Synthesizes RGB frames from structured world states exported by physics engines; it reformulates a heavy generative renderer into a few-step autoregressive streaming model and uses lightweight distilled codecs to reach playable ~30 FPS while preserving G-buffer and prompt control.
Analyzes internal computation of text-to-image diffusion transformers and shows structural template tokens act as implicit semantic registers that maintain object identity during denoising. Introduces a causal interpretability framework (attention decomposition + targeted interventions) and a training-free pruning rule that cuts ~20% attention FLOPs for a ~1.4-point GenEval drop.
Efficient 4B-scale image generation and editing model family that pairs a lightweight VAE tokenizer (Mage-VAE) with a native-resolution multimodal diffusion transformer, reducing tokenization cost by an order of magnitude and enabling few-step high-resolution generation and editing.
AI Video Papers2026
Extrapolates long video sequences from very short contexts by restoring memory-writing supervision in autoregressive video diffusion models using a two-pass Self Gradient Forcing (SGF). SGF records a no-gradient rollout at a sampled denoising exit and then recomputes KV context in a second parallel pass so future losses teach earlier latent writes, enabling minutes-long extrapolation from ~5s windows.
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.
Evaluates spatial cognition of image-generation models by eliciting protocol-constrained visual answers and parsing pixel outputs into structured predictions compatible with existing metrics. Introduces the ProVisE framework and SpatialGen-Bench (470 samples) to compare image-generation models and text-output VLMs on unified spatial tasks.
Converts image-content removal into a contrastive on-policy self-distillation signal: the EMA teacher produces next-token distributions with and without image content, uses their log-probability differences to sharpen visual-grounded candidates, and distills that full-distribution target into the student—no external teacher or extra inference cost.
Empirically studies how transformer-based native multimodal pre-training scales under fixed compute, deriving compute- and data-allocation power laws and an efficiency frontier for model size, token count, and data mixture; evaluates cross-modal transfer and multimodal in-context learning.
AI Agent Papers2026
Drives long‑horizon desktop agents by reading and manipulating program state (files, DOM, backends) instead of relying on screenshots. The main agent uses code for actions and structural verification while a lightweight GUI subagent handles rare screenshot-click steps, improving success rates and lowering per-task cost versus screenshot-only approaches.
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.
Generates polygonal meshes from images using flow matching for fast, native mesh synthesis. Decodes vertices, edge connectivity, and face winding in one parallel pass, preserves artist-authored topology without vertex quantization or welding, supports a user-set vertex budget for face-count control, and completes image-to-mesh in ~6s median.
Embodied AI2026
Provides a portable, robot-free UMI capture pipeline and shows that policies post-trained only on this high-fidelity data deploy directly on real robots matching teleoperation baselines. Capture achieves ~3 mm end-effector accuracy, microsecond sync, ultra-wide FOV, and releases 2,000h HiFi-UMI-2K.