminhdinh.github.io/garden/the-loss-decides-what-the-model-ignores/ Sat, 20 Jun 2026 00:00:00 +0000 https://quangminhdinh.github.io/garden/the-loss-decides-what-the-model-ignores/ Two projects where the objective, not the architecture, dictated what the model paid attention to and what it left blank. https://quangminhdinh.github.io/garden/build-on-the-representation-that-already-travels/ Thu, 18 Jun 2026 00:00:00 +0000 https://quangminhdinh.github.io/garden/build-on-the-representation-that-already-travels/ PedroVerse stylized 3D assets by editing only their UV maps, because UV maps render everywhere. Choosing the substrate that is already universal buys portability for free. https://quangminhdinh.github.io/garden/read-the-data-first/ Mon, 15 Jun 2026 00:00:00 +0000 https://quangminhdinh.github.io/garden/read-the-data-first/ Supervision and structure are often already in the dataset, hiding in plain sight. The second vehicle in a sentence was free labels. https://quangminhdinh.github.io/garden/cheap-structure-beats-heavy-machinery/ Fri, 12 Jun 2026 00:00:00 +0000 https://quangminhdinh.github.io/garden/cheap-structure-beats-heavy-machinery/ The simplest mechanism that clears the bar keeps winning over the impressive one that doesn't. A pattern across a startup, a challenge entry, and a rendering project. https://quangminhdinh.github.io/garden/the-test-distribution-is-the-only-one-that-counts/ Sat, 30 May 2026 00:00:00 +0000 https://quangminhdinh.github.io/garden/the-test-distribution-is-the-only-one-that-counts/ A strong validation number can be a trap. My clearest version of this lesson came from a 0.58 that became a 0.35. https://quangminhdinh.github.io/garden/bottleneck-is-rarely-the-model/ Thu, 28 May 2026 00:00:00 +0000 https://quangminhdinh.github.io/garden/bottleneck-is-rarely-the-model/ Across four very different projects, the thing that capped quality was almost never the network. It was a systems or representation cost hiding underneath. https://quangminhdinh.github.io/garden/world-models/ Tue, 10 Mar 2026 00:00:00 +0000 https://quangminhdinh.github.io/garden/world-models/ Why a common representation of the world is upstream of believable multi-agent behaviour. https://quangminhdinh.github.io/garden/reachy-pilot-study/ Sun, 01 Mar 2026 00:00:00 +0000 https://quangminhdinh.github.io/garden/reachy-pilot-study/ Our autonomous HRI pilot fooled participants 62% of the time, but the way it failed mattered more than the number. https://quangminhdinh.github.io/garden/multi-agent-grounding/ Fri, 20 Feb 2026 00:00:00 +0000 https://quangminhdinh.github.io/garden/multi-agent-grounding/ If we want agents to share more than what can be said, the grounding signal has to be richer than text. https://quangminhdinh.github.io/garden/phd-motivation/ Sun, 01 Feb 2026 00:00:00 +0000 https://quangminhdinh.github.io/garden/phd-motivation/ A personal note on the path from audio processing at Huawei to wanting to spend six years on world models. https://quangminhdinh.github.io/garden/conditioning-is-an-assumption/ Thu, 15 Jan 2026 00:00:00 +0000 https://quangminhdinh.github.io/garden/conditioning-is-an-assumption/ Lessons from extending IMLE to text-conditional generation: failures almost always traced to latent mismatch. https://quangminhdinh.github.io/garden/what-is-a-world-state/ Tue, 15 Aug 2023 00:00:00 +0000 https://quangminhdinh.github.io/garden/what-is-a-world-state/ We talk about world models as if 'the state' were given. The representation is the hard part.