Yan Zhou

Qingkai Fang, Shoutao Guo, Yan Zhou et al.

Models like GPT-4o enable real-time interaction with large language models (LLMs) through speech, significantly enhancing user experience compared to traditional text-based interaction. However, there is still a lack of exploration on how to build speech interaction models based on open-source LLMs. To address this, we propose LLaMA-Omni, a novel model architecture designed for low-latency and high-quality speech interaction with LLMs. LLaMA-Omni integrates a pretrained speech encoder, a speech adaptor, an LLM, and a streaming speech decoder. It eliminates the need for speech transcription, and can simultaneously generate text and speech responses directly from speech instructions with extremely low latency. We build our model based on the latest Llama-3.1-8B-Instruct model. To align the model with speech interaction scenarios, we construct a dataset named InstructS2S-200K, which includes 200K speech instructions and corresponding speech responses. Experimental results show that compared to previous speech-language models, LLaMA-Omni provides better responses in both content and style, with a response latency as low as 226ms. Additionally, training LLaMA-Omni takes less than 3 days on just 4 GPUs, paving the way for the efficient development of speech-language models in the future.

Yan Zhou, Qingkai Fang, Yun Hong et al.

Currently, large language models (LLMs) predominantly focus on the text modality. To enable more natural human-AI interaction, speech LLMs are emerging, but building effective end-to-end speech LLMs remains challenging due to limited data and the difficulty in expanding to more languages. In this paper, we introduce Cross-lingual Speech Language Model (CSLM), an efficient training method for cross-lingual speech LLMs based on discrete speech tokens. We propose a novel alignment strategy that achieves cross-modal and cross-lingual alignment through continual pre-training. By conducting instruction fine-tuning following a speech-text interleaved chain-of-modality generation process, we enhance modal alignment at a finer granularity, thereby improving generation quality and reducing latency. CSLM aligns different modalities and languages simultaneously without the need for massive speech data, thus exhibiting good language scalability. Evaluations on cross-modal tasks, mono-lingual conversational tasks, and cross-lingual conversational tasks demonstrate CSLM's strong cross-modal alignment capabilities and general task abilities. (Code is available at: https://github.com/ictnlp/CSLM)

Chen hao, Xie Runfeng, Cui Xiangyang et al.

Accurately recommending candidate news articles to users is a basic challenge faced by personalized news recommendation systems. Traditional methods are usually difficult to grasp the complex semantic information in news texts, resulting in unsatisfactory recommendation results. Besides, these traditional methods are more friendly to active users with rich historical behaviors. However, they can not effectively solve the "long tail problem" of inactive users. To address these issues, this research presents a novel general framework that combines Large Language Models (LLM) and Knowledge Graphs (KG) into semantic representations of traditional methods. In order to improve semantic understanding in complex news texts, we use LLMs' powerful text understanding ability to generate news representations containing rich semantic information. In addition, our method combines the information about news entities and mines high-order structural information through multiple hops in KG, thus alleviating the challenge of long tail distribution. Experimental results demonstrate that compared with various traditional models, the framework significantly improves the recommendation effect. The successful integration of LLM and KG in our framework has established a feasible path for achieving more accurate personalized recommendations in the news field. Our code is available at https://github.com/Xuan-ZW/LKPNR.

Pierre Del Moral, Ajay Jasra, Kody Law et al.

This article considers the sequential Monte Carlo (SMC) approximation of ratios of normalizing constants associated to posterior distributions which in principle rely on continuum models. Therefore, the Monte Carlo estimation error and the discrete approximation error must be balanced. A multilevel strategy is utilized to substantially reduce the cost to obtain a given error level in the approximation as compared to standard estimators. Two estimators are considered and relative variance bounds are given. The theoretical results are numerically illustrated for the example of identifying a parametrized permeability in an elliptic equation given point-wise observations of the pressure.

Shaolei Zhang, Qingkai Fang, Zhuocheng Zhang et al.

Large language models (LLMs) have demonstrated remarkable prowess in language understanding and generation. Advancing from foundation LLMs to instructionfollowing LLMs, instruction tuning plays a vital role in aligning LLMs to human preferences. However, the existing LLMs are usually focused on English, leading to inferior performance in non-English languages. In order to improve the performance for non-English languages, it is necessary to collect language-specific training data for foundation LLMs and construct language-specific instructions for instruction tuning, both of which are heavy loads. To minimize human workload, we propose to transfer the capabilities of language generation and instruction following from English to other languages through an interactive translation task. We have developed BayLing, an instruction-following LLM by utilizing LLaMA as the foundation LLM and automatically constructing interactive translation instructions for instructing tuning. Extensive assessments demonstrate that BayLing achieves comparable performance to GPT-3.5-turbo, despite utilizing a considerably smaller parameter size of only 13 billion. Experimental results on translation tasks show that BayLing achieves 95% of single-turn translation capability compared to GPT-4 with automatic evaluation and 96% of interactive translation capability compared to GPT-3.5-turbo with human evaluation. To estimate the performance on general tasks, we created a multi-turn instruction test set called BayLing-80. The experimental results on BayLing-80 indicate that BayLing achieves 89% of performance compared to GPT-3.5-turbo. BayLing also demonstrates outstanding performance on knowledge assessment of Chinese GaoKao and English SAT, second only to GPT-3.5-turbo among a multitude of instruction-following LLMs. Demo, homepage, code and models of BayLing are available.

Chang'an Yi, Haotian Chen, Yifan Zhang et al.

Test-time adaptation (TTA) aims to adapt a model, initially trained on training data, to test data with potential distribution shifts. Most existing TTA methods focus on classification problems. The pronounced success of classification might lead numerous newcomers and engineers to assume that classic TTA techniques can be directly applied to the more challenging task of semantic segmentation. However, this belief is still an open question. In this paper, we investigate the applicability of existing classic TTA strategies in semantic segmentation. Our comprehensive results have led to three key observations. First, the classic normalization updating strategy only brings slight performance improvement, and in some cases, it might even adversely affect the results. Even with the application of advanced distribution estimation techniques like batch renormalization, the problem remains unresolved. Second, although the teacher-student scheme does enhance the training stability for segmentation TTA in the presence of noisy pseudo-labels and temporal correlation, it cannot directly result in performance improvement compared to the original model without TTA under complex data distribution. Third, segmentation TTA suffers a severe long-tailed class-imbalance problem, which is substantially more complex than that in TTA for classification. This long-tailed challenge negatively affects segmentation TTA performance, even when the accuracy of pseudo-labels is high. Besides those observations, we find that visual prompt tuning (VisPT) is promising in segmentation TTA and propose a novel method named TTAP. The outstanding performance of TTAP has also been verified. We hope the community can give more attention to this challenging, yet important, segmentation TTA task in the future. The source code is available at: \textit{https://github.com/ycarobot/TTAP

Jiehui Huang, Yuechen Zhang, Xu He et al.

