Tagged articles

Zero-Shot Generalization

10 articles · Page 1 of 1

Nov 2, 2026 · Artificial Intelligence

PhysLDM: Latent Diffusion Paradigm for High-Fidelity Deformable Simulation

PhysLDM introduces a latent diffusion paradigm for high-fidelity deformable simulation, achieving millimeter-level reconstruction accuracy, zero-shot generalization to unseen objects, and end-to-end differentiability by compressing entire simulation trajectories into a spatio-temporal VAE and generating them with a diffusion model, outperforming regression and autoregressive baselines in chaotic dynamics.

Chaotic DynamicsDeformable ObjectsEnd-to-End Differentiable

0 likes · 11 min read

PhysLDM: Latent Diffusion Paradigm for High-Fidelity Deformable Simulation

Machine Heart

Oct 15, 2026 · Artificial Intelligence

Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning

Tadpole introduces an autoencoder-based foundation model for 3D partial differential equations, pretrained via reconstruction on massive online-generated simulation data (202 TB equivalent) without storing it, enabling zero-shot reconstruction, dynamics prediction via lightweight adaptation, and generation across diverse 3D physical systems and resolutions.

3D PDEZero-Shot Generalizationautoencoder

0 likes · 14 min read

Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning

Machine Learning Algorithms & Natural Language Processing

Oct 3, 2026 · Artificial Intelligence

Structured Representations as Scaffolding for Robot Reasoning: Jiajun Wu's IROS 2026 Talk

Jiajun Wu's IROS 2026 talk presents structured representations as scaffolding for robot reasoning, covering learning predicates and actions from demonstrations, differentiable planning with foundation models, post-training for unseen objects, and generating interaction sequences via video diffusion models without human demonstrations.

IROS 2026Jiajun WuZero-Shot Generalization

0 likes · 25 min read

Structured Representations as Scaffolding for Robot Reasoning: Jiajun Wu's IROS 2026 Talk

Machine Heart

Sep 26, 2026 · Artificial Intelligence

Show-Harness: A Semantic Action Interface Lets VLMs Control Real Robots Zero-Shot

Show-Harness introduces an Embodied Harness — a semantic action interface enabling vision-language models to control diverse robots through interpretable, composable actions like move, rotate, grasp, and release, achieving 89–100% zero-shot success across tasks, environments, and embodiments while unifying human teleoperation, GUI agents, and VLM control via the GUMI interface.

Embodied AIGUMISemantic Action Interface

0 likes · 16 min read

Show-Harness: A Semantic Action Interface Lets VLMs Control Real Robots Zero-Shot

Machine Heart

Sep 17, 2026 · Artificial Intelligence

World Synesthesia Model Achieves Robust Dexterous In-Hand Manipulation Under Real-World Perturbations

Sharpa Robotics' World Synesthesia Model (WSM), accepted at CoRL 2026, unifies visual geometry, tactile contact, proprioception, and action history into a reusable world model state, enabling a 22-DoF five-finger hand to achieve robust, generalizable in-hand rotation across unseen objects and real-world perturbations through clean depth supervision and recurrent memory.

CoRL 2026Sim-to-RealWorld Models

0 likes · 12 min read

World Synesthesia Model Achieves Robust Dexterous In-Hand Manipulation Under Real-World Perturbations

DeepHub IMBA

Sep 4, 2026 · Artificial Intelligence

TimesFM-3: Google's Native Multivariate Forecasting with One-Pass Decoding

Google's TimesFM-3 introduces native multivariate time series forecasting with non-autoregressive decoding, enabling joint predictions across multiple targets and covariates in a single forward pass, outperforming competitors on benchmarks while offering zero-shot generalization and probabilistic outputs.

TimesFM-3Zero-Shot Generalizationfoundation models

0 likes · 15 min read

TimesFM-3: Google's Native Multivariate Forecasting with One-Pass Decoding

Machine Heart

Jul 18, 2026 · Artificial Intelligence

World’s First Cloud‑Deployed Embodied AI Model Swaps Robotic Hands in 30 Seconds

Visics demonstrated the world’s first cloud‑based embodied AI model at WAIC 2026, showing a single brain controlling multiple robotic hands that can be swapped in 30 seconds without retraining, achieving 99% grasp success across ten hand types using a VLOA architecture and massive video‑simulation data.

EaaSEmbodied AIZero-Shot Generalization

0 likes · 10 min read

World’s First Cloud‑Deployed Embodied AI Model Swaps Robotic Hands in 30 Seconds

SuanNi

May 31, 2026 · Artificial Intelligence

How NVIDIA’s Gamma‑World Turns Single‑Agent Models into Multiplayer Experiences

Gamma‑World introduces a multi‑agent world model that solves identity, interaction, and real‑time inference challenges with parameter‑free geometric encoding, sparse hub attention, and teacher‑student distillation, enabling zero‑shot generalization from two to four agents and achieving 24 FPS interactive video generation.

Gamma-WorldReal-time InferenceSimplex Rotary Agent Encoding

0 likes · 11 min read

How NVIDIA’s Gamma‑World Turns Single‑Agent Models into Multiplayer Experiences

AI Frontier Lectures

Dec 15, 2025 · Artificial Intelligence

How UnityVideo Unifies Multimodal Training to Boost Video Generation

UnityVideo, a new vision framework from HKUST, CUHK, Tsinghua and Kuaishou, unifies training across depth, flow, pose, segmentation and RGB modalities, achieving faster convergence, higher video quality, zero‑shot generalization and stronger physical reasoning compared with existing single‑modality video generators.

AI researchMultimodal Video GenerationUnityVideo

0 likes · 15 min read

How UnityVideo Unifies Multimodal Training to Boost Video Generation

AI Frontier Lectures

Jul 18, 2025 · Artificial Intelligence

How Anchored Attributes Boost Prompt Learning for Vision‑Language Models

The paper introduces ATPrompt, a method that inserts fixed attribute tokens into learnable prompts for CLIP‑style vision‑language models, enabling the soft prompts to capture generic attribute representations and significantly improve base‑to‑novel generalization without extra regularization losses.

ATPromptZero-Shot Generalizationattribute anchoring

0 likes · 20 min read

How Anchored Attributes Boost Prompt Learning for Vision‑Language Models