Rui Liu

Rui Liu, Young Jin Kim, Alexandre Muzio et al. · microsoft-research

Sparsely activated transformers, such as Mixture of Experts (MoE), have received great interest due to their outrageous scaling capability which enables dramatical increases in model size without significant increases in computational cost. To achieve this, MoE models replace the feedforward sub-layer with Mixture-of-Experts sub-layer in transformers and use a gating network to route each token to its assigned experts. Since the common practice for efficient training of such models requires distributing experts and tokens across different machines, this routing strategy often incurs huge cross-machine communication cost because tokens and their assigned experts likely reside in different machines. In this paper, we propose \emph{Gating Dropout}, which allows tokens to ignore the gating network and stay at their local machines, thus reducing the cross-machine communication. Similar to traditional dropout, we also show that Gating Dropout has a regularization effect during training, resulting in improved generalization performance. We validate the effectiveness of Gating Dropout on multilingual machine translation tasks. Our results demonstrate that Gating Dropout improves a state-of-the-art MoE model with faster wall-clock time convergence rates and better BLEU scores for a variety of model sizes and datasets.

Haolin Zuo, Rui Liu, Jinming Zhao et al.

Multimodal emotion recognition leverages complementary information across modalities to gain performance. However, we cannot guarantee that the data of all modalities are always present in practice. In the studies to predict the missing data across modalities, the inherent difference between heterogeneous modalities, namely the modality gap, presents a challenge. To address this, we propose to use invariant features for a missing modality imagination network (IF-MMIN) which includes two novel mechanisms: 1) an invariant feature learning strategy that is based on the central moment discrepancy (CMD) distance under the full-modality scenario; 2) an invariant feature based imagination module (IF-IM) to alleviate the modality gap during the missing modalities prediction, thus improving the robustness of multimodal joint representation. Comprehensive experiments on the benchmark dataset IEMOCAP demonstrate that the proposed model outperforms all baselines and invariantly improves the overall emotion recognition performance under uncertain missing-modality conditions. We release the code at: https://github.com/ZhuoYulang/IF-MMIN.

Rui Liu, Berrak Sisman, Björn Schuller et al.

Emotion classification of speech and assessment of the emotion strength are required in applications such as emotional text-to-speech and voice conversion. The emotion attribute ranking function based on Support Vector Machine (SVM) was proposed to predict emotion strength for emotional speech corpus. However, the trained ranking function doesn't generalize to new domains, which limits the scope of applications, especially for out-of-domain or unseen speech. In this paper, we propose a data-driven deep learning model, i.e. StrengthNet, to improve the generalization of emotion strength assessment for seen and unseen speech. This is achieved by the fusion of emotional data from various domains. We follow a multi-task learning network architecture that includes an acoustic encoder, a strength predictor, and an auxiliary emotion predictor. Experiments show that the predicted emotion strength of the proposed StrengthNet is highly correlated with ground truth scores for both seen and unseen speech. We release the source codes at: https://github.com/ttslr/StrengthNet.

Yuxiang Chai, Han Xiao, Xinyu Fu et al.

Recent advances in mobile GUI agents have shown strong potential for automating mobile tasks, but most effective systems still depend on large vision-language models for screenshot understanding and long-horizon planning. Small GUI agents that can be deployed directly on mobile devices are more attractive for practical use, offering lower inference cost and better protection of sensitive on-device information. However, due to limited model capacity, such lightweight agents remain unreliable when planning and executing GUI tasks end-to-end from screenshots alone. We propose Knowledge-Oriented Behavior Exploration (\textbf{UI-KOBE}), a framework that improves lightweight mobile GUI agents with reusable app-specific graph knowledge. UI-KOBE first autonomously explores a mobile application and constructs an app knowledge graph, where nodes represent distinct UI states and edges represent executable transitions. At runtime, a lightweight GUI agent uses the graph as external guidance: given a user task and the current screenshot, it identifies the current graph node and selects among self-loop actions, neighboring transitions, task completion, or fallback free actions associated with that node. By supporting runtime decisions with app-specific graph guidance, UI-KOBE reduces the burden of end-to-end GUI planning and helps lightweight models perform mobile GUI tasks more effectively, offering a practical step toward efficient, interpretable, and privacy-conscious on-device GUI agents.

Jiangnan Li, Fandong Meng, Zheng Lin et al. · tsinghua

Conversational Causal Emotion Entailment aims to detect causal utterances for a non-neutral targeted utterance from a conversation. In this work, we build conversations as graphs to overcome implicit contextual modelling of the original entailment style. Following the previous work, we further introduce the emotion information into graphs. Emotion information can markedly promote the detection of causal utterances whose emotion is the same as the targeted utterance. However, it is still hard to detect causal utterances with different emotions, especially neutral ones. The reason is that models are limited in reasoning causal clues and passing them between utterances. To alleviate this problem, we introduce social commonsense knowledge (CSK) and propose a Knowledge Enhanced Conversation graph (KEC). KEC propagates the CSK between two utterances. As not all CSK is emotionally suitable for utterances, we therefore propose a sentiment-realized knowledge selecting strategy to filter CSK. To process KEC, we further construct the Knowledge Enhanced Directed Acyclic Graph networks. Experimental results show that our method outperforms baselines and infers more causes with different emotions from the targeted utterance.

Rui Liu, Bin Liu, Haizhou Li

Prosodic phrasing is crucial to the naturalness and intelligibility of end-to-end Text-to-Speech (TTS). There exist both linguistic and emotional prosody in natural speech. As the study of prosodic phrasing has been linguistically motivated, prosodic phrasing for expressive emotion rendering has not been well studied. In this paper, we propose an emotion-aware prosodic phrasing model, termed \textit{EmoPP}, to mine the emotional cues of utterance accurately and predict appropriate phrase breaks. We first conduct objective observations on the ESD dataset to validate the strong correlation between emotion and prosodic phrasing. Then the objective and subjective evaluations show that the EmoPP outperforms all baselines and achieves remarkable performance in terms of emotion expressiveness. The audio samples and the code are available at \url{https://github.com/AI-S2-Lab/EmoPP}.

Yifan Hu, Rui Liu, Guanglai Gao et al.