Recent video generation models demonstrate impressive synthesis capabilities but remain limited by single-modality conditioning, constraining their holistic world understanding. This stems from insufficient cross-modal interaction and limited modal diversity for comprehensive world knowledge representation. To address these limitations, we introduce UnityVideo, a unified framework for world-aware video generation that jointly learns across multiple modalities (segmentation masks, human skeletons, DensePose, optical flow, and depth maps) and training paradigms. Our approach features two core components: (1) dynamic noising to unify heterogeneous training paradigms, and (2) a modality switcher with an in-context learner that enables unified processing via modular parameters and contextual learning. We contribute a large-scale unified dataset with 1.3M samples. Through joint optimization, UnityVideo accelerates convergence and significantly enhances zero-shot generalization to unseen data. We demonstrate that UnityVideo achieves superior video quality, consistency, and improved alignment with physical world constraints. Code and data can be found at: https://github.com/dvlab-research/UnityVideo

Yuyao Wang, Zhongjian Zhang, Mo Chi et al.

Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution. However, memory is also essential for agents, as it enables them to store, update, and retrieve information over time. This ability remains under-evaluated, largely because existing benchmarks do not provide a systematic way to assess memory mechanisms. In this paper, we study agent memory from a self-evolving perspective and introduce EvoMemBench, a unified benchmark organized along two axes: memory scope (in-episode vs. cross-episode) and memory content (knowledge-oriented vs. execution-oriented). We compare 15 representative memory methods with strong long-context baselines under a standardized protocol. Results show that current memory systems are still far from a general solution: long-context baselines remain highly competitive, memory helps most when the current context is insufficient or tasks are difficult, and no single memory form works consistently across all settings. Retrieval-based methods remain strong for knowledge-intensive settings, whereas procedural and long-term memory methods are more effective for execution-oriented tasks when their stored experience matches the task structure. We hope EvoMemBench facilitates future research on more effective memory systems for LLM-based agents. Our code is available at https://github.com/DSAIL-Memory/EvoMemBench.

Jie Guo, Meiting Wang, Yan Zhou et al.

Image-text retrieval (ITR) is a challenging task in the field of multimodal information processing due to the semantic gap between different modalities. In recent years, researchers have made great progress in exploring the accurate alignment between image and text. However, existing works mainly focus on the fine-grained alignment between image regions and sentence fragments, which ignores the guiding significance of context background information. Actually, integrating the local fine-grained information and global context background information can provide more semantic clues for retrieval. In this paper, we propose a novel Hierarchical Graph Alignment Network (HGAN) for image-text retrieval. First, to capture the comprehensive multimodal features, we construct the feature graphs for the image and text modality respectively. Then, a multi-granularity shared space is established with a designed Multi-granularity Feature Aggregation and Rearrangement (MFAR) module, which enhances the semantic corresponding relations between the local and global information, and obtains more accurate feature representations for the image and text modalities. Finally, the ultimate image and text features are further refined through three-level similarity functions to achieve the hierarchical alignment. To justify the proposed model, we perform extensive experiments on MS-COCO and Flickr30K datasets. Experimental results show that the proposed HGAN outperforms the state-of-the-art methods on both datasets, which demonstrates the effectiveness and superiority of our model.

Kling Team, Jialu Chen, Yikang Ding et al.

Character animation aims to generate lifelike videos by transferring motion dynamics from a driving video to a reference image. Recent strides in generative models have paved the way for high-fidelity character animation. In this work, we present Kling-MotionControl, a unified DiT-based framework engineered specifically for robust, precise, and expressive holistic character animation. Leveraging a divide-and-conquer strategy within a cohesive system, the model orchestrates heterogeneous motion representations tailored to the distinct characteristics of body, face, and hands, effectively reconciling large-scale structural stability with fine-grained articulatory expressiveness. To ensure robust cross-identity generalization, we incorporate adaptive identity-agnostic learning, facilitating natural motion retargeting for diverse characters ranging from realistic humans to stylized cartoons. Simultaneously, we guarantee faithful appearance preservation through meticulous identity injection and fusion designs, further supported by a subject library mechanism that leverages comprehensive reference contexts. To ensure practical utility, we implement an advanced acceleration framework utilizing multi-stage distillation, boosting inference speed by over 10x. Kling-MotionControl distinguishes itself through intelligent semantic motion understanding and precise text responsiveness, allowing for flexible control beyond visual inputs. Human preference evaluations demonstrate that Kling-MotionControl delivers superior performance compared to leading commercial and open-source solutions, achieving exceptional fidelity in holistic motion control, open domain generalization, and visual quality and coherence. These results establish Kling-MotionControl as a robust solution for high-quality, controllable, and lifelike character animation.

Laura R. Marusich, Jonathan Z. Bakdash, Yan Zhou et al.

AI Uncertainty Quantification (UQ) has the potential to improve human decision-making beyond AI predictions alone by providing additional probabilistic information to users. The majority of past research on AI and human decision-making has concentrated on model explainability and interpretability, with little focus on understanding the potential impact of UQ on human decision-making. We evaluated the impact on human decision-making for instance-level UQ, calibrated using a strict scoring rule, in two online behavioral experiments. In the first experiment, our results showed that UQ was beneficial for decision-making performance compared to only AI predictions. In the second experiment, we found UQ had generalizable benefits for decision-making across a variety of representations for probabilistic information. These results indicate that implementing high quality, instance-level UQ for AI may improve decision-making with real systems compared to AI predictions alone.

Mianxin Liu, Jingyang Zhang, Yao Wang et al.

Brain disorders in the early and late life of humans potentially share pathological alterations in brain functions. However, the key evidence from neuroimaging data for pathological commonness remains unrevealed. To explore this hypothesis, we build a deep learning model, using multi-site functional magnetic resonance imaging data (N=4,410, 6 sites), for classifying 5 different brain disorders from healthy controls, with a set of common features. Our model achieves 62.6(1.9)% overall classification accuracy on data from the 6 investigated sites and detects a set of commonly affected functional subnetworks at different spatial scales, including default mode, executive control, visual, and limbic networks. In the deep-layer feature representation for individual data, we observe young and aging patients with disorders are continuously distributed, which is in line with the clinical concept of the "spectrum of disorders". The revealed spectrum underlying early- and late-life brain disorders promotes the understanding of disorder comorbidities in the lifespan.

