Weekly · 2026-W44
Cinematic video generation requires both temporal inference from limited inputs (i.e., sparse rather than frame-by-frame guidance) and factor-aware control of character, scene, action, and camera. Mul...
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...
Looped language models can run more iterations at test time, but additional iterations need not help them solve longer problems. For sequential state tracking, final-answer supervision does not specif...
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 t...
Moving from controllable videos to genuinely playable worlds requires persistent world state, executable game rules, and low-latency interaction. We outline a roadmap for the next generation of Matrix...
Autoregressive video diffusion models generate videos chunk by chunk, yet producing plausible continuations does not guarantee that they capture how scenes evolve. Under teacher forcing, strong tempor...
Multimodal large language models (MLLMs) have made rapid progress on visual reasoning, yet many tasks require evidence that is difficult to obtain through internal reasoning alone: our controlled stud...
Spatial reasoning asks a model to work out where objects are in 3D space, how they relate to one another, and how they move. Agentic VLMs have recently brought large improvements on such tasks by lett...
In this report, we introduce Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adaptive capability composition. Compared with A1, Sage...
We study language-conditioned local navigation, where a robot must navigate to a text-specified target visible in its initial observation and stop at the described location. End-to-end navigation poli...
Game engines and coding agents can specify the layout, motion, and camera of a scene, yet turning such coarse structure into realistic video requires a renderer that follows the structure and complete...
Reliable multi-view forecasting requires videos from different cameras to describe the same evolving 3D scene. To this end, we introduce Video-Point Model (VPM), a world model that conditions on multi...
We present IQuest-Q1, a sparse Mixture-of-Experts (MoE) agentic foundation model with 320B total parameters (15B activated). IQuest-Q1 is developed through a three-stage process: (1) stable and effici...
Reconstructing human activity from egocentric video requires more than recovering individual 3D components: the observer's motion, surrounding geometry, and hand-object interactions must fit together ...
Human egocentric experience offers a rich foundation for learning how the world is organized and how it changes through interaction. Realizing this potential at scale requires turning growing volumes ...