Jiahui Zhu

Ke Wang, Jiahui Zhu, Minjie Ren et al.

The success of Large Language Models (LLMs) is inherently linked to the availability of vast, diverse, and high-quality data for training and evaluation. However, the growth rate of high-quality data is significantly outpaced by the expansion of training datasets, leading to a looming data exhaustion crisis. This underscores the urgent need to enhance data efficiency and explore new data sources. In this context, synthetic data has emerged as a promising solution. Currently, data generation primarily consists of two major approaches: data augmentation and synthesis. This paper comprehensively reviews and summarizes data generation techniques throughout the lifecycle of LLMs, including data preparation, pre-training, fine-tuning, instruction-tuning, preference alignment, and applications. Furthermore, We discuss the current constraints faced by these methods and investigate potential pathways for future development and research. Our aspiration is to equip researchers with a clear understanding of these methodologies, enabling them to swiftly identify appropriate data generation strategies in the construction of LLMs, while providing valuable insights for future exploration.

Miao Peng, Ben Liu, Wenjie Xu et al.

Temporal Knowledge Graph Reasoning (TKGR) is the task of inferring missing facts for incomplete TKGs in complex scenarios (e.g., transductive and inductive settings), which has been gaining increasing attention. Recently, to mitigate dependence on structured connections in TKGs, text-based methods have been developed to utilize rich linguistic information from entity descriptions. However, suffering from the enormous parameters and inflexibility of pre-trained language models, existing text-based methods struggle to balance the textual knowledge and temporal information with computationally expensive purpose-built training strategies. To tap the potential of text-based models for TKGR in various complex scenarios, we propose ChapTER, a Contrastive historical modeling framework with prefix-tuning for TEmporal Reasoning. ChapTER feeds history-contextualized text into the pseudo-Siamese encoders to strike a textual-temporal balance via contrastive estimation between queries and candidates. By introducing virtual time prefix tokens, it applies a prefix-based tuning method to facilitate the frozen PLM capable for TKGR tasks under different settings. We evaluate ChapTER on four transductive and three few-shot inductive TKGR benchmarks, and experimental results demonstrate that ChapTER achieves superior performance compared to competitive baselines with only 0.17% tuned parameters. We conduct thorough analysis to verify the effectiveness, flexibility and efficiency of ChapTER.

Yizhou Jin, Jiahui Zhu, Guodong Wang et al.

Incremental anomaly detection aims to sequentially identify defects in industrial product lines but suffers from catastrophic forgetting, primarily due to knowledge overwriting during parameter updates and feature conflicts between tasks. In this work, We propose ONER (ONline Experience Replay), an end-to-end framework that addresses these issues by synergistically integrating two types of experience: (1) decomposed prompts, which dynamically generate image-conditioned prompts from reusable modules to retain prior knowledge thus prevent knowledge overwriting, and (2) semantic prototypes, which enforce separability in latent feature spaces at pixel and image levels to mitigate cross-task feature conflicts. Extensive experiments demonstrate the superiority of ONER, achieving state-of-the-art performance with +4.4% Pixel AUROC and +28.3% Pixel AUPR improvements on the MVTec AD dataset over prior methods. Remarkably, ONER achieves this with only 0.019M parameters and 5 training epochs per task, confirming its efficiency and stability for real-world industrial deployment.

Team Seedance, Heyi Chen, Siyan Chen et al.

Recent strides in video generation have paved the way for unified audio-visual generation. In this work, we present Seedance 1.5 pro, a foundational model engineered specifically for native, joint audio-video generation. Leveraging a dual-branch Diffusion Transformer architecture, the model integrates a cross-modal joint module with a specialized multi-stage data pipeline, achieving exceptional audio-visual synchronization and superior generation quality. To ensure practical utility, we implement meticulous post-training optimizations, including Supervised Fine-Tuning (SFT) on high-quality datasets and Reinforcement Learning from Human Feedback (RLHF) with multi-dimensional reward models. Furthermore, we introduce an acceleration framework that boosts inference speed by over 10X. Seedance 1.5 pro distinguishes itself through precise multilingual and dialect lip-syncing, dynamic cinematic camera control, and enhanced narrative coherence, positioning it as a robust engine for professional-grade content creation. Seedance 1.5 pro is now accessible on Volcano Engine at https://console.volcengine.com/ark/region:ark+cn-beijing/experience/vision?type=GenVideo.

Jiahui Zhu, Kihyun Yu, Dabeen Lee et al.

Online safe reinforcement learning (RL) plays a key role in dynamic environments, with applications in autonomous driving, robotics, and cybersecurity. The objective is to learn optimal policies that maximize rewards while satisfying safety constraints modeled by constrained Markov decision processes (CMDPs). Existing methods achieve sublinear regret under stochastic constraints but often fail in adversarial settings, where constraints are unknown, time-varying, and potentially adversarially designed. In this paper, we propose the Optimistic Mirror Descent Primal-Dual (OMDPD) algorithm, the first to address online CMDPs with anytime adversarial constraints. OMDPD achieves optimal regret O(sqrt(K)) and strong constraint violation O(sqrt(K)) without relying on Slater's condition or the existence of a strictly known safe policy. We further show that access to accurate estimates of rewards and transitions can further improve these bounds. Our results offer practical guarantees for safe decision-making in adversarial environments.

Yicheng Deng, Cheng Sun, Jiahui Zhu et al.

Recovering 3D human pose from 2D joints is still a challenging problem, especially without any 3D annotation, video information, or multi-view information. In this paper, we present an unsupervised GAN-based model consisting of multiple weight-sharing generators to estimate a 3D human pose from a single image without 3D annotations. In our model, we introduce single-view-multi-angle consistency (SVMAC) to significantly improve the estimation performance. With 2D joint locations as input, our model estimates a 3D pose and a camera simultaneously. During training, the estimated 3D pose is rotated by random angles and the estimated camera projects the rotated 3D poses back to 2D. The 2D reprojections will be fed into weight-sharing generators to estimate the corresponding 3D poses and cameras, which are then mixed to impose SVMAC constraints to self-supervise the training process. The experimental results show that our method outperforms the state-of-the-art unsupervised methods on Human 3.6M and MPI-INF-3DHP. Moreover, qualitative results on MPII and LSP show that our method can generalize well to unknown data.

Yicheng Deng, Cheng Sun, Yongqi Sun et al.

3D human pose estimation from a single image is still a challenging problem despite the large amount of work that has been performed in this field. Generally, most methods directly use neural networks and ignore certain constraints (e.g., reprojection constraints, joint angle, and bone length constraints). While a few methods consider these constraints but train the network separately, they cannot effectively solve the depth ambiguity problem. In this paper, we propose a GAN-based model for 3D human pose estimation, in which a reprojection network is employed to learn the mapping of the distribution from 3D poses to 2D poses, and a discriminator is employed for 2D-3D consistency discrimination. We adopt a novel strategy to synchronously train the generator, the reprojection network and the discriminator. Furthermore, inspired by the typical kinematic chain space (KCS) matrix, we introduce a weighted KCS matrix and take it as one of the discriminator's inputs to impose joint angle and bone length constraints. The experimental results on Human3.6M show that our method significantly outperforms state-of-the-art methods in most cases.