DOOM

Headlines · 4

1. 2d
   DOOMFORMER implements a Transformer through DOOM mechanics

   A creator introduced DOOMFORMER, an experimental Transformer whose mathematical operations are implemented through DOOM game mechanics and voodoo dolls rather than a conventional numerical library. The creator says it can classify MNIST digits drawn on DOOM maps, make decisions, and play DOOM across many game instances. These capabilities and the scale of the experiment have not been independently reproduced or benchmarked.

   Hacker News 首页（100+ 分） · 🔥 1
2. Oct 22
   miHoYo and universities open-source GameScaling game-agent models from 0.8B to 27B

   IT Home reports that miHoYo's Honkai AI team, together with Tsinghua University, Peking University, the University of Chinese Academy of Sciences, the University of Hong Kong and the National University of Singapore, has released the open-source GameScaling series of game-playing models. The team published eight checkpoints at 0.8B, 2B, 9B and 27B parameters, each in an S1 version trained only on Minecraft data and an S3 version trained on mixed-game data with Minecraft at 27%, all using 1,600 hours of gameplay. According to the project's GitHub description, the models are continually pre-trained from the Qwen3.5 vision-language model and take current and earlier frames plus input history to emit keyboard and mouse actions, with each call covering about 200 ms including six 33 ms steps; tasks span mining, crafting and combat in Minecraft, fighting and pathfinding in Doom, and escape-room puzzles. Code and weights are under Apache 2.0, vLLM serving is supported, and the 0.8B, 2B and 9B weights fit on one GPU while 27B needs two GPUs with tensor parallelism, the report says.

   IT之家 AI · 🔥 0
3. Oct 19
   OverSeer world model adds fixed auxiliary cameras to keep multi-agent video consistent

   A new arXiv preprint (2610.28554, submitted 20 Oct 2026) from Runjia Li and co-authors introduces OverSeer, a multi-agent video world model that augments each agent's egocentric view with auxiliary camera views. The authors argue that fixing these auxiliary views in space makes them a proxy for a world-centric representation, and report that they substantially help the model maintain consistency; a delta-VAE encoder that stores only changes relative to a static reference image cuts the tokens needed to process them. Experiments in Minecraft and Doom are said to show improved world and agent consistency, with qualitative results on real-world multi-camera captures, though all results are self-reported and not yet peer-reviewed.

   Hugging Face · Papers · 🔥 0
4. Oct 6
   System Switch: When Should a Fast Decision Model Stop and Think?

   This arXiv paper studies dual-process agents in which a fast learned actor makes every decision and hands control to a reasoning vision-language model only when a gate opens, while the game keeps running. Testing on closed-loop Doom and new open "System One" typed-decision models (0.15B–9B parameters, 900 held-out questions), the author finds accuracy, calibration and sensitivity are distinct: models with similar accuracy differ widely in AUROC. Offline, deferring the least confident 30% of decisions to a reasoner beats random deferral in proportion to the actor's AUROC (rank correlation 0.87), with a gain of +0.13 [0.08, 0.18] on held-out games (+0.08 [0.02, 0.14] with shuffled options), about half of it coming from reasoning — yet in closed loop (33 games, three seeds) no variant reaches the exit.

   Hugging Face · Papers · 🔥 0

Experience and discussion from the community

Share my DOOM experienceAsk about DOOM