Qingkai Fang, Yan Zhou, Yang Feng

Direct speech-to-speech translation (S2ST) translates speech from one language into another using a single model. However, due to the presence of linguistic and acoustic diversity, the target speech follows a complex multimodal distribution, posing challenges to achieving both high-quality translations and fast decoding speeds for S2ST models. In this paper, we propose DASpeech, a non-autoregressive direct S2ST model which realizes both fast and high-quality S2ST. To better capture the complex distribution of the target speech, DASpeech adopts the two-pass architecture to decompose the generation process into two steps, where a linguistic decoder first generates the target text, and an acoustic decoder then generates the target speech based on the hidden states of the linguistic decoder. Specifically, we use the decoder of DA-Transformer as the linguistic decoder, and use FastSpeech 2 as the acoustic decoder. DA-Transformer models translations with a directed acyclic graph (DAG). To consider all potential paths in the DAG during training, we calculate the expected hidden states for each target token via dynamic programming, and feed them into the acoustic decoder to predict the target mel-spectrogram. During inference, we select the most probable path and take hidden states on that path as input to the acoustic decoder. Experiments on the CVSS Fr-En benchmark demonstrate that DASpeech can achieve comparable or even better performance than the state-of-the-art S2ST model Translatotron 2, while preserving up to 18.53x speedup compared to the autoregressive baseline. Compared with the previous non-autoregressive S2ST model, DASpeech does not rely on knowledge distillation and iterative decoding, achieving significant improvements in both translation quality and decoding speed. Furthermore, DASpeech shows the ability to preserve the speaker's voice of the source speech during translation.

Jinchuan Zhang, Yan Zhou, Yaxin Liu et al.

Automated red teaming is an effective method for identifying misaligned behaviors in large language models (LLMs). Existing approaches, however, often focus primarily on improving attack success rates while overlooking the need for comprehensive test case coverage. Additionally, most of these methods are limited to single-turn red teaming, failing to capture the multi-turn dynamics of real-world human-machine interactions. To overcome these limitations, we propose HARM (Holistic Automated Red teaMing), which scales up the diversity of test cases using a top-down approach based on an extensible, fine-grained risk taxonomy. Our method also leverages a novel fine-tuning strategy and reinforcement learning techniques to facilitate multi-turn adversarial probing in a human-like manner. Experimental results demonstrate that our framework enables a more systematic understanding of model vulnerabilities and offers more targeted guidance for the alignment process.

Hongmei Zhang, Kai Wang, Yan Zhou et al.

Objective: Estimation of the global optima of multiple model parameters is valuable in imaging to form a reliable diagnostic image. Given non convexity of the objective function, it is challenging to avoid from different local minima. Methods: We first formulate the global searching of multiply parameters to be a k-D move in the parametric space, and convert parameters updating to be state-action decision-making problem. We proposed a novel Deep Q-learning of Model Parameters (DQMP) method for global optimization of model parameters by updating the parameter configurations through actions that maximize a Q-value, which employs a Deep Reward Network designed to learn global reward values from both visible curve fitting errors and hidden parameter errors. Results: The DQMP method was evaluated by viscoelastic imaging on soft matter by Kelvin-Voigt fractional derivative (KVFD) modeling. In comparison to other methods, imaging of parameters by DQMP yielded the smallest errors (< 2%) to the ground truth images. DQMP was applied to viscoelastic imaging on biological tissues, which indicated a great potential of imaging on physical parameters in diagnostic applications. Conclusions: DQMP method is able to achieve global optima, yielding accurate model parameter estimates in viscoelastic imaging. Assessment of DQMP by simulation imaging and ultrasound breast imaging demonstrated the consistency, reliability of the imaged parameters, and powerful global searching ability of DQMP. Significance: DQMP method is promising for imaging of multiple parameters, and can be generalized to global optimization for many other complex nonconvex functions and imaging of physical parameters.

Kling Team, Jialu Chen, Yuanzheng Ci et al.

We present Kling-Omni, a generalist generative framework designed to synthesize high-fidelity videos directly from multimodal visual language inputs. Adopting an end-to-end perspective, Kling-Omni bridges the functional separation among diverse video generation, editing, and intelligent reasoning tasks, integrating them into a holistic system. Unlike disjointed pipeline approaches, Kling-Omni supports a diverse range of user inputs, including text instructions, reference images, and video contexts, processing them into a unified multimodal representation to deliver cinematic-quality and highly-intelligent video content creation. To support these capabilities, we constructed a comprehensive data system that serves as the foundation for multimodal video creation. The framework is further empowered by efficient large-scale pre-training strategies and infrastructure optimizations for inference. Comprehensive evaluations reveal that Kling-Omni demonstrates exceptional capabilities in in-context generation, reasoning-based editing, and multimodal instruction following. Moving beyond a content creation tool, we believe Kling-Omni is a pivotal advancement toward multimodal world simulators capable of perceiving, reasoning, generating and interacting with the dynamic and complex worlds.

Shuzhan Wang, Ruxue Jiang, Zhaoqi Wang et al.

Computer network anomaly detection and log analysis, as an important topic in the field of network security, has been a key task to ensure network security and system reliability. First, existing network anomaly detection and log analysis methods are often challenged by high-dimensional data and complex network topologies, resulting in unstable performance and high false-positive rates. In addition, traditional methods are usually difficult to handle time-series data, which is crucial for anomaly detection and log analysis. Therefore, we need a more efficient and accurate method to cope with these problems. To compensate for the shortcomings of current methods, we propose an innovative fusion model that integrates Isolation Forest, GAN (Generative Adversarial Network), and Transformer with each other, and each of them plays a unique role. Isolation Forest is used to quickly identify anomalous data points, and GAN is used to generate synthetic data with the real data distribution characteristics to augment the training dataset, while the Transformer is used for modeling and context extraction on time series data. The synergy of these three components makes our model more accurate and robust in anomaly detection and log analysis tasks. We validate the effectiveness of this fusion model in an extensive experimental evaluation. Experimental results show that our model significantly improves the accuracy of anomaly detection while reducing the false alarm rate, which helps to detect potential network problems in advance. The model also performs well in the log analysis task and is able to quickly identify anomalous behaviors, which helps to improve the stability of the system. The significance of this study is that it introduces advanced deep learning techniques, which work anomaly detection and log analysis.

Xiaowei Wu, Shengyun Wei, Yan Zhou

Currently, deep learning methods with stacking small size convolutional filters are widely used for automatic modulation classification (AMC). In this report, we find some experienced improvements by using large kernel size for convolutional deep convolution neural network based AMC, which is more efficient in extracting multi-scale features of the raw signal I/Q sequence data. Also, Squeeze-and-Excitation (SE) mechanisms can significantly help AMC networks to focus on the more important features of the signal. As a result, we propose a multi-scale feature network with large kernel size and SE mechanism (SE-MSFN) in this paper. SE-MSFN achieves state-of-the-art classification performance on the public well-known RADIOML 2018.01A dataset, with average classification accuracy of 64.50%, surpassing CLDNN by 1.42%, maximum classification accuracy of 98.5%, and an average classification accuracy of 85.53% in the lower SNR range 0dB to 10dB, surpassing CLDNN by 2.85%. In addition, we also verified that ensemble learning can help further improve classification performance. We hope this report can provide some references for developers and researchers in practical scenes.