Conversational Text-to-Speech (TTS) aims to synthesis an utterance with the right linguistic and affective prosody in a conversational context. The correlation between the current utterance and the dialogue history at the utterance level was used to improve the expressiveness of synthesized speech. However, the fine-grained information in the dialogue history at the word level also has an important impact on the prosodic expression of an utterance, which has not been well studied in the prior work. Therefore, we propose a novel expressive conversational TTS model, termed as FCTalker, that learn the fine and coarse grained context dependency at the same time during speech generation. Specifically, the FCTalker includes fine and coarse grained encoders to exploit the word and utterance-level context dependency. To model the word-level dependencies between an utterance and its dialogue history, the fine-grained dialogue encoder is built on top of a dialogue BERT model. The experimental results show that the proposed method outperforms all baselines and generates more expressive speech that is contextually appropriate. We release the source code at: https://github.com/walker-hyf/FCTalker.

Haizhong Zheng, Rui Liu, Fan Lai et al.

One-shot coreset selection aims to select a representative subset of the training data, given a pruning rate, that can later be used to train future models while retaining high accuracy. State-of-the-art coreset selection methods pick the highest importance examples based on an importance metric and are found to perform well at low pruning rates. However, at high pruning rates, they suffer from a catastrophic accuracy drop, performing worse than even random sampling. This paper explores the reasons behind this accuracy drop both theoretically and empirically. We first propose a novel metric to measure the coverage of a dataset on a specific distribution by extending the classical geometric set cover problem to a distribution cover problem. This metric helps explain why coresets selected by SOTA methods at high pruning rates perform poorly compared to random sampling because of worse data coverage. We then propose a novel one-shot coreset selection method, Coverage-centric Coreset Selection (CCS), that jointly considers overall data coverage upon a distribution as well as the importance of each example. We evaluate CCS on five datasets and show that, at high pruning rates (e.g., 90%), it achieves significantly better accuracy than previous SOTA methods (e.g., at least 19.56% higher on CIFAR10) as well as random selection (e.g., 7.04% higher on CIFAR10) and comparable accuracy at low pruning rates. We make our code publicly available at https://github.com/haizhongzheng/Coverage-centric-coreset-selection.

Wei Dai, Rui Liu, Tianyi Wu et al.

Accurate and unbiased examinations of skin lesions are critical for the early diagnosis and treatment of skin diseases. Visual features of skin lesions vary significantly because the images are collected from patients with different lesion colours and morphologies by using dissimilar imaging equipment. Recent studies have reported that ensembled convolutional neural networks (CNNs) are practical to classify the images for early diagnosis of skin disorders. However, the practical use of these ensembled CNNs is limited as these networks are heavyweight and inadequate for processing contextual information. Although lightweight networks (e.g., MobileNetV3 and EfficientNet) were developed to achieve parameters reduction for implementing deep neural networks on mobile devices, insufficient depth of feature representation restricts the performance. To address the existing limitations, we develop a new lite and effective neural network, namely HierAttn. The HierAttn applies a novel deep supervision strategy to learn the local and global features by using multi-stage and multi-branch attention mechanisms with only one training loss. The efficacy of HierAttn was evaluated by using the dermoscopy images dataset ISIC2019 and smartphone photos dataset PAD-UFES-20 (PAD2020). The experimental results show that HierAttn achieves the best accuracy and area under the curve (AUC) among the state-of-the-art lightweight networks. The code is available at https://github.com/anthonyweidai/HierAttn.

Kailin Liang, Bin Liu, Yifan Hu et al.

Text-to-Speech (TTS) synthesis for low-resource languages is an attractive research issue in academia and industry nowadays. Mongolian is the official language of the Inner Mongolia Autonomous Region and a representative low-resource language spoken by over 10 million people worldwide. However, there is a relative lack of open-source datasets for Mongolian TTS. Therefore, we make public an open-source multi-speaker Mongolian TTS dataset, named MnTTS2, for the benefit of related researchers. In this work, we prepare the transcription from various topics and invite three professional Mongolian announcers to form a three-speaker TTS dataset, in which each announcer records 10 hours of speeches in Mongolian, resulting 30 hours in total. Furthermore, we build the baseline system based on the state-of-the-art FastSpeech2 model and HiFi-GAN vocoder. The experimental results suggest that the constructed MnTTS2 dataset is sufficient to build robust multi-speaker TTS models for real-world applications. The MnTTS2 dataset, training recipe, and pretrained models are released at: \url{https://github.com/ssmlkl/MnTTS2}

Runpeng Dai, Tong Zheng, Rui Liu et al.

Test-time scaling improves the reasoning performance of large language models but incurs substantial cost in both total computation and latency. Existing adaptive sampling methods partially mitigate this issue by dynamically deciding when to stop sampling, yet they typically rely on heuristic rules or rely on distribution assumptions. In this work, we formulate adaptive sampling as a Markov decision process (MDP). We train a lightweight sampling controller with reinforcement learning (RL) to jointly balance answer correctness, latency, and computation cost. At each round, the controller decides to stop sampling or to acquire additional samples. Our method is lightweight which only relies on statistics of final answers, and can be trained and deployed on CPU. We further show that the resulting framework admits an interpretation as the Lagrangian relaxation of a constrained optimization problem with explicit budget constraints. Experiments against strong baselines such as ASC and ESC show that our method achieves improved trade-offs among answer correctness, sampling rounds, and total samples required.

Anran Li, Rui Liu, Ming Hu et al. · mit

Federated learning (FL) enables multiple data owners to build machine learning models collaboratively without exposing their private local data. In order for FL to achieve widespread adoption, it is important to balance the need for performance, privacy-preservation and interpretability, especially in mission critical applications such as finance and healthcare. Thus, interpretable federated learning (IFL) has become an emerging topic of research attracting significant interest from the academia and the industry alike. Its interdisciplinary nature can be challenging for new researchers to pick up. In this paper, we bridge this gap by providing (to the best of our knowledge) the first survey on IFL. We propose a unique IFL taxonomy which covers relevant works enabling FL models to explain the prediction results, support model debugging, and provide insights into the contributions made by individual data owners or data samples, which in turn, is crucial for allocating rewards fairly to motivate active and reliable participation in FL. We conduct comprehensive analysis of the representative IFL approaches, the commonly adopted performance evaluation metrics, and promising directions towards building versatile IFL techniques.

Xudong Lu, Xueying Li, Annan Wang et al.

