Provides a unified data and evaluation suite for measuring gameplay capabilities across short, medium, and long temporal horizons. Includes an automated annotator, a 5,000-hour AAA gameplay dataset with temporally aligned frames, actions and multi-horizon instructions, and a reproducible offline + stepwise online benchmark.
Evaluates whether generative world models maintain consistent, controllable, and physically plausible simulated environments under exploration, interaction, and intervention. Introduces a six-level W1–W6 capability taxonomy across three tracks (video, spatial, embodied) with human A/B Arena and automated metrics to measure behavioral correctness.
Compresses a geometry-foundation model’s multi-level features into a compact latent that decodes jointly to RGB, depth, cameras and point maps — enabling a conditional flow to generate 3D-consistent video and novel views with measurably improved coherence.
Provides WROP: a 1.5M-sample synthetic video corpus and a 300-question exam for training and evaluating object permanence and solidity in video world models. Includes 150 Blender task generators, a human Elo benchmark across 14 models, and a fine-tuned 16B continuation model (PWM-WROP).
Surveys memory mechanisms for autoregressive video generation, framing memory as persistent historical information that influences future generation. Organizes work by Forms, Functions, Operations, Learning, and Evaluation, and synthesizes challenges for long-horizon consistency and memory-aware learning.
Enables native joint video-and-audio generation and training up to 2K using a dynamic block-sparse attention scheme that cuts attention cost while preserving audio–visual coupling; provides preview checkpoints, training and inference code. High-resolution training requires large multi-GPU (80GB) clusters and CUDA ≥ 12.4.
Transforms user prompts into shot-level cinematic directions for text-to-video generation, using a 397B prompt-enhancer trained on 1.05M videos and SC-GRPO to preserve semantic consistency across shots; evaluated on WanPEval (5–30s) with large human-preference gains.
Provides imagined interaction segments generated by world models for RoboTwin2.0 tasks, stored as fixed-length HDF5 chunks (21 observation frames, 20 actions, rewards and episode flags). Useful for training and evaluating world-model-based policies; currently limited to the RoboTwin2.0 subdataset.
Replaces a selected person in a source video with a character from a reference image via a MiniMax H3 LoRA adapter, aiming to preserve scene, camera, and background. Trained for 1,000 updates; intended for Ref2VA runtimes and ComfyUI. Short (≈4–5s) continuous shots work best; distributed under the MiniMax H3 Community License.
Learns joint predictive visual dynamics and action generation for generalist robot manipulation, translating future-relevant visual representations into actions. Integrates a Mixture-of-Transformers coupling a video expert and action expert, a frozen vision-language model for semantics, 4D distillation, and Causal Imprint; pretrained on a 20K+ hour heterogeneous corpus.
Multimodal real-robot dataset of 28,993 teleoperated bimanual manipulation demonstrations (~300 hours) with synchronized multi-view RGB/tactile videos, 65D robot state/action, 60D fingertip tactile signals, and temporally aligned language segments; intended for imitation, visuomotor and visual‑tactile research, CC BY‑NC 4.0 (non‑commercial).
Proposes a forward-process RL method that dynamically localizes gradient updates and adapts multi-reward coordination for joint audio–video diffusion models. Uses bidirectional cross-attention responses for token/layer routing and preference-preserving reweighting to balance competing objectives, improving modality quality, alignment, and synchronization.