Game world models have made rapid progress toward real-time interactive generation. Yet action control is still predominantly implemented as feature conditioning, leaving the model to learn from training data how each action should move th…
Scene-level 3D generation has long been dominated by 2D multi-view or video diffusion models. Typically, these 2D-based approaches perform scene generation in a 2D latent space, which introduces two fundamental issues: (i) representing 3D…
Adapting existing manga into coherent animation that stays faithful to the source is a valuable yet challenging task. Existing methods either access the manga mainly through text, losing its characters and art style, or feed manga pages di…
Memory-native evolution requires making memory an intrinsic capability of foundation models, enabling them to continuously accumulate and utilize information. To this end, we introduce MemT-1.0, a new architecture of memory foundation mode…
Coding agents can answer analytical questions over a data lake by discovering, cleaning, and joining the relevant data. However, they discard this work after each question and redo it from scratch for the next one. Tool evolution, which au…
Generalizing real-time physics-based animation across diverse 3D shapes and spatial discretizations remains challenging. In this paper, we introduce PhysSkin++, a physics-informed framework that learns continuous neural skinning fields fro…
LLM routing dynamically selects and coordinates heterogeneous language models across diverse tasks. However, existing approaches are largely built around a predefined execution paradigm, such as single-round, multi-round, or agentic routin…
We propose KronLSTM, a linear attention architecture based on the Kronecker Delta Rule, a novel update rule for associative matrix memories. KronLSTM extends the xLSTM family with a memory-revision mechanism that corrects targeted associat…
The goal of a world model is to capture the dynamics of an environment. This has the great appeal that it allows agents to plan and simulate a course of actions with the help of a world model. For these uses to be reliable, however, the le…
Agents need reliable ways to validate their outputs, both when completing tasks and when filtering synthetic training data. We study verifier generation: from the instruction and environment available for solving a task, an agent writes an…
Video face swapping transfers the reference identity to a target video while preserving its other attributes and motion. Despite recent progress in reference-guided flow-based methods, jointly achieving faithful identity transfer, high fid…
Scaling laws suggest that increasing model size, training data, and compute generally yields monotonic performance improvements. While this often holds at the aggregate level, we present systematic evidence that vision-language models (VLM…
Diffusion Transformers (DiTs) achieve high-fidelity image and video generation, but they suffer from substantial inference costs due to repeated transformer evaluations across many denoising steps. Feature caching reduces this cost by reus…
As language-model agents grow more capable, they can carry more of a task without asking anyone for help. Falling reliance on a human partner is easy to read as a failure of collaboration when it may instead be a correct division of labor,…
Brain encoding models aim to predict neural responses to stimuli. The most widely used approach fits readouts from frozen pretrained backbones. Using neural data to train large models from scratch or fully fine-tune them after task-pretrai…
Experience generated during deployment offers an opportunity for robots to improve policy reliability through learning from their own executions. However, learning through human corrections requires teleoperators to monitor execution and i…
Nature Machine Intelligence, Published online: 19 October 2026; doi:10.1038/s42256-026-01311-y This work studies the reusability of CORNETO, a previously developed framework for learning biological networks from multi-omics data. Robust ne…
Large Language Model (LLM) agents are increasingly deployed in unfamiliar and evolving environments, requiring them to proactively explore, understand, and adapt to environmental dynamics. However, existing benchmarks rarely test whether a…
Training high-quality diffusion models is computationally expensive, and inference-time guidance often adds further sampling cost. In this work, we introduce Swift, a simple yet effective self-guided training method that uses a frozen weak…
Cooperative language-model agents can improve without weight updates by revising reusable skills, but only if a shared team reward is traced to the responsible agent and skill. Existing methods credit the skills present in each trajectory,…