#Diffusion Transformer (9)

SANA is NVIDIA Labs open-source codebase for high-resolution image and video generation (9k+ stars, Apache-2.0, PyTorch). Its efficiency comes from two structural changes: linear attention replaces vanilla attention in the transformer, and a deep compression autoencoder compresses images 32x instead of the usual 8x. Official figures: the 0.6B model renders a 1024 image in 0.9 s, roughly one fortieth of FLUX-dev 23 s, while FID improves from 10.15 to 5.61. The series now spans one-step generation, video, world models and streaming editing, and runs 4K in 8 GB of VRAM under 4-bit quantization. No benchmarks reproduced; recorded as unverified.

Image GenerationText-to-Image

Python9.2k737102

Video GenerationMediaTopC

Wan: the open-weights baseline on the video side, letting the whole ecosystem iterate on its own hardware

Alibaba Tongyi's Wan releases video generation weights under Apache-2.0, making it the most important public baseline in the video domain. Its value differs from a closed service: not "best-looking output today" but that it is fine-tunable, reproducible and runnable on your own inference stack - the whole ecosystem of LoRAs, ControlNet-style conditioning, quantisation and few-step distillation builds on it. For an intelligence site, an open-weights baseline means the question "what can video generation do today" finally has a reference can be verified directly instead of trusting vendor-selected samples. The licence and the public repository, verified; picture quality and physical plausibility remain C-grade vendor claims.

Apache-2.0Open-weight licenceVendor Claim · 2025-07

ProductAlibaba TongyiSite Repo

0:10

WholeBodyWAM: Generalizing Pre-trained World-Action Priors to Humanoid Loco-Manipulation via WBC-Grounded Coordination

World Action Models (WAMs) offer a promising approach to general-purpose robot manipulation by jointly modeling visual dynamics and actions. However, most WAM studies focus on tabletop or arm-centric manipulation, while humanoid loco-manipulation remains less explored. To address this gap, we introduce WholeBodyWAM, which jointly predicts future visual dynamics, manipulation actions, and whole-body control intents for generalizable humanoid loco-manipulation. It preserves pre-trained world-action priors while grounding heterogeneous whole-body controller (WBC) semantics and coordinating whole-body behavior. Extensive experiments show that WholeBodyWAM achieves an overall simulation task success rate of 91.9%, with a 0.23 improvement in real-world out-of-distribution task progress and a 70% reduction in success-rate variance across WBCs relative to the respective baselines. These results suggest a path toward scalable humanoid whole-body intelligence by extending pre-trained world-action priors through structured WBC grounding and coordination, rather than relearning whole-body behavior from scratch. Project page: https://wholebodywam.github.io/.

Li, Zhuo, Yao, Yiming, Tan, Jim · 900 views · Sep 15, 2026

World-action modelsHumanoid

Sep 15, 2026

1:37

Odyssey-3: A Foundation World Model for Physical Agents

@odysseyml · 1.2k views · 2026-09-15

World ModelsFoundation Models

Pre-training Visual Dexterity in Simulation

Large-scale pre-training has made robot policy fine-tuning increasingly data-efficient, but this progress has largely been driven by datasets and embodiments built around simple parallel-jaw grippers. Dexterous, multi-fingered hands remain comparatively data-starved because real teleoperation is costly to scale, while human hand video is off-embodiment and requires lossy pose estimation and retargeting. We introduce Simulation Pre-training for Dexterity (SPD), a pre-training framework for dexterous manipulation that uses data entirely collected in simulation. In SPD, humans manipulate virtual objects inside a VR headset, enabling on-embodiment trajectories and robot-free collection. With the help of five operators, we collect 75 hours of multi-task dexterous manipulation over one week, and use it to pre-train a causal transformer on a sequence modeling objective. We study the benefits of simulation pre-training on real-world tasks by fine-tuning on 1-2 hours of physical demonstrations on a 56-DoF bimanual dexterous setup. We find that our approach outperforms training behavior cloning policies from scratch, showing that simulation teleoperation is a viable pre-training source for real-world dexterous manipulation. We perform ablation studies, measuring the benefits of history conditioning and short action chunks for reactive control.

Sarthak Kamat, Adam Rashid, Satvik Sharma · 783 views · Aug 16, 2026

Sim-to-RealDexterous Manipulation

Aug 16, 2026

AtlasVLA: Persistent World-Ego State Modeling for Vision-Language-Action Models

While Vision-Language-Action (VLA) models have advanced embodied AI, their fundamentally reactive paradigm severely limits performance in partially observable and long-horizon tasks. When restricted to a single wrist-mounted camera, they inevitably suffer from perception forgetting as objects exit the field of view, and temporal task-progress forgetting} during multi-step execution. To overcome these bottlenecks, we propose AtlasVLA, a novel framework that transitions from direct reactive manipulation to proactive reasoning through a persistent world-ego state. AtlasVLA features a dual-memory architecture: a 4D Persistent World State Memory that lifts transient 2D observations into a globally updated, voxel-hashed spatial state to resolve visual blind spots, and an Ego-Working State Memory that tracks historical ego state and task progress. By conditioning a diffusion transformer (DiT) on this joint World-Ego state, AtlasVLA enables robust spatial reasoning. Extensive evaluations across LIBERO, RLBench, and real-world benchmarks demonstrate that AtlasVLA achieves state-of-the-art performance using solely a wrist camera. Remarkably, it decisively outperforms multi-view baselines, yielding absolute success rate improvements of 9.4% on LIBERO-Long and 17.5% in real-world long-horizon tasks.

Guiyu Zhao, Longteng Guo, Yanghong Mei · 681 views · Aug 7, 2026

VLAPhysical AI

Aug 7, 2026

As an Amazon Associate, we earn from qualifying purchases.

#Diffusion Transformer (9)

SANA: 4K Text-to-Image That Fits in Laptop VRAM

Wan: the open-weights baseline on the video side, letting the whole ecosystem iterate on its own hardware

Ref2VA-VSA Cuts MiniMax-H3 Generation to 72s

Veda Sparse Attention Speeds Up Video Character Replacement in ComfyUI

COSMI: Compositional Human-Object Interaction Dataset and Diffusion Model

WholeBodyWAM: Generalizing Pre-trained World-Action Priors to Humanoid Loco-Manipulation via WBC-Grounded Coordination

Odyssey-3: A Foundation World Model for Physical Agents

Pre-training Visual Dexterity in Simulation

AtlasVLA: Persistent World-Ego State Modeling for Vision-Language-Action Models