Selects a referred target from candidate bounding boxes, then decodes tracking waypoints for single-camera embodied visual tracking. Injects past selected-bbox geometry via sliding-window TVBI tokens and is co-trained on a Refer‑QA dataset; achieves SOTA on EVT‑Bench and demonstrates sim-to-real on legged and humanoid robots.
AI Model2026
Delivers image and video understanding plus a built-in event‑gated streaming gate — a unified 4B multimodal foundation model that uses codec-aligned tokenization to cut visual tokens by >75% and yield up to 3.5× wall‑clock inference speedup for streaming and long‑horizon video tasks.
AI Video Papers2026
Real-time streaming multimodal foundation model that uses a codec-native tokenizer (Mage-ViT) to encode motion- and residual-rich regions from video I/P frames, reducing visual token usage by over 75% and enabling up to ~3.5× wall-clock inference speedup after training on ~560M images and 100M video frames.
AI Video2026
Generates synchronized stereo audio and video from multimodal inputs (text, images, video, audio), producing 4–15s clips at 24 FPS with a 768p base and an in‑context regeneration path to 2K; supports first/last‑frame and multi‑reference modes and ships as two task‑specific checkpoints.
AI Dataset2026
Captures synchronized multimodal embodied-human data in real homes — egocentric and multi-view video, metric body/hand/object motion, audio, and tactile signals. Released under a gated non-commercial research license with identifiable participants and strict non-redistribution/privacy constraints.
AI Video Papers2026
Converts text prompts into physically consistent videos by synthesizing executable Blender programs as a process-level chain-of-thought and using a dual-engine pipeline (deterministic simulation draft + draft-conditioned video editor). Ships with a VideoCoCo-3K draft–instruction–target dataset and shows substantial gains in physical-consistency benchmarks.
Learns a discrete “physical language” from unlabeled videos and uses a reason-then-render pipeline: predict compact state-transition tokens, then decode them into future video. Separates dynamics inference from pixel synthesis to improve physical fidelity, controllable simulation, and zero-shot motion transfer.
AI Dataset2026
Provides 30,969 action-conditioned video episodes, each with source MP4, per-frame keyboard control logs, captions, and a COLMAP sparse pose model — intended for research on action-conditioned video prediction, controllable world models, and representation learning.
AI Model2026
Provides GGUF-quantized, ComfyUI-ready MiniMax‑H3 model files (FL2VA/REF2VA, text encoder, audio/video VAEs) to enable local ComfyUI inference for short video + stereo audio generation; requires the official VAEs and sufficient VRAM.
AI Video Papers2026
Introduces WorldExam, a diagnostic benchmark that evaluates controllable video world models across four levels from visual quality to inherent world reactivity. Covers 1,474 cases across eight tasks and supports camera-, action-, and language-driven paradigms, measuring scene-conditioned reactions beyond explicit instructions.
AI Video Papers2026
Performs real-time, instruction-guided video-to-video editing on streaming input using a 16B autoregressive diffusion model that preserves subject identity and long-term temporal coherence; achieves end-to-end 720p at ≈30 FPS on a single Nvidia B200 GPU. Key features include chunk-wise autoregressive adaptation, Source-Anchored Distribution Matching Distillation (SA-DMD) that reduces diffusion to a two-step generator, and Long-Horizon Autoregressive Distillation to mitigate temporal drift.
AI Model2026
A quickly trained 2D "tine" VAE for MiniMax‑H3 that speeds up preview renders of video outputs and typically outperforms latent2rgb for preview use. Currently only compatible with the ModelPreviewOverride node in ComfyUI‑KJNodes and intended for previewing rather than production-grade decoding.