We introduce OmniInteract, a streaming benchmark for real-time omnimodal large language models evaluated through native online inference over audio-visual streams. Unlike offline video understanding or text-prompted streaming QA, OmniInteract preserves the original audio-visual stream and requires models to process it online, without access to future content. User queries and ambient sounds are embedded in the audio track, requiring models to detect multimodal triggers, decide when to respond, and answer while the stream unfolds. OmniInteract contains 250 videos with 1,430 temporally grounded response slots: 1,062 1Q1A slots across real-time, proactive, and nested scenarios, and 368 1QnA slots for continuous task monitoring and step guidance. Each slot includes a trigger, response window, and target answer. We evaluate response correctness, timing, invalid outputs, interruption handling, and context continuity using Interaction-Aware Quality-Timeliness F1, Interruption Diagnostic Suite, and Nested Chain Completion Score. Experiments show that current models remain weak in streaming interaction, with the best overall IA-QTF1 reaching only 0.368 and the best 1QnA IA-QTF1 only 0.052. Further study on mathematical reasoning in full-duplex settings shows that offline capability does not necessarily transfer to online interaction. Code and datasets will be made publicly accessible at https://github.com/Lucky-Lance/OmniInteract.

Peiwen Sun, Xudong Lu, Huadai Liu et al.

While video streaming understanding has made significant strides, real-world applications, such as live sports broadcasting, autonomous driving, and multi-screen collaboration, inherently demand continuous, multi-stream interactions. However, existing benchmarks are confined to single-stream paradigms, leaving a critical gap in evaluating online, cross-stream reasoning. To bridge this, we introduce X-Stream, the first benchmark dedicated to multi-stream streaming understanding. Comprising 4,220 rigorously curated QA pairs across 932 videos, X-Stream evaluates 11 subtasks across multi-window, multi-view, and multi-device scenarios. Crucially, our dataset is constructed using a novel dual-verification pipeline that prevents over-reliance on a single stream. Furthermore, we pioneer the conceptualization of multi-modal large language models (MLLMs) as naive multiplexers, systematically evaluating their performance through the lens of Signal Multiplexing Theory. Our extensive online inference experiments reveal a stark reality: state-of-the-art MLLMs struggle significantly with concurrent streams, achieving only about 50% score and exhibiting poor proactive ability. Ultimately, X-Stream exposes the trade-off of current multiplexing schemes, providing both a practical evaluation protocol and empirical guidance for next-generation multi-stream agents.

Rui Liu, Xiaohan Wang, Wenguan Wang et al.

Vision-language navigation (VLN), which entails an agent to navigate 3D environments following human instructions, has shown great advances. However, current agents are built upon panoramic observations, which hinders their ability to perceive 3D scene geometry and easily leads to ambiguous selection of panoramic view. To address these limitations, we present a BEV Scene Graph (BSG), which leverages multi-step BEV representations to encode scene layouts and geometric cues of indoor environment under the supervision of 3D detection. During navigation, BSG builds a local BEV representation at each step and maintains a BEV-based global scene map, which stores and organizes all the online collected local BEV representations according to their topological relations. Based on BSG, the agent predicts a local BEV grid-level decision score and a global graph-level decision score, combined with a sub-view selection score on panoramic views, for more accurate action prediction. Our approach significantly outperforms state-of-the-art methods on REVERIE, R2R, and R4R, showing the potential of BEV perception in VLN.

Eduardo Pérez-Pellitero, Sibi Catley-Chandar, Richard Shaw et al.

This paper reviews the challenge on constrained high dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2022. This manuscript focuses on the competition set-up, datasets, the proposed methods and their results. The challenge aims at estimating an HDR image from multiple respective low dynamic range (LDR) observations, which might suffer from under- or over-exposed regions and different sources of noise. The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i.e. solutions can not exceed a given number of operations). In Track 2, participants are asked to minimize the complexity of their solutions while imposing a constraint on fidelity scores (i.e. solutions are required to obtain a higher fidelity score than the prescribed baseline). Both tracks use the same data and metrics: Fidelity is measured by means of PSNR with respect to a ground-truth HDR image (computed both directly and with a canonical tonemapping operation), while complexity metrics include the number of Multiply-Accumulate (MAC) operations and runtime (in seconds).

Rui Liu, Yifan Hu, Yi Ren et al.

Conversational Speech Synthesis (CSS) aims to express a target utterance with the proper speaking style in a user-agent conversation setting. Existing CSS methods employ effective multi-modal context modeling techniques to achieve empathy understanding and expression. However, they often need to design complex network architectures and meticulously optimize the modules within them. In addition, due to the limitations of small-scale datasets containing scripted recording styles, they often fail to simulate real natural conversational styles. To address the above issues, we propose a novel generative expressive CSS system, termed GPT-Talker.We transform the multimodal information of the multi-turn dialogue history into discrete token sequences and seamlessly integrate them to form a comprehensive user-agent dialogue context. Leveraging the power of GPT, we predict the token sequence, that includes both semantic and style knowledge, of response for the agent. After that, the expressive conversational speech is synthesized by the conversation-enriched VITS to deliver feedback to the user.Furthermore, we propose a large-scale Natural CSS Dataset called NCSSD, that includes both naturally recorded conversational speech in improvised styles and dialogues extracted from TV shows. It encompasses both Chinese and English languages, with a total duration of 236 hours.We conducted comprehensive experiments on the reliability of the NCSSD and the effectiveness of our GPT-Talker. Both subjective and objective evaluations demonstrate that our model outperforms other state-of-the-art CSS systems significantly in terms of naturalness and expressiveness. The Code, Dataset, and Pre-trained Model are available at: https://github.com/AI-S2-Lab/GPT-Talker.

Yifan Hu, Pengkai Yin, Rui Liu et al.

This paper introduces a high-quality open-source text-to-speech (TTS) synthesis dataset for Mongolian, a low-resource language spoken by over 10 million people worldwide. The dataset, named MnTTS, consists of about 8 hours of transcribed audio recordings spoken by a 22-year-old professional female Mongolian announcer. It is the first publicly available dataset developed to promote Mongolian TTS applications in both academia and industry. In this paper, we share our experience by describing the dataset development procedures and faced challenges. To demonstrate the reliability of our dataset, we built a powerful non-autoregressive baseline system based on FastSpeech2 model and HiFi-GAN vocoder, and evaluated it using the subjective mean opinion score (MOS) and real time factor (RTF) metrics. Evaluation results show that the powerful baseline system trained on our dataset achieves MOS above 4 and RTF about $3.30\times10^{-1}$, which makes it applicable for practical use. The dataset, training recipe, and pretrained TTS models are freely available \footnote{\label{github}\url{https://github.com/walker-hyf/MnTTS}}.

Wuque Cai, Hongze Sun, Rui Liu et al.