Lijuan Wang, Yijia Hu, Yan Zhou

In the context of global trade, cross-border commodity pricing largely determines the competitiveness and market share of businesses. However, existing methodologies often prove inadequate, as they lack the agility and precision required to effectively respond to the dynamic international markets. Time series data is of great significance in commodity pricing and can reveal market dynamics and trends. Therefore, we propose a new method based on the hybrid neural network model CNN-BiGRU-SSA. The goal is to achieve accurate prediction and optimization of cross-border commodity pricing strategies through in-depth analysis and optimization of time series data. Our model undergoes experimental validation across multiple datasets. The results show that our method achieves significant performance advantages on datasets such as UNCTAD, IMF, WITS and China Customs. For example, on the UNCTAD dataset, our model reduces MAE to 4.357, RMSE to 5.406, and R2 to 0.961, significantly better than other models. On the IMF and WITS datasets, our method also achieves similar excellent performance. These experimental results verify the effectiveness and reliability of our model in the field of cross-border commodity pricing. Overall, this study provides an important reference for enterprises to formulate more reasonable and effective cross-border commodity pricing strategies, thereby enhancing market competitiveness and profitability. At the same time, our method also lays a foundation for the application of deep learning in the fields of international trade and economic strategy optimization, which has important theoretical and practical significance.

Shaolei Zhang, Kehao Zhang, Qingkai Fang et al.

Large language models (LLMs), with their powerful generative capabilities and vast knowledge, empower various tasks in everyday life. However, these abilities are primarily concentrated in high-resource languages, leaving low-resource languages with weaker generative capabilities and relatively limited knowledge. Enhancing the multilingual capabilities of LLMs is therefore crucial for serving over 100 linguistic communities worldwide. An intuitive approach to enhance the multilingual capabilities would be to construct instruction data for various languages, but constructing instruction data for over 100 languages is prohibitively costly. In this paper, we introduce BayLing 2, which efficiently transfers generative capabilities and knowledge from high-resource languages to low-resource languages through language alignment. To achieve this, we constructed a dataset of 3.2 million instructions, comprising high-resource language instructions (Chinese and English) and cross-lingual instructions for 100+ languages and performed instruction tuning based on the dataset to facilitate the capability transfer between languages. Using Llama as the foundation model, we developed BayLing-2-7B, BayLing-2-13B, and BayLing-2-8B, and conducted a comprehensive evaluation of BayLing. For multilingual translation across 100+ languages, BayLing shows superior performance compared to open-source models of similar scale. For multilingual knowledge and understanding benchmarks, BayLing achieves significant improvements across over 20 low-resource languages, demonstrating its capability of effective knowledge transfer from high-resource to low-resource languages. Furthermore, results on English benchmarks indicate that BayLing maintains high performance in highresource languages while enhancing the performance in low-resource languages. Demo, homepage, code and models of BayLing are available.

Jingping Liu, Ziyan Liu, Zhedong Cen et al.

Spatial relation reasoning is a crucial task for multimodal large language models (MLLMs) to understand the objective world. However, current benchmarks have issues like relying on bounding boxes, ignoring perspective substitutions, or allowing questions to be answered using only the model's prior knowledge without image understanding. To address these issues, we introduce SpatialMQA, a human-annotated spatial relation reasoning benchmark based on COCO2017, which enables MLLMs to focus more on understanding images in the objective world. To ensure data quality, we design a well-tailored annotation procedure, resulting in SpatialMQA consisting of 5,392 samples. Based on this benchmark, a series of closed- and open-source MLLMs are implemented and the results indicate that the current state-of-the-art MLLM achieves only 48.14% accuracy, far below the human-level accuracy of 98.40%. Extensive experimental analyses are also conducted, suggesting the future research directions. The benchmark and codes are available at https://github.com/ziyan-xiaoyu/SpatialMQA.git.

Yihong Luo, Yuhan Chen, Siya Qiu et al.

Graph Neural Networks (GNNs) have shown superior performance in node classification. However, GNNs perform poorly in the Few-Shot Node Classification (FSNC) task that requires robust generalization to make accurate predictions for unseen classes with limited labels. To tackle the challenge, we propose the integration of Sharpness-Aware Minimization (SAM)--a technique designed to enhance model generalization by finding a flat minimum of the loss landscape--into GNN training. The standard SAM approach, however, consists of two forward-backward steps in each training iteration, doubling the computational cost compared to the base optimizer (e.g., Adam). To mitigate this drawback, we introduce a novel algorithm, Fast Graph Sharpness-Aware Minimization (FGSAM), that integrates the rapid training of Multi-Layer Perceptrons (MLPs) with the superior performance of GNNs. Specifically, we utilize GNNs for parameter perturbation while employing MLPs to minimize the perturbed loss so that we can find a flat minimum with good generalization more efficiently. Moreover, our method reutilizes the gradient from the perturbation phase to incorporate graph topology into the minimization process at almost zero additional cost. To further enhance training efficiency, we develop FGSAM+ that executes exact perturbations periodically. Extensive experiments demonstrate that our proposed algorithm outperforms the standard SAM with lower computational costs in FSNC tasks. In particular, our FGSAM+ as a SAM variant offers a faster optimization than the base optimizer in most cases. In addition to FSNC, our proposed methods also demonstrate competitive performance in the standard node classification task for heterophilic graphs, highlighting the broad applicability. The code is available at https://github.com/draym28/FGSAM_NeurIPS24.

Ming Chen, Yan Zhou, Weihua Jian et al.

Though significant progress in human pose and shape recovery from monocular RGB images has been made in recent years, obtaining 3D human motion with high accuracy and temporal consistency from videos remains challenging. Existing video-based methods tend to reconstruct human motion from global image features, which lack detailed representation capability and limit the reconstruction accuracy. In this paper, we propose a Temporal-Aware Refining Network (TAR), to synchronously explore temporal-aware global and local image features for accurate pose and shape recovery. First, a global transformer encoder is introduced to obtain temporal global features from static feature sequences. Second, a bidirectional ConvGRU network takes the sequence of high-resolution feature maps as input, and outputs temporal local feature maps that maintain high resolution and capture the local motion of the human body. Finally, a recurrent refinement module iteratively updates estimated SMPL parameters by leveraging both global and local temporal information to achieve accurate and smooth results. Extensive experiments demonstrate that our TAR obtains more accurate results than previous state-of-the-art methods on popular benchmarks, i.e., 3DPW, MPI-INF-3DHP, and Human3.6M.

Jinchuan Zhang, Lu Yin, Yan Zhou et al.

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous work has shown that current LLM-based agents execute numerous malicious tasks even without being attacked, indicating a deficiency in agentic use safety alignment during the post-training phase. To address this gap, we propose AgentAlign, a novel framework that leverages abstract behavior chains as a medium for safety alignment data synthesis. By instantiating these behavior chains in simulated environments with diverse tool instances, our framework enables the generation of highly authentic and executable instructions while capturing complex multi-step dynamics. The framework further ensures model utility by proportionally synthesizing benign instructions through non-malicious interpretations of behavior chains, precisely calibrating the boundary between helpfulness and harmlessness. Evaluation results on AgentHarm demonstrate that fine-tuning three families of open-source models using our method substantially improves their safety (35.8% to 79.5% improvement) while minimally impacting or even positively enhancing their helpfulness, outperforming various prompting methods. The dataset and code have both been open-sourced.

