arXiv Machine Learning September 17, 2026 By Zhongben Gong, Xiaoqun Wu, Mingyang Zhou, Hui Huang

Structural Inference under Hidden Agents

Read the original on arXiv Machine Learning →

The paper introduces SIHA, a method for jointly recovering hidden-agent trajectories and their interaction structures in multi-agent dynamics. It tackles the circular dependency between trajectory reconstruction and structural inference by combining a structure‑agnostic initialization with iterative, structure‑guided refinement using Neural Relational Inference and multi‑strength structural attention. Experiments on benchmark dynamical systems and motion‑capture data show that SIHA improves both visible‑to‑visible structural inference and hidden‑state reconstruction, leading to better future predictions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Aug 10

Decoupling Intention from Trajectory: A Representational Deduction Framework for World Action Models

arXiv:2608. 06994v1 Announce Type: cross Abstract: World Action Models (WAMs) aim to construct a unified architecture capable of understanding world state evolution and guiding to generative motion planning.

By Xiangkai Ma, Yue Ma, Junjie Wang, Sheng Xu, Mingyang Li, Han Zhang, Yuzheng Zhuang, Wenzhong Li, Zhihao Yuan

robotics fine-tuning safety

arXiv Machine Learning

Jul 20

Dynamics-Aware Meta-Imitation for Generalization to Unseen Robotic Manipulation

arXiv:2607. 15880v1 Announce Type: cross Abstract: Imitation Learning aims to learn skills from extensive observations and demonstrations for robots, so it suffers from data scarcity and environment generalization.

By Zhenduo Shang, Xiyao Liu, Bohan Li, Xudong Wang, Teng Ren, Lianqing Liu, Zhi Han

agents diffusion robotics fine-tuning multimodal benchmarks

arXiv Machine Learning

Sep 29

I Act Therefore I Am: When Is JEPA's Action-Conditioning Enough to Learn Causal Mechanisms?

The paper studies when joint-embedding predictive architectures (JEPAs) can recover underlying causal states from high‑dimensional observations. It introduces a latent variable model where observations arise from causal states with action‑conditioned dynamics, and proposes an information‑theoretic objective that maximizes conditional likelihood while preserving state entropy. The authors prove identifiability conditions—particularly sufficient action‑induced variation—and instantiate the objective as an action‑modulated Gaussian additive‑noise model (A‑JEPA), demonstrating theoretical and empirical success in synthetic and visual benchmarks.

By Yuhang Liu, Zhuo Huang, Javen Qinfeng Shi

rag benchmarks

arXiv Computer Vision

Sep 15

Reconstructing Is Not Acting: Action-Centric Latent Dynamics Modeling

arXiv:2609.15189v1 Announce Type: new Abstract: Latent action models (LAMs) learn action representations from unlabeled videos by inferring latent actions from visual transitions and reconstructing f...

By Dingjie Fu, Dianxing Shi, Yangyang Xu, Jun Yu

robotics benchmarks

arXiv AI

Jun 17

ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model

arXiv:2603. 22281v2 Announce Type: replace-cross Abstract: Recent progress in latent world models (e.

By Haichao Zhang, Yijiang Li, Shwai He, Tushar Nagarajan, Mingfei Chen, Jianglin Lu, Ang Li, Yun Fu

llms robotics multimodal safety

arXiv Computer Vision

Aug 28

Residual Flow Matching with Dynamic Cross-Interaction for 3D Multi-Person Motion Prediction

The paper introduces a Prior‑Guided Residual Flow Matching framework for 3D multi‑person motion prediction. It uses a Deterministic Coarse Prior to anchor kinematics and a Dynamic Cross‑Interaction mechanism to synchronize inter‑agent message passing during integration, thereby improving structural consistency and social context extraction. A decoupled joint‑motion architecture with bidirectional fusion further preserves fine‑grained kinematic coherence, achieving state‑of‑the‑art accuracy on several datasets.

By Wei Wei, Yinyuan Zhao, Ruixuan Yu

agents diffusion benchmarks