Spiking neural networks (SNNs) mimic brain computational strategies, and exhibit substantial capabilities in spatiotemporal information processing. As an essential factor for human perception, visual attention refers to the dynamic process for selecting salient regions in biological vision systems. Although visual attention mechanisms have achieved great success in computer vision applications, they are rarely introduced into SNNs. Inspired by experimental observations on predictive attentional remapping, we propose a new spatial-channel-temporal-fused attention (SCTFA) module that can guide SNNs to efficiently capture underlying target regions by utilizing accumulated historical spatial-channel information in the present study. Through a systematic evaluation on three event stream datasets (DVS Gesture, SL-Animals-DVS and MNIST-DVS), we demonstrate that the SNN with the SCTFA module (SCTFA-SNN) not only significantly outperforms the baseline SNN (BL-SNN) and two other SNN models with degenerated attention modules, but also achieves competitive accuracy with existing state-of-the-art methods. Additionally, our detailed analysis shows that the proposed SCTFA-SNN model has strong robustness to noise and outstanding stability when faced with incomplete data, while maintaining acceptable complexity and efficiency. Overall, these findings indicate that incorporating appropriate cognitive mechanisms of the brain may provide a promising approach to elevate the capabilities of SNNs.

Rui Liu, Jiatian Xi, Ziyue Jiang et al.

Text-based speech editing (TSE) techniques are designed to enable users to edit the output audio by modifying the input text transcript instead of the audio itself. Despite much progress in neural network-based TSE techniques, the current techniques have focused on reducing the difference between the generated speech segment and the reference target in the editing region, ignoring its local and global fluency in the context and original utterance. To maintain the speech fluency, we propose a fluency speech editing model, termed \textit{FluentEditor}, by considering fluency-aware training criterion in the TSE training. Specifically, the \textit{acoustic consistency constraint} aims to smooth the transition between the edited region and its neighboring acoustic segments consistent with the ground truth, while the \textit{prosody consistency constraint} seeks to ensure that the prosody attributes within the edited regions remain consistent with the overall style of the original utterance. The subjective and objective experimental results on VCTK demonstrate that our \textit{FluentEditor} outperforms all advanced baselines in terms of naturalness and fluency. The audio samples and code are available at \url{https://github.com/Ai-S2-Lab/FluentEditor}.

Zhaoqing Li, Haoning Xu, Jingran Su et al.

We present UNISON, a latent diffusion framework that unifies speech generation, sound generation, and audio editing within a single model. A single model handles text-to-audio, text-to-speech, zero-shot speaker cloning, mixed speech-and-sound generation, scene-level audio editing, speech-in-scene editing, and timed temporal composition, all of which share a single set of weights. Our architecture features two core designs: (1) Layer-wise deep LLM fusion, which injects hidden states from uniformly sampled layers of a frozen MLLM into corresponding MM-DiT blocks via learned projections, providing depth-matched semantic conditioning that improves instruction following over single-layer baselines; and (2) a unified multi-task architecture where task identity is encoded solely by a channel-wise mask and source audio is provided through VAE-encoded channel concatenation. Training is stabilized by an online GPU-side multi-task data synthesis pipeline with task-homogeneous batching and a two-stage curriculum. With 621M--732M trainable parameters, UNISON achieves results competitive with or exceeding task-specialist models across evaluated domains, while being roughly $4\times$ smaller than comparable unified systems.

Saleh Valizadeh Sotubadi, Rui Liu, Vinh Neguyen

This research aims develop an Explainable Artificial Intelligence (XAI) framework to facilitate human-understandable solutions for tool wear prediction during turning. A random forest algorithm was used as the supervised Machine Learning (ML) classifier for training and binary classification using acceleration, acoustics, temperature, and spindle speed during the orthogonal tube turning process as input features. The ML classifier was used to predict the condition of the tool after the cutting process, which was determined in a binary class form indicating if the cutting tool was available or failed. After the training process, the Shapley criterion was used to explain the predictions of the trained ML classifier. Specifically, the significance of each input feature in the decision-making and classification was identified to explain the reasoning of the ML classifier predictions. After implementing the Shapley criterion on all testing datasets, the tool temperature was identified as the most significant feature in determining the classification of available versus failed cutting tools. Hence, this research demonstrates capability of XAI to provide machining operators the ability to diagnose and understand complex ML classifiers in prediction of tool wear.

Rui Liu, Barzan Mozafari

Transformers achieve state-of-the-art performance for natural language processing tasks by pre-training on large-scale text corpora. They are extremely compute-intensive and have very high sample complexity. Memory replay is a mechanism that remembers and reuses past examples by saving to and replaying from a memory buffer. It has been successfully used in reinforcement learning and GANs due to better sample efficiency. In this paper, we propose \emph{Transformer with Memory Replay} (TMR), which integrates memory replay with transformer, making transformer more sample-efficient. Experiments on GLUE and SQuAD benchmark datasets show that Transformer with Memory Replay achieves at least $1\%$ point increase compared to the baseline transformer model when pretrained with the same number of examples. Further, by adopting a careful design that reduces the wall-clock time overhead of memory replay, we also empirically achieve a better runtime efficiency.

Rui Liu, Tao Zhe, Dongjie Wang et al.

The rapid emergence of open-source, locally hosted intelligent agents marks a critical inflection point in human-computer interaction. Systems such as OpenClaw demonstrate that Large Language Model (LLM)-based agents can autonomously operate local computing environments, orchestrate workflows, and integrate external tools. However, within the current paradigm, these agents remain conventional applications running on legacy operating systems originally designed for Graphical User Interfaces (GUIs) or Command Line Interfaces (CLIs). This architectural mismatch leads to fragmented interaction models, poorly structured permission management (often described as "Shadow AI"), and severe context fragmentation. This paper proposes a new paradigm: a Personal Agent Operating System (AgentOS). In AgentOS, traditional GUI desktops are replaced by a Natural User Interface (NUI) centered on a unified natural language or voice portal. The system core becomes an Agent Kernel that interprets user intent, decomposes tasks, and coordinates multiple agents, while traditional applications evolve into modular Skills-as-Modules enabling users to compose software through natural language rules. We argue that realizing AgentOS fundamentally becomes a Knowledge Discovery and Data Mining (KDD) problem. The Agent Kernel must operate as a real-time engine for intent mining and knowledge discovery. Viewed through this lens, the operating system becomes a continuous data mining pipeline involving sequential pattern mining for workflow automation, recommender systems for skill retrieval, and dynamically evolving personal knowledge graphs. These challenges define a new research agenda for the KDD community in building the next generation of intelligent computing systems.