Shaohua Pan, Xinyu Yi, Yan Zhou et al.

Combining sparse IMUs and a monocular camera is a new promising setting to perform real-time human motion capture. This paper proposes a diffusion-based solution to learn human motion priors and fuse the two modalities of signals together seamlessly in a unified framework. By delicately considering the characteristics of the two signals, the sequential visual information is considered as a whole and transformed into a condition embedding, while the inertial measurement is concatenated with the noisy body pose frame by frame to construct a sequential input for the diffusion model. Firstly, we observe that the visual information may be unavailable in some frames due to occlusions or subjects moving out of the camera view. Thus incorporating the sequential visual features as a whole to get a single feature embedding is robust to the occasional degenerations of visual information in those frames. On the other hand, the IMU measurements are robust to occlusions and always stable when signal transmission has no problem. So incorporating them frame-wisely could better explore the temporal information for the system. Experiments have demonstrated the effectiveness of the system design and its state-of-the-art performance in pose estimation compared with the previous works. Our codes are available for research at https://shaohua-pan.github.io/diffcap-page.

Ravi Raj Shrestha, Zhi Zhou, Limon Barua et al.

The anticipated widespread adoption of electric vehicles (EVs) necessitates a critical evaluation of existing power distribution infrastructures, as EV integration imposes additional stress on distribution networks that can lead to component overloading and power quality degradation. Implementing smart charging mechanisms can mitigate these adverse effects and defer or even avoid upgrades. This study assesses the performance of two smart charging strategies - Time of Use (TOU) pricing and Load Balancing (LB) on seven representative real-world feeders identified using k-means clustering. A time series-based steady-state load flow analysis was conducted on these feeders to simulate the impact of EV charging under both strategies across four different EV enrollment scenarios and three representative days to capture seasonal load characteristics. A grid upgrade strategy has been proposed to strengthen the power grid to support EV integration with minimal cost. Results demonstrate that both TOU and LB strategies effectively manage the additional EV load with reduced upgrade requirement and cost to existing infrastructure compared to the case without smart charging strategies and LB outperforms TOU when the customer enrollment levels are high. These findings support the viability of smart charging in facilitating EV integration while maintaining distribution network reliability and reducing investment cost.

Kling Team, Jialu Chen, Yikang Ding et al.

Avatar video generation models have achieved remarkable progress in recent years. However, prior work exhibits limited efficiency in generating long-duration high-resolution videos, suffering from temporal drifting, quality degradation, and weak prompt following as video length increases. To address these challenges, we propose KlingAvatar 2.0, a spatio-temporal cascade framework that performs upscaling in both spatial resolution and temporal dimension. The framework first generates low-resolution blueprint video keyframes that capture global semantics and motion, and then refines them into high-resolution, temporally coherent sub-clips using a first-last frame strategy, while retaining smooth temporal transitions in long-form videos. To enhance cross-modal instruction fusion and alignment in extended videos, we introduce a Co-Reasoning Director composed of three modality-specific large language model (LLM) experts. These experts reason about modality priorities and infer underlying user intent, converting inputs into detailed storylines through multi-turn dialogue. A Negative Director further refines negative prompts to improve instruction alignment. Building on these components, we extend the framework to support ID-specific multi-character control. Extensive experiments demonstrate that our model effectively addresses the challenges of efficient, multimodally aligned long-form high-resolution video generation, delivering enhanced visual clarity, realistic lip-teeth rendering with accurate lip synchronization, strong identity preservation, and coherent multimodal instruction following.

Chang'an Yi, Xiaohui Deng, Shuaicheng Niu et al.

Test-time adaptation (TTA) aims to transfer knowledge from a source model to unknown test data with potential distribution shifts in an online manner. Many existing TTA methods rely on entropy as a confidence metric to optimize the model. However, these approaches are sensitive to the predefined entropy threshold, influencing which samples are chosen for model adaptation. Consequently, potentially reliable target samples are often overlooked and underutilized. For instance, a sample's entropy might slightly exceed the threshold initially, but fall below it after the model is updated. Such samples can provide stable supervised information and offer a normal range of gradients to guide model adaptation. In this paper, we propose a general approach, \underline{POEM}, to promote TTA via ex\underline{\textbf{p}}loring the previously unexpl\underline{\textbf{o}}red reliabl\underline{\textbf{e}} sa\underline{\textbf{m}}ples. Additionally, we introduce an extra Adapt Branch network to strike a balance between extracting domain-agnostic representations and achieving high performance on target data. Comprehensive experiments across multiple architectures demonstrate that POEM consistently outperforms existing TTA methods in both challenging scenarios and real-world domain shifts, while remaining computationally efficient. The effectiveness of POEM is evaluated through extensive analyses and thorough ablation studies. Moreover, the core idea behind POEM can be employed as an augmentation strategy to boost the performance of existing TTA approaches. The source code is publicly available at \emph{https://github.com/ycarobot/POEM}

Chang'an Yi, Xiaohui Deng, Guohao Chen et al.

Test-time Adaptation (TTA) adapts a given model to testing domain data with potential domain shifts through online unsupervised learning, yielding impressive performance. However, to date, existing TTA methods primarily focus on single-model adaptation. In this work, we investigate an intriguing question: how does cross-model knowledge influence the TTA process? Our findings reveal that, in TTA's unsupervised online setting, each model can provide complementary, confident knowledge to the others, even when there are substantial differences in model size. For instance, a smaller model like MobileViT (10.6M parameters) can effectively guide a larger model like ViT-Base (86.6M parameters). In light of this, we propose COCA, a Cross-Model Co-Learning framework for TTA, which mainly consists of two main strategies. 1) Co-adaptation adaptively integrates complementary knowledge from other models throughout the TTA process, reducing individual model biases. 2) Self-adaptation enhances each model's unique strengths via unsupervised learning, enabling diverse adaptation to the target domain. Extensive experiments show that COCA, which can also serve as a plug-and-play module, significantly boosts existing SOTAs, on models with various sizes--including ResNets, ViTs, and Mobile-ViTs--via cross-model co-learned TTA. For example, with Mobile-ViT's guidance, COCA raises ViT-Base's average adaptation accuracy on ImageNet-C from 51.7% to 64.5%. The code is publicly available at https://github.com/ycarobot/COCA.

Yan Zhou, Qingkai Fang, Yang Feng

End-to-end speech translation (ST) is the task of translating speech signals in the source language into text in the target language. As a cross-modal task, end-to-end ST is difficult to train with limited data. Existing methods often try to transfer knowledge from machine translation (MT), but their performances are restricted by the modality gap between speech and text. In this paper, we propose Cross-modal Mixup via Optimal Transport CMOT to overcome the modality gap. We find the alignment between speech and text sequences via optimal transport and then mix up the sequences from different modalities at a token level using the alignment. Experiments on the MuST-C ST benchmark demonstrate that CMOT achieves an average BLEU of 30.0 in 8 translation directions, outperforming previous methods. Further analysis shows CMOT can adaptively find the alignment between modalities, which helps alleviate the modality gap between speech and text. Code is publicly available at https://github.com/ictnlp/CMOT.

