arXiv subjects

Zhaoyang Yang

Publications and source records attributed to Zhaoyang Yang.

7 recordsLinked to original sources

arXiv2026

PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models

We present PhysBrain 1.5, a unified model for understanding physical environments, generating actions, and predicting future states. Motivated by the physical loop of observation, interaction, and environmental change, we bring these capabilities into a common learning framework. Starting from a general vision--language model, we encode language responses, end-effector motion, and dense visual targets as discrete sequences and jointly optimize them with autoregressive next-token prediction. Pre-training draws its embodied supervision entirely from human interaction videos, using task-centered episodes to pair semantic and spatial context with recovered motion and subsequent observations. We then adapt the model through supervised fine-tuning on a mixture of human demonstrations, robot trajectories, and simulated experience. Across 28 embodied understanding benchmarks, our 8B model achieves an average score of 72.5, setting a new open-source state of the art and performing on par with leading proprietary models such as GPT-6-Astra and Gemini 3.6 Flash. It achieves the best open-source results on 14 benchmarks while retaining general multimodal capabilities. Beyond these understanding evaluations, qualitative examples show the model's ability to produce end-effector trajectories and predict future scenes through spatially aligned RGB, depth, and robot-mask outputs.

cs.CV↗

arXiv2026

EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields

Pretrained video diffusion models provide powerful spatiotemporal generative priors, making them a natural foundation for robotic world models. While recent world-action models jointly optimize future videos and actions, they predominantly treat video generation as an auxiliary representation for policy learning. Consequently, they insufficiently explore the inverse problem: leveraging action signals to guide video synthesis, thereby often failing to preserve precise robot spatial geometry and fine-grained robot-object interaction dynamics in the generated rollouts. To bridge this gap, we present EA-WM, an Event-Aware Generative World Model that effectively closes the loop between kinematic control and visual perception. Rather than injecting joint or end-effector actions as abstract, low-dimensional tokens, EA-WM projects actions and kinematic states directly into the target camera view as Structured Kinematic-to-Visual Action Fields. To fully exploit this geometrically grounded representation, we introduce event-aware bidirectional fusion blocks that modulate cross-branch attention, capturing object state changes and interaction dynamics. Evaluated on the comprehensive WorldArena benchmark, EA-WM achieves state-of-the-art performance, outperforming existing baselines by a significant margin.

cs.CV↗

arXiv2025

Context-Aware Lifelong Sequential Modeling for Online Click-Through Rate Prediction

Lifelong sequential modeling (LSM) is becoming increasingly critical in social media recommendation systems for predicting the click-through rate (CTR) of items presented to users. Central to this process is the attention mechanism, which extracts interest representations with respect to candidate items from the user sequence. Typically, attention mechanisms operate in a point-wise manner, focusing solely on the relevance of individual items in the sequence to the candidate item. In contrast, context-aware LSM aims to also consider adjacent items in the user behavior sequence to better assess the importance of each item. In this paper, we propose the Context-Aware Interest Network (CAIN), which utilizes the Temporal Convolutional Network (TCN) to create context-aware representations for each item throughout the lifelong sequence. These enhanced representations are then used in the attention mechanism instead of the original item representations to derive context-aware interest representations. Building upon this TCN framework, we propose the Multi-Scope Interest Aggregator (MSIA) module, which incorporates multiple TCN layers and their corresponding attention modules to capture interest representations across varying context scopes. Furthermore, we introduce the Personalized Extractor Generation (PEG) module, which generates convolution filters based on users' basic profile features. These personalized filters are then used in the TCN layers instead of the original global filters to generate more user-specific representations. We conducted extensive experiments on both a public dataset and an industrial dataset from the WeChat Channels platform. The results demonstrate that CAIN outperforms existing methods in terms of prediction accuracy and online performance metrics.

cs.IR↗

arXiv2025

A double-layer placement algorithm for integrated circuit-based modules on printed circuit board

Considering that the physical design of printed circuit board (PCB) follows the principle of modularized design, this paper proposes an automatic placement algorithm for functional modules. We first model the placement problem as a mixed-variable optimization problem, and then, developed tailored algorithms of global placement and legalization for the top-layer centralized placement subproblem and the bottom-layer pin-oriented placement subproblem. Numerical comparison demonstrates that the proposed mixed-variable optimization scheme can get optimized total wirelength of placement. Meanwhile, experimental results on several industrial PCB cases show that the developed centralized strategies can well accommodate the requirement of top-layer placement, and the pin-oriented global placement based on bin clustering contributes to optimized placement results meeting the requirement of pin-oriented design.

cs.OH↗

arXiv2024

Cross Domain LifeLong Sequential Modeling for Online Click-Through Rate Prediction

Deep neural networks (DNNs) that incorporated lifelong sequential modeling (LSM) have brought great success to recommendation systems in various social media platforms. While continuous improvements have been made in domain-specific LSM, limited work has been done in cross-domain LSM, which considers modeling of lifelong sequences of both target domain and source domain. In this paper, we propose Lifelong Cross Network (LCN) to incorporate cross-domain LSM to improve the click-through rate (CTR) prediction in the target domain. The proposed LCN contains a LifeLong Attention Pyramid (LAP) module that comprises of three levels of cascaded attentions to effectively extract interest representations with respect to the candidate item from lifelong sequences. We also propose Cross Representation Production (CRP) module to enforce additional supervision on the learning and alignment of cross-domain representations so that they can be better reused on learning of the CTR prediction in the target domain. We conducted extensive experiments on WeChat Channels industrial dataset as well as on benchmark dataset. Results have revealed that the proposed LCN outperforms existing work in terms of both prediction accuracy and online performance.

cs.IR↗

arXiv2020

Fully Convolutional Networks for Continuous Sign Language Recognition

Continuous sign language recognition (SLR) is a challenging task that requires learning on both spatial and temporal dimensions of signing frame sequences. Most recent work accomplishes this by using CNN and RNN hybrid networks. However, training these networks is generally non-trivial, and most of them fail in learning unseen sequence patterns, causing an unsatisfactory performance for online recognition. In this paper, we propose a fully convolutional network (FCN) for online SLR to concurrently learn spatial and temporal features from weakly annotated video sequences with only sentence-level annotations given. A gloss feature enhancement (GFE) module is introduced in the proposed network to enforce better sequence alignment learning. The proposed network is end-to-end trainable without any pre-training. We conduct experiments on two large scale SLR datasets. Experiments show that our method for continuous SLR is effective and performs well in online recognition.

cs.CV↗

arXiv2019

SF-Net: Structured Feature Network for Continuous Sign Language Recognition

Continuous sign language recognition (SLR) aims to translate a signing sequence into a sentence. It is very challenging as sign language is rich in vocabulary, while many among them contain similar gestures and motions. Moreover, it is weakly supervised as the alignment of signing glosses is not available. In this paper, we propose Structured Feature Network (SF-Net) to address these challenges by effectively learn multiple levels of semantic information in the data. The proposed SF-Net extracts features in a structured manner and gradually encodes information at the frame level, the gloss level and the sentence level into the feature representation. The proposed SF-Net can be trained end-to-end without the help of other models or pre-training. We tested the proposed SF-Net on two large scale public SLR datasets collected from different continuous SLR scenarios. Results show that the proposed SF-Net clearly outperforms previous sequence level supervision based methods in terms of both accuracy and adaptability.

cs.CV↗