Runs local video, capture-card feeds, and game streams through a real-time GPU enhancement pipeline with super resolution, denoising, HDR processing, and frame generation. Supports NVIDIA and AMD GPUs on Windows 11; some models and features depend on specific hardware or runtimes.
Provides 1,274 hours of head-mounted egocentric video paired with seven-point IMU arm tracking (24 Hz orientation; raw accel/gyro/mag on a subset), packaged for embodied-AI and egocentric-vision research. Key features: torso-relative pose via chest reference, separate Parquet IMU repo for efficient joins, CC-BY-4.0 license; heavy class skew and limited contributor diversity are important constraints.
Provides 22 curated Three.js-based cases for code-guided video generation across eight application categories. Each case bundles an editable scene (Three.js program), a 960×544 proxy video, a 1536×864 reference image, and a plain-text prompt for controlled video-generation evaluation.
Generates MiniMax H3 videos locally on consumer hardware, adapting its inference path to available memory and compute. It can run with as little as 8 GB of VRAM and 16 GB of RAM.
Evaluates whether MiniMax-H3 can infer latent physical events from incomplete multimodal evidence and produce videos consistent with those inferences. Builds a 517-instance benchmark across four reasoning scenarios (multi-view, audio disambiguation, video continuation, audiovisual integration) and quantifies modality-specific failure modes.
Introduces a rubric-based approach for video reward modeling that generates explicit, query-adaptive evaluation criteria before scoring to reduce scalar drift; proposes RGPO, a two-stage training (seed warm-up + joint optimization) that achieves strong pointwise and pairwise evaluation with high data efficiency.
Learns a camera-queryable implicit 3D-aware memory that compresses multi-view history into target-view tokens to enable long-horizon, camera-controllable video generation. Improves revisit consistency and camera-control accuracy and supports streaming exploration from a single image or text prompt.
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.
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.