Yaowen Huang, Jun Der Leu, Baoli Lu et al.

Risk analysis is an important business decision support task in customer relationship management (CRM), involving the identification of potential risks or challenges that may affect customer satisfaction, retention rates, and overall business performance. To enhance risk analysis in CRM, this paper combines the advantages of quantile region convolutional neural network-long short-term memory (QRCNN-LSTM) and cross-attention mechanisms for modeling. The QRCNN-LSTM model combines sequence modeling with deep learning architectures commonly used in natural language processing tasks, enabling the capture of both local and global dependencies in sequence data. The cross-attention mechanism enhances interactions between different input data parts, allowing the model to focus on specific areas or features relevant to CRM risk analysis. By applying QRCNN-LSTM and cross-attention mechanisms to CRM risk analysis, empirical evidence demonstrates that this approach can effectively identify potential risks and provide data-driven support for business decisions.

Yun Hong, Yan Zhou, Yang Feng

Empathy is essential for fostering natural interactions in spoken dialogue systems, as it enables machines to recognize the emotional tone of human speech and deliver empathetic responses. Recent research has made significant progress in developing empathetic spoken chatbots based on large language models (LLMs). However, several challenges still exist when training such models, including reliance on costly empathetic speech instruction data and a lack of emotional expressiveness in the generated speech. Finetuning LLM with cross-modal empathetic instruction data may also lead to catastrophic forgetting and a degradation of its general capability. To address these challenges, we propose FreezeEmpath, an end-to-end empathetic spoken chatbot trained in a simple and efficient manner. The entire training process relies solely on existing speech instruction data and speech emotion recognition (SER) data, while keeping the LLM's parameters frozen. Experiments demonstrate that FreezeEmpath is able to generate emotionally expressive speech and outperforms other empathetic models in empathetic dialogue, SER, and SpokenQA tasks, demonstrating the effectiveness of our training strategy.

Yan Zhou

We identify and prove a fundamental trade-off governing long-sequence models: no model can simultaneously achieve (i) per-step computation independent of sequence length (Efficiency), (ii) state size independent of sequence length (Compactness), and (iii) the ability to recall a number of historical facts proportional to sequence length (Recall). We formalize this trade-off within an Online Sequence Processor abstraction that unifies Transformers, state space models, linear recurrent networks, and their hybrids. Using the Data Processing Inequality and Fano's Inequality, we prove that any model satisfying Efficiency and Compactness can recall at most O(poly(d)/log V) key-value pairs from a sequence of arbitrary length, where d is the model dimension and V is the vocabulary size. We classify 52 architectures published before March 2026 into the triangle, showing that each achieves at most two of the three properties and that hybrid architectures trace continuous trajectories in the interior. Experiments on synthetic associative recall tasks with five representative architectures validate the theoretical bound: empirical recall capacity lies strictly below the information-theoretic limit, and no architecture escapes the triangle.

Cangqing Wang, Mingxiu Sui, Dan Sun et al.

This research delves deeply into Meta Reinforcement Learning (Meta RL) through a exploration focusing on defining generalization limits and ensuring convergence. By employing a approach this article introduces an innovative theoretical framework to meticulously assess the effectiveness and performance of Meta RL algorithms. We present an explanation of generalization limits measuring how well these algorithms can adapt to learning tasks while maintaining consistent results. Our analysis delves into the factors that impact the adaptability of Meta RL revealing the relationship, between algorithm design and task complexity. Additionally we establish convergence assurances by proving conditions under which Meta RL strategies are guaranteed to converge towards solutions. We examine the convergence behaviors of Meta RL algorithms across scenarios providing a comprehensive understanding of the driving forces behind their long term performance. This exploration covers both convergence and real time efficiency offering a perspective, on the capabilities of these algorithms.

Xirui Peng, Qiming Xu, Zheng Feng et al.

This paper explores an automatic news generation and fact-checking system based on language processing, aimed at enhancing the efficiency and quality of news production while ensuring the authenticity and reliability of the news content. With the rapid development of Natural Language Processing (NLP) and deep learning technologies, automatic news generation systems are capable of extracting key information from massive data and generating well-structured, fluent news articles. Meanwhile, by integrating fact-checking technology, the system can effectively prevent the spread of false news and improve the accuracy and credibility of news. This study details the key technologies involved in automatic news generation and factchecking, including text generation, information extraction, and the application of knowledge graphs, and validates the effectiveness of these technologies through experiments. Additionally, the paper discusses the future development directions of automatic news generation and fact-checking systems, emphasizing the importance of further integration and innovation of technologies. The results show that with continuous technological optimization and practical application, these systems will play an increasingly important role in the future news industry, providing more efficient and reliable news services.

Yuan Wang, Di Huang, Yaqi Zhang et al.

Generating lifelike human motions from descriptive texts has experienced remarkable research focus in the recent years, propelled by the emerging requirements of digital humans.Despite impressive advances, existing approaches are often constrained by limited control modalities, task specificity, and focus solely on body motion representations.In this paper, we present MotionGPT-2, a unified Large Motion-Language Model (LMLM) that addresses these limitations. MotionGPT-2 accommodates multiple motion-relevant tasks and supporting multimodal control conditions through pre-trained Large Language Models (LLMs). It quantizes multimodal inputs-such as text and single-frame poses-into discrete, LLM-interpretable tokens, seamlessly integrating them into the LLM's vocabulary. These tokens are then organized into unified prompts, guiding the LLM to generate motion outputs through a pretraining-then-finetuning paradigm. We also show that the proposed MotionGPT-2 is highly adaptable to the challenging 3D holistic motion generation task, enabled by the innovative motion discretization framework, Part-Aware VQVAE, which ensures fine-grained representations of body and hand movements. Extensive experiments and visualizations validate the effectiveness of our method, demonstrating the adaptability of MotionGPT-2 across motion generation, motion captioning, and generalized motion completion tasks.

Yan Zhou, Kevin Hamlen, Michael De Lucia et al.

Machine learning-based intrusion detection requires complex models to capture patterns in high-dimensional, noisy, and class-imbalanced raw network traffic, yet deploying such models remains impractical on resource-constrained devices with limited processing power and memory. In this paper, we present a correlation-aware divide-and-conquer learning technique that decomposes a complex learning problem into smaller, more manageable subproblems. This enables lightweight models as simple as decision trees to be trained on focused subtasks, yielding up to 43.3% higher local accuracy and up to 257 times reduction in model size on real-world network intrusion detection datasets, while also improving adversarial robustness and explainability.

Qingkai Fang, Yan Zhou, Shoutao Guo et al.

Real-time, intelligent, and natural speech interaction is an essential part of the next-generation human-computer interaction. Recent advancements have showcased the potential of building intelligent spoken chatbots based on large language models (LLMs). In this paper, we introduce LLaMA-Omni 2, a series of speech language models (SpeechLMs) ranging from 0.5B to 14B parameters, capable of achieving high-quality real-time speech interaction. LLaMA-Omni 2 is built upon the Qwen2.5 series models, integrating a speech encoder and an autoregressive streaming speech decoder. Despite being trained on only 200K multi-turn speech dialogue samples, LLaMA-Omni 2 demonstrates strong performance on several spoken question answering and speech instruction following benchmarks, surpassing previous state-of-the-art SpeechLMs like GLM-4-Voice, which was trained on millions of hours of speech data.

Te Li, Mengze Zhang, Yan Zhou

Against the backdrop of increasingly severe global environmental changes, accurately predicting and meeting renewable energy demands has become a key challenge for sustainable business development. Traditional energy demand forecasting methods often struggle with complex data processing and low prediction accuracy. To address these issues, this paper introduces a novel approach that combines deep learning techniques with environmental decision support systems. The model integrates advanced deep learning techniques, including LSTM and Transformer, and PSO algorithm for parameter optimization, significantly enhancing predictive performance and practical applicability. Results show that our model achieves substantial improvements across various metrics, including a 30% reduction in MAE, a 20% decrease in MAPE, a 25% drop in RMSE, and a 35% decline in MSE. These results validate the model's effectiveness and reliability in renewable energy demand forecasting. This research provides valuable insights for applying deep learning in environmental decision support systems.

Haihong Zhao, Chenyi Zi, Yang Liu et al.

Anomaly detection (AD) plays a pivotal role in numerous web-based applications, including malware detection, anti-money laundering, device failure detection, and network fault analysis. Most methods, which rely on unsupervised learning, are hard to reach satisfactory detection accuracy due to the lack of labels. Weakly Supervised Anomaly Detection (WSAD) has been introduced with a limited number of labeled anomaly samples to enhance model performance. Nevertheless, it is still challenging for models, trained on an inadequate amount of labeled data, to generalize to unseen anomalies. In this paper, we introduce a novel framework Knowledge-Data Alignment (KDAlign) to integrate rule knowledge, typically summarized by human experts, to supplement the limited labeled data. Specifically, we transpose these rules into the knowledge space and subsequently recast the incorporation of knowledge as the alignment of knowledge and data. To facilitate this alignment, we employ the Optimal Transport (OT) technique. We then incorporate the OT distance as an additional loss term to the original objective function of WSAD methodologies. Comprehensive experimental results on five real-world datasets demonstrate that our proposed KDAlign framework markedly surpasses its state-of-the-art counterparts, achieving superior performance across various anomaly types.

Yaxin Liu, Yan Zhou, Ziming Li et al.

As an important multimodal sentiment analysis task, Joint Multimodal Aspect-Sentiment Analysis (JMASA), aiming to jointly extract aspect terms and their associated sentiment polarities from the given text-image pairs, has gained increasing concerns. Existing works encounter two limitations: (1) multi-level modality noise, i.e., instance- and feature-level noise; and (2) multi-grained semantic gap, i.e., coarse- and fine-grained gap. Both issues may interfere with accurate identification of aspect-sentiment pairs. To address these limitations, we propose a novel framework named RNG for JMASA. Specifically, to simultaneously reduce multi-level modality noise and multi-grained semantic gap, we design three constraints: (1) Global Relevance Constraint (GR-Con) based on text-image similarity for instance-level noise reduction, (2) Information Bottleneck Constraint (IB-Con) based on the Information Bottleneck (IB) principle for feature-level noise reduction, and (3) Semantic Consistency Constraint (SC-Con) based on mutual information maximization in a contrastive learning way for multi-grained semantic gap reduction. Extensive experiments on two datasets validate our new state-of-the-art performance.

Ziqi Gao, Tao Feng, Jiaxuan You et al.

AlphaFold can be used for both single-chain and multi-chain protein structure prediction, while the latter becomes extremely challenging as the number of chains increases. In this work, by taking each chain as a node and assembly actions as edges, we show that an acyclic undirected connected graph can be used to predict the structure of multi-chain protein complexes (a.k.a., protein complex modelling, PCM). However, there are still two challenges: 1) The huge combinatorial optimization space of $N^{N-2}$ ($N$ is the number of chains) for the PCM problem can easily lead to high computational cost. 2) The scales of protein complexes exhibit distribution shift due to variance in chain numbers, which calls for the generalization in modelling complexes of various scales. To address these challenges, we propose GAPN, a Generative Adversarial Policy Network powered by domain-specific rewards and adversarial loss through policy gradient for automatic PCM prediction. Specifically, GAPN learns to efficiently search through the immense assembly space and optimize the direct docking reward through policy gradient. Importantly, we design an adversarial reward function to enhance the receptive field of our model. In this way, GAPN will simultaneously focus on a specific batch of complexes and the global assembly rules learned from complexes with varied chain numbers. Empirically, we have achieved both significant accuracy (measured by RMSD and TM-Score) and efficiency improvements compared to leading PCM softwares.

Shaolei Zhang, Shoutao Guo, Qingkai Fang et al.

The emergence of GPT-4o-like large multimodal models (LMMs) has raised the exploration of integrating text, vision, and speech modalities to support more flexible multimodal interaction. Existing LMMs typically concatenate representation of modalities along the sequence dimension and feed them into a large language model (LLM) backbone. While sequence-dimension concatenation is straightforward for modality integration, it often relies heavily on large-scale data to learn modality alignments. In this paper, we aim to model the relationships between modalities more purposefully, thereby achieving more efficient and flexible modality alignments. To this end, we propose Stream-Omni, a large language-vision-speech model with efficient modality alignments, which can simultaneously support interactions under various modality combinations. Stream-Omni employs LLM as the backbone and aligns the vision and speech to the text based on their relationships. For vision that is semantically complementary to text, Stream-Omni uses sequence-dimension concatenation to achieve vision-text alignment. For speech that is semantically consistent with text, Stream-Omni introduces a CTC-based layer-dimension mapping to achieve speech-text alignment. In this way, Stream-Omni can achieve modality alignments with less data (especially speech), enabling the transfer of text capabilities to other modalities. Experiments on various benchmarks demonstrate that Stream-Omni achieves strong performance on visual understanding, speech interaction, and vision-grounded speech interaction tasks. Owing to the layer-dimensional mapping, Stream-Omni can simultaneously provide intermediate text outputs (such as ASR transcriptions and model responses) during speech interaction, offering users a comprehensive multimodal experience.

Yujun Zhang, Runlong Li, Xiaoxiang Liang et al.

The abnormal fluctuations in network traffic may indicate potential security threats or system failures. Therefore, efficient network traffic prediction and anomaly detection methods are crucial for network security and traffic management. This paper proposes a novel network traffic prediction and anomaly detection model, MamNet, which integrates time-domain modeling and frequency-domain feature extraction. The model first captures the long-term dependencies of network traffic through the Mamba module (time-domain modeling), and then identifies periodic fluctuations in the traffic using Fourier Transform (frequency-domain feature extraction). In the feature fusion layer, multi-scale information is integrated to enhance the model's ability to detect network traffic anomalies. Experiments conducted on the UNSW-NB15 and CAIDA datasets demonstrate that MamNet outperforms several recent mainstream models in terms of accuracy, recall, and F1-Score. Specifically, it achieves an improvement of approximately 2% to 4% in detection performance for complex traffic patterns and long-term trend detection. The results indicate that MamNet effectively captures anomalies in network traffic across different time scales and is suitable for anomaly detection tasks in network security and traffic management. Future work could further optimize the model structure by incorporating external network event information, thereby improving the model's adaptability and stability in complex network environments.

Nasla Saleem, Talukder Zaki Jubery, Aditya Balu et al.

High-density planting is a widely adopted strategy to enhance maize productivity, yet it introduces challenges such as increased interplant competition and shading, which can limit light capture and overall yield potential. In response, some maize plants naturally reorient their canopies to optimize light capture, a process known as canopy reorientation. Understanding this adaptive response and its impact on light capture is crucial for maximizing agricultural yield potential. This study introduces an end-to-end framework that integrates realistic 3D reconstructions of field-grown maize with photosynthetically active radiation (PAR) modeling to assess the effects of phyllotaxy and planting density on light interception. In particular, using 3D point clouds derived from field data, virtual fields for a diverse set of maize genotypes were constructed and validated against field PAR measurements. Using this framework, we present detailed analyses of the impact of canopy orientations, plant and row spacings, and planting row directions on PAR interception throughout a typical growing season. Our findings highlight significant variations in light interception efficiency across different planting densities and canopy orientations. By elucidating the relationship between canopy architecture and light capture, this study offers valuable guidance for optimizing maize breeding and cultivation strategies across diverse agricultural settings.

Bo Liu, Runlong Li, Li Zhou et al.

This paper proposes a Diffusion Model-Optimized Neural Radiance Field (DT-NeRF) method, aimed at enhancing detail recovery and multi-view consistency in 3D scene reconstruction. By combining diffusion models with Transformers, DT-NeRF effectively restores details under sparse viewpoints and maintains high accuracy in complex geometric scenes. Experimental results demonstrate that DT-NeRF significantly outperforms traditional NeRF and other state-of-the-art methods on the Matterport3D and ShapeNet datasets, particularly in metrics such as PSNR, SSIM, Chamfer Distance, and Fidelity. Ablation experiments further confirm the critical role of the diffusion and Transformer modules in the model's performance, with the removal of either module leading to a decline in performance. The design of DT-NeRF showcases the synergistic effect between modules, providing an efficient and accurate solution for 3D scene reconstruction. Future research may focus on further optimizing the model, exploring more advanced generative models and network architectures to enhance its performance in large-scale dynamic scenes.

Ming Chen, Liyuan Cui, Wenyuan Zhang et al.

Recently, interactive digital human video generation has attracted widespread attention and achieved remarkable progress. However, building such a practical system that can interact with diverse input signals in real time remains challenging to existing methods, which often struggle with heavy computational cost and limited controllability. In this work, we introduce an autoregressive video generation framework that enables interactive multimodal control and low-latency extrapolation in a streaming manner. With minimal modifications to a standard large language model (LLM), our framework accepts multimodal condition encodings including audio, pose, and text, and outputs spatially and semantically coherent representations to guide the denoising process of a diffusion head. To support this, we construct a large-scale dialogue dataset of approximately 20,000 hours from multiple sources, providing rich conversational scenarios for training. We further introduce a deep compression autoencoder with up to 64$\times$ reduction ratio, which effectively alleviates the long-horizon inference burden of the autoregressive model. Extensive experiments on duplex conversation, multilingual human synthesis, and interactive world model highlight the advantages of our approach in low latency, high efficiency, and fine-grained multimodal controllability.

Yan Zhou, Bradley Malin, Murat Kantarcioglu

Privacy-preserving data publication, including synthetic data sharing, often experiences trade-offs between privacy and utility. Synthetic data is generally more effective than data anonymization in balancing this trade-off, however, not without its own challenges. Synthetic data produced by generative models trained on source data may inadvertently reveal information about outliers. Techniques specifically designed for preserving privacy, such as introducing noise to satisfy differential privacy, often incur unpredictable and significant losses in utility. In this work we show that, with the right mechanism of synthetic data generation, we can achieve strong privacy protection without significant utility loss. Synthetic data generators producing contracting data patterns, such as Synthetic Minority Over-sampling Technique (SMOTE), can enhance a differentially private data generator, leveraging the strengths of both. We prove in theory and through empirical demonstration that this SMOTE-DP technique can produce synthetic data that not only ensures robust privacy protection but maintains utility in downstream learning tasks.

Nan Gao, Yihua Bao, Dongdong Weng et al.

Co-speech gesture generation enhances human-computer interaction realism through speech-synchronized gesture synthesis. However, generating semantically meaningful gestures remains a challenging problem. We propose SARGes, a novel framework that leverages large language models (LLMs) to parse speech content and generate reliable semantic gesture labels, which subsequently guide the synthesis of meaningful co-speech gestures.First, we constructed a comprehensive co-speech gesture ethogram and developed an LLM-based intent chain reasoning mechanism that systematically parses and decomposes gesture semantics into structured inference steps following ethogram criteria, effectively guiding LLMs to generate context-aware gesture labels. Subsequently, we constructed an intent chain-annotated text-to-gesture label dataset and trained a lightweight gesture label generation model, which then guides the generation of credible and semantically coherent co-speech gestures. Experimental results demonstrate that SARGes achieves highly semantically-aligned gesture labeling (50.2% accuracy) with efficient single-pass inference (0.4 seconds). The proposed method provides an interpretable intent reasoning pathway for semantic gesture synthesis.

Yan Zhou, Mingji Li, Xiantao Zeng et al.

Sketch-based 3D reconstruction remains a challenging task due to the abstract and sparse nature of sketch inputs, which often lack sufficient semantic and geometric information. To address this, we propose Sketch2Symm, a two-stage generation method that produces geometrically consistent 3D shapes from sketches. Our approach introduces semantic bridging via sketch-to-image translation to enrich sparse sketch representations, and incorporates symmetry constraints as geometric priors to leverage the structural regularity commonly found in everyday objects. Experiments on mainstream sketch datasets demonstrate that our method achieves superior performance compared to existing sketch-based reconstruction methods in terms of Chamfer Distance, Earth Mover's Distance, and F-Score, verifying the effectiveness of the proposed semantic bridging and symmetry-aware design.