Pengyu Liu, Tinghao Feng, Rui Liu

We introduce a graph polynomial that distinguishes tree structures to represent dependency grammar and a measure based on the polynomial representation to quantify syntax similarity. The polynomial encodes accurate and comprehensive information about the dependency structure and dependency relations of words in a sentence. We apply the polynomial-based methods to analyze sentences in the Parallel Universal Dependencies treebanks. Specifically, we compare the syntax of sentences and their translations in different languages, and we perform a syntactic typology study of available languages in the Parallel Universal Dependencies treebanks. We also demonstrate and discuss the potential of the methods in measuring syntax diversity of corpora.

Qin Yang, Rui Liu

As a unifying concept in economics, game theory, and operations research, even in the Robotics and AI field, the utility is used to evaluate the level of individual needs, preferences, and interests. Especially for decision-making and learning in multi-agent/robot systems (MAS/MRS), a suitable utility model can guide agents in choosing reasonable strategies to achieve their current needs and learning to cooperate and organize their behaviors, optimizing the system's utility, building stable and reliable relationships, and guaranteeing each group member's sustainable development, similar to the human society. Although these systems' complex, large-scale, and long-term behaviors are strongly determined by the fundamental characteristics of the underlying relationships, there has been less discussion on the theoretical aspects of mechanisms and the fields of applications in Robotics and AI. This paper introduces a utility-orient needs paradigm to describe and evaluate inter and outer relationships among agents' interactions. Then, we survey existing literature in relevant fields to support it and propose several promising research directions along with some open problems deemed necessary for further investigations.

Rui Liu, Haolin Zuo, Zheng Lian et al.

Emotion and Intent Joint Understanding in Multimodal Conversation (MC-EIU) aims to decode the semantic information manifested in a multimodal conversational history, while inferring the emotions and intents simultaneously for the current utterance. MC-EIU is enabling technology for many human-computer interfaces. However, there is a lack of available datasets in terms of annotation, modality, language diversity, and accessibility. In this work, we propose an MC-EIU dataset, which features 7 emotion categories, 9 intent categories, 3 modalities, i.e., textual, acoustic, and visual content, and two languages, i.e., English and Mandarin. Furthermore, it is completely open-source for free access. To our knowledge, MC-EIU is the first comprehensive and rich emotion and intent joint understanding dataset for multimodal conversation. Together with the release of the dataset, we also develop an Emotion and Intent Interaction (EI$^2$) network as a reference system by modeling the deep correlation between emotion and intent in the multimodal conversation. With comparative experiments and ablation studies, we demonstrate the effectiveness of the proposed EI$^2$ method on the MC-EIU dataset. The dataset and codes will be made available at: https://github.com/MC-EIU/MC-EIU.

Jianzhe Gao, Rui Liu, Wenguan Wang

Vision-language navigation (VLN) requires an agent to traverse complex 3D environments based on natural language instructions, necessitating a thorough scene understanding. While existing works equip agents with various scene representations to enhance spatial awareness, they often neglect the complex 3D geometry and rich semantics in VLN scenarios, limiting the ability to generalize across diverse and unseen environments. To address these challenges, this work proposes a 3D Gaussian Map that represents the environment as a set of differentiable 3D Gaussians and accordingly develops a navigation strategy for VLN. Specifically, Egocentric Scene Map is constructed online by initializing 3D Gaussians from sparse pseudo-lidar point clouds, providing informative geometric priors for scene understanding. Each Gaussian primitive is further enriched through Open-Set Semantic Grouping operation, which groups 3D Gaussians based on their membership in object instances or stuff categories within the open world, resulting in a unified 3D Gaussian Map. Building on this map, Multi-Level Action Prediction strategy, which combines spatial-semantic cues at multiple granularities, is designed to assist agents in decision-making. Extensive experiments conducted on three public benchmarks (i.e., R2R, R4R, and REVERIE) validate the effectiveness of our method.

Mingjie Li, Rui Liu, Guangsi Shi et al.

Long-term time-series forecasting (LTSF) is fundamental to various real-world applications, where Transformer-based models have become the dominant framework due to their ability to capture long-range dependencies. However, these models often experience overfitting due to data redundancy in rolling forecasting settings, limiting their generalization ability particularly evident in longer sequences with highly similar adjacent data. In this work, we introduce CLMFormer, a novel framework that mitigates redundancy through curriculum learning and a memory-driven decoder. Specifically, we progressively introduce Bernoulli noise to the training samples, which effectively breaks the high similarity between adjacent data points. This curriculum-driven noise introduction aids the memory-driven decoder by supplying more diverse and representative training data, enhancing the decoder's ability to model seasonal tendencies and dependencies in the time-series data. To further enhance forecasting accuracy, we introduce a memory-driven decoder. This component enables the model to capture seasonal tendencies and dependencies in the time-series data and leverages temporal relationships to facilitate the forecasting process. Extensive experiments on six real-world LTSF benchmarks show that CLMFormer consistently improves Transformer-based models by up to 30%, demonstrating its effectiveness in long-horizon forecasting.

Rui Liu, Berrak Sisman, Guanglai Gao et al.

Accented text-to-speech (TTS) synthesis seeks to generate speech with an accent (L2) as a variant of the standard version (L1). Accented TTS synthesis is challenging as L2 is different from L1 in both in terms of phonetic rendering and prosody pattern. Furthermore, there is no easy solution to the control of the accent intensity in an utterance. In this work, we propose a neural TTS architecture, that allows us to control the accent and its intensity during inference. This is achieved through three novel mechanisms, 1) an accent variance adaptor to model the complex accent variance with three prosody controlling factors, namely pitch, energy and duration; 2) an accent intensity modeling strategy to quantify the accent intensity; 3) a consistency constraint module to encourage the TTS system to render the expected accent intensity at a fine level. Experiments show that the proposed system attains superior performance to the baseline models in terms of accent rendering and intensity control. To our best knowledge, this is the first study of accented TTS synthesis with explicit intensity control.

Yaowei Wang, Zhouxin Yang, Rui Liu et al.

Object detection is an algorithm that recognizes and locates the objects in the image and has a wide range of applications in the visual understanding of complex urban scenes. Existing object detection benchmarks mainly focus on a single specific scenario and their annotation attributes are not rich enough, these make the object detection model is not generalized for the smart city scenes. Considering the diversity and complexity of scenes in intelligent city governance, we build a large-scale object detection benchmark for the smart city. Our benchmark contains about 500K images and includes three scenarios: intelligent transportation, intelligent security, and drones. For the complexity of the real scene in the smart city, the diversity of weather, occlusion, and other complex environment diversity attributes of the images in the three scenes are annotated. The characteristics of the benchmark are analyzed and extensive experiments of the current state-of-the-art target detection algorithm are conducted based on our benchmark to show their performance.

Rui Liu, Haolin Zuo, De Hu et al.

Accented text-to-speech (TTS) synthesis seeks to generate speech with an accent (L2) as a variant of the standard version (L1). How to control the intensity of accent in the process of TTS is a very interesting research direction, and has attracted more and more attention. Recent work design a speaker-adversarial loss to disentangle the speaker and accent information, and then adjust the loss weight to control the accent intensity. However, such a control method lacks interpretability, and there is no direct correlation between the controlling factor and natural accent intensity. To this end, this paper propose a new intuitive and explicit accent intensity control scheme for accented TTS. Specifically, we first extract the posterior probability, called as ``goodness of pronunciation (GoP)'' from the L1 speech recognition model to quantify the phoneme accent intensity for accented speech, then design a FastSpeech2 based TTS model, named Ai-TTS, to take the accent intensity expression into account during speech generation. Experiments show that the our method outperforms the baseline model in terms of accent rendering and intensity control.

Zihan Lin, Songhe Deng, Shuwei He et al.

Existing video captioning methods struggle to balance visual fidelity and redundancy: holistic captions are compact but lose fine-grained evidence, whereas segment-wise captions improve coverage but introduce heavy redundancy. We propose CodecCap, a codec-inspired framework for high-fidelity dense video captioning. Analogous to video codecs, CodecCap represents videos using keyframe and residual captions. Keyframe captions exhaustively encode stable visual context, while residual captions capture temporally only localized actions, motions and changes. This effectively preserves fine-grained visual evidence while reducing redundant descriptions. To quantify the fidelity of captions, we introduce VidCapQA, a caption-then-QA benchmark with 1,000 questions across 14 capability dimensions. Results on VidCapQA show that captions directly generated by strong VLMs still miss many visual details, highlighting caption representation as a critical bottleneck. Experiments show that CodecCap significantly surpasses direct captioning with the same underlying VLMs, suggesting keyframe-residual captioning a way for high-fidelity video-language supervision. We further use CodecCap to construct CodecVDC-100K, a large-scale dense captioning dataset with anchor, residual, scene-level, and video-level supervision.

Ning Wu, Rui Liu, Xinkun Lin et al.

Distilling demonstration effects into hidden-space interventions offers a lightweight alternative to full finetuning. However, existing multimodal variants are mostly evaluated on short-form tasks, where outputs end after a few tokens. Extending these methods to long-form generation exposes a fundamental yet underexamined limitation: token-level distillation implicitly treats all output tokens as equally informative, but long-form outputs are dominated by high-frequency template and grammatical tokens, while the tokens that actually determine output quality are sparsely distributed. In medical report generation (MRG), two such decisive tokens stand out: pathology-related tokens that determine diagnostic content, and the end-of-sequence (EOS) event that determines termination. Both receive insufficient supervision under uniform cross-entropy, and autoregressive decoding further compounds the problem by drifting away from teacher-forced trajectories. We propose DIVE, a frozen-backbone distillation framework that addresses long-form report generation through two complementary mechanisms matched to these failures. Decisive-token supervision restores supervision balance by upweighting the cross-entropy contribution of pathology-related tokens and the EOS event, ensuring that content fidelity and termination are learned during training rather than imposed at decoding time. State-conditioned dynamic steering replaces fixed open-loop residuals with hidden-state-dependent adapters, allowing the injected signal to adapt as decoding drifts. Experiments on MIMIC-CXR and CheXpert Plus with two medical VLM backbones show that DIVE consistently ranks among the strongest methods across lexical and clinical-proxy metrics. Our method achieves the best BLEU-4, ROUGE-L, and RadGraph F1 in all dataset--backbone settings, while remaining competitive on coarse label-level CheXbert F1.

Jianzhe Gao, Rui Liu, Yuxuan Xu et al.

Vision-Language Navigation (VLN) requires an agent to navigate 3D environments following natural language instructions. During navigation, existing agents commonly encounter perceptual uncertainty, such as insufficient evidence for reliable grounding or ambiguity in interpreting spatial cues, yet they typically ignore such information when predicting actions. In this work, we explicitly model three forms of perceptual uncertainty (i.e., geometric, semantic, and appearance uncertainty) and integrate them into the agent's observation space to enable informed decision-making. Concretely, our agent first constructs a Semantic Gaussian Map (SGM), composed of differentiable 3D Gaussian primitives initialized from panoramic observations, that encodes both the geometric structure and semantic content of the environment. On top of SGM, geometric uncertainty is estimated through variational perturbations of Gaussian position and scale to assess structural reliability; semantic uncertainty is captured by perturbing Gaussian semantic attributes to reveal ambiguous interpretations; and appearance uncertainty is characterized by Fisher Information, which measures the sensitivity of rendered observations to Gaussian-level variations. These uncertainties are incorporated into SGM, extending it into a unified 3D Value Map, which grounds them as affordances and constraints that support reliable navigation. Comprehensive evaluations across multiple VLN benchmarks show the effectiveness of our agent.

Wang Qi, Rui Liu, Yuan Zuo et al.

Creating an essay based on a few given topics is a challenging NLP task. Although several effective methods for this problem, topic-to-essay generation, have appeared recently, there is still much room for improvement, especially in terms of the coverage of the given topics and the coherence of the generated text. In this paper, we propose a novel approach called TegFormer which utilizes the Transformer architecture where the encoder is enriched with domain-specific contexts while the decoder is enhanced by a large-scale pre-trained language model. Specifically, a \emph{Topic-Extension} layer capturing the interaction between the given topics and their domain-specific contexts is plugged into the encoder. Since the given topics are usually concise and sparse, such an additional layer can bring more topic-related semantics in to facilitate the subsequent natural language generation. Moreover, an \emph{Embedding-Fusion} module that combines the domain-specific word embeddings learnt from the given corpus and the general-purpose word embeddings provided by a GPT-2 model pre-trained on massive text data is integrated into the decoder. Since GPT-2 is at a much larger scale, it contains a lot more implicit linguistic knowledge which would help the decoder to produce more grammatical and readable text. Extensive experiments have shown that the pieces of text generated by TegFormer have better topic coverage and higher text coherence than those from SOTA topic-to-essay techniques, according to automatic and human evaluations. As revealed by ablation studies, both the Topic-Extension layer and the Embedding-Fusion module contribute substantially to TegFormer's performance advantage.

Yuan Zhao, Zhenqi Jia, Rui Liu et al.

Automatic Video Dubbing (AVD) aims to take the given script and generate speech that aligns with lip motion and prosody expressiveness. Current AVD models mainly utilize visual information of the current sentence to enhance the prosody of synthesized speech. However, it is crucial to consider whether the prosody of the generated dubbing aligns with the multimodal context, as the dubbing will be combined with the original context in the final video. This aspect has been overlooked in previous studies. To address this issue, we propose a Multimodal Context-aware video Dubbing model, termed \textbf{MCDubber}, to convert the modeling object from a single sentence to a longer sequence with context information to ensure the consistency of the global context prosody. MCDubber comprises three main components: (1) A context duration aligner aims to learn the context-aware alignment between the text and lip frames; (2) A context prosody predictor seeks to read the global context visual sequence and predict the context-aware global energy and pitch; (3) A context acoustic decoder ultimately predicts the global context mel-spectrogram with the assistance of adjacent ground-truth mel-spectrograms of the target sentence. Through this process, MCDubber fully considers the influence of multimodal context on the prosody expressiveness of the current sentence when dubbing. The extracted mel-spectrogram belonging to the target sentence from the output context mel-spectrograms is the final required dubbing audio. Extensive experiments on the Chem benchmark dataset demonstrate that our MCDubber significantly improves dubbing expressiveness compared to all advanced baselines. The code and demos are available at https://github.com/XiaoYuanJun-zy/MCDubber.

Rui Liu, Yuanyuan Chen, Anran Li et al.

Insufficient data is a long-standing challenge for Brain-Computer Interface (BCI) to build a high-performance deep learning model. Though numerous research groups and institutes collect a multitude of EEG datasets for the same BCI task, sharing EEG data from multiple sites is still challenging due to the heterogeneity of devices. The significance of this challenge cannot be overstated, given the critical role of data diversity in fostering model robustness. However, existing works rarely discuss this issue, predominantly centering their attention on model training within a single dataset, often in the context of inter-subject or inter-session settings. In this work, we propose a hierarchical personalized Federated Learning EEG decoding (FLEEG) framework to surmount this challenge. This innovative framework heralds a new learning paradigm for BCI, enabling datasets with disparate data formats to collaborate in the model training process. Each client is assigned a specific dataset and trains a hierarchical personalized model to manage diverse data formats and facilitate information exchange. Meanwhile, the server coordinates the training procedure to harness knowledge gleaned from all datasets, thus elevating overall performance. The framework has been evaluated in Motor Imagery (MI) classification with nine EEG datasets collected by different devices but implementing the same MI task. Results demonstrate that the proposed frame can boost classification performance up to 16.7% by enabling knowledge sharing between multiple datasets, especially for smaller datasets. Visualization results also indicate that the proposed framework can empower the local models to put a stable focus on task-related areas, yielding better performance. To the best of our knowledge, this is the first end-to-end solution to address this important challenge.

Qi Fan, Haolin Zuo, Rui Liu et al.

Multimodal emotion recognition (MER) in practical scenarios is significantly challenged by the presence of missing or incomplete data across different modalities. To overcome these challenges, researchers have aimed to simulate incomplete conditions during the training phase to enhance the system's overall robustness. Traditional methods have often involved discarding data or substituting data segments with zero vectors to approximate these incompletenesses. However, such approaches neither accurately represent real-world conditions nor adequately address the issue of noisy data availability. For instance, a blurry image cannot be simply replaced with zero vectors, while still retaining information. To tackle this issue and develop a more precise MER system, we introduce a novel noise-robust MER model that effectively learns robust multimodal joint representations from noisy data. This approach includes two pivotal components: firstly, a noise scheduler that adjusts the type and level of noise in the data to emulate various realistic incomplete situations. Secondly, a Variational AutoEncoder (VAE)-based module is employed to reconstruct these robust multimodal joint representations from the noisy inputs. Notably, the introduction of the noise scheduler enables the exploration of an entirely new type of incomplete data condition, which is impossible with existing methods. Extensive experimental evaluations on the benchmark datasets IEMOCAP and CMU-MOSEI demonstrate the effectiveness of the noise scheduler and the excellent performance of our proposed model. Our project is publicly available on https://github.com/WooyoohL/Noise-robust_MER.

Sheng Fan, Rui Liu, Wenguan Wang et al.

Navigation instruction generation, which requires embodied agents to describe the navigation routes, has been of great interest in robotics and human-computer interaction. Existing studies directly map the sequence of 2D perspective observations to route descriptions. Though straightforward, they overlook the geometric information and object semantics of the 3D environment. To address these challenges, we propose BEVInstructor, which incorporates Bird's Eye View (BEV) features into Multi-Modal Large Language Models (MLLMs) for instruction generation. Specifically, BEVInstructor constructs a PerspectiveBEVVisual Encoder for the comprehension of 3D environments through fusing BEV and perspective features. To leverage the powerful language capabilities of MLLMs, the fused representations are used as visual prompts for MLLMs, and perspective-BEV prompt tuning is proposed for parameter-efficient updating. Based on the perspective-BEV prompts, BEVInstructor further adopts an instance-guided iterative refinement pipeline, which improves the instructions in a progressive manner. BEVInstructor achieves impressive performance across diverse datasets (i.e., R2R, REVERIE, and UrbanWalk).

Rui Liu, Jiatian Xi, Ziyue Jiang et al.

Text-based speech editing (TSE) allows users to edit speech by modifying the corresponding text directly without altering the original recording. Current TSE techniques often focus on minimizing discrepancies between generated speech and reference within edited regions during training to achieve fluent TSE performance. However, the generated speech in the edited region should maintain acoustic and prosodic consistency with the unedited region and the original speech at both the local and global levels. To maintain speech fluency, we propose a new fluency speech editing scheme based on our previous \textit{FluentEditor} model, termed \textit{\textbf{FluentEditor2}}, by modeling the multi-scale acoustic and prosody consistency training criterion in TSE training. Specifically, for local acoustic consistency, we propose \textit{hierarchical local acoustic smoothness constraint} to align the acoustic properties of speech frames, phonemes, and words at the boundary between the generated speech in the edited region and the speech in the unedited region. For global prosody consistency, we propose \textit{contrastive global prosody consistency constraint} to keep the speech in the edited region consistent with the prosody of the original utterance. Extensive experiments on the VCTK and LibriTTS datasets show that \textit{FluentEditor2} surpasses existing neural networks-based TSE methods, including Editspeech, Campnet, A$^3$T, FluentSpeech, and our Fluenteditor, in both subjective and objective. Ablation studies further highlight the contributions of each module to the overall effectiveness of the system. Speech demos are available at: \url{https://github.com/Ai-S2-Lab/FluentEditor2}.

Rui Liu, Zahiruddin Mahammad, Amisha Bhaskar et al.

Robotic assistive feeding holds significant promise for improving the quality of life for individuals with eating disabilities. However, acquiring diverse food items under varying conditions and generalizing to unseen food presents unique challenges. Existing methods that rely on surface-level geometric information (e.g., bounding box and pose) derived from visual cues (e.g., color, shape, and texture) often lacks adaptability and robustness, especially when foods share similar physical properties but differ in visual appearance. We employ imitation learning (IL) to learn a policy for food acquisition. Existing methods employ IL or Reinforcement Learning (RL) to learn a policy based on off-the-shelf image encoders such as ResNet-50. However, such representations are not robust and struggle to generalize across diverse acquisition scenarios. To address these limitations, we propose a novel approach, IMRL (Integrated Multi-Dimensional Representation Learning), which integrates visual, physical, temporal, and geometric representations to enhance the robustness and generalizability of IL for food acquisition. Our approach captures food types and physical properties (e.g., solid, semi-solid, granular, liquid, and mixture), models temporal dynamics of acquisition actions, and introduces geometric information to determine optimal scooping points and assess bowl fullness. IMRL enables IL to adaptively adjust scooping strategies based on context, improving the robot's capability to handle diverse food acquisition scenarios. Experiments on a real robot demonstrate our approach's robustness and adaptability across various foods and bowl configurations, including zero-shot generalization to unseen settings. Our approach achieves improvement up to $35\%$ in success rate compared with the best-performing baseline. More details can be found on our website https://ruiiu.github.io/imrl.

Qi Fan, Hongyu Yuan, Haolin Zuo et al.

Multimodal emotion recognition utilizes complete multimodal information and robust multimodal joint representation to gain high performance. However, the ideal condition of full modality integrity is often not applicable in reality and there always appears the situation that some modalities are missing. For example, video, audio, or text data is missing due to sensor failure or network bandwidth problems, which presents a great challenge to MER research. Traditional methods extract useful information from the complete modalities and reconstruct the missing modalities to learn robust multimodal joint representation. These methods have laid a solid foundation for research in this field, and to a certain extent, alleviated the difficulty of multimodal emotion recognition under missing modalities. However, relying solely on internal reconstruction and multimodal joint learning has its limitations, especially when the missing information is critical for emotion recognition. To address this challenge, we propose a novel framework of Retrieval Augment for Missing Modality Multimodal Emotion Recognition (RAMER), which introduces similar multimodal emotion data to enhance the performance of emotion recognition under missing modalities. By leveraging databases, that contain related multimodal emotion data, we can retrieve similar multimodal emotion information to fill in the gaps left by missing modalities. Various experimental results demonstrate that our framework is superior to existing state-of-the-art approaches in missing modality MER tasks. Our whole project is publicly available on https://github.com/WooyoohL/Retrieval_Augment_MER.

Xudong Lu, Huankang Guan, Yang Bo et al.

Multimodal Large Language Models excel at offline audio-visual understanding, but their ability to serve as mobile assistants in continuous real-world streams remains underexplored. In daily phone use, mobile assistants must track streaming audio-visual inputs and respond at the right time, yet existing benchmarks are often restricted to multiple-choice questions or use shorter videos. In this paper, we introduce PhoStream, the first mobile-centric streaming benchmark that unifies on-screen and off-screen scenarios to evaluate video, audio, and temporal reasoning. PhoStream contains 5,572 open-ended QA pairs from 578 videos across 4 scenarios and 10 capabilities. We build it with an Automated Generative Pipeline backed by rigorous human verification, and evaluate models using a realistic Online Inference Pipeline and LLM-as-a-Judge evaluation for open-ended responses. Experiments reveal a temporal asymmetry in LLM-judged scores (0-100): models perform well on Instant and Backward tasks (Gemini 3 Pro exceeds 80), but drop sharply on Forward tasks (16.40), largely due to early responses before the required visual and audio cues appear. This highlights a fundamental limitation: current MLLMs struggle to decide when to speak, not just what to say. Code and datasets used in this work will be made publicly accessible at https://github.com/Lucky-Lance/PhoStream.

Ruibo Fu, Rui Liu, Chunyu Qiang et al.

The Inspirational and Convincing Audio Generation Challenge 2024 (ICAGC 2024) is part of the ISCSLP 2024 Competitions and Challenges track. While current text-to-speech (TTS) technology can generate high-quality audio, its ability to convey complex emotions and controlled detail content remains limited. This constraint leads to a discrepancy between the generated audio and human subjective perception in practical applications like companion robots for children and marketing bots. The core issue lies in the inconsistency between high-quality audio generation and the ultimate human subjective experience. Therefore, this challenge aims to enhance the persuasiveness and acceptability of synthesized audio, focusing on human alignment convincing and inspirational audio generation. A total of 19 teams have registered for the challenge, and the results of the competition and the competition are described in this paper.

Tong Zheng, Haolin Liu, Chengsong Huang et al.

Test-time scaling (TTS) has become an effective approach for improving large language model performance by allocating additional computation during inference. However, existing TTS strategies are largely hand-crafted: researchers manually design reasoning patterns and tune heuristics by intuition, leaving much of the computation-allocation space unexplored. We propose an environment-driven framework, AutoTTS, that changes what researchers design: from individual TTS heuristics to environments where TTS strategies can be discovered automatically. The key to AutoTTS lies in environment construction: the discovery environment must make the control space tractable and provide cheap, frequent feedback for TTS search. As a concrete instantiation, we formulate width--depth TTS as controller synthesis over pre-collected reasoning trajectories and probe signals, where controllers decide when to branch, continue, probe, prune, or stop and can be evaluated cheaply without repeated LLM calls. We further introduce beta parameterization to make the search tractable and fine-grained execution trace feedback to improve discovery efficiency by helping the agent diagnose why a TTS program fails. Experiments on mathematical reasoning benchmarks show that the discovered strategies improve the overall accuracy--cost tradeoff over strong manually designed baselines. The discovered strategies generalize to held-out benchmarks and model scales, while the entire discovery costs only $39.9 and 160 minutes. Our data, and code will be open-source at https://github.com/zhengkid/AutoTTS.

Qiankun Liu, Rui Liu, Bolun Zheng et al.

Recently, infrared small target detection (IRSTD) has been dominated by deep-learning-based methods. However, these methods mainly focus on the design of complex model structures to extract discriminative features, leaving the loss functions for IRSTD under-explored. For example, the widely used Intersection over Union (IoU) and Dice losses lack sensitivity to the scales and locations of targets, limiting the detection performance of detectors. In this paper, we focus on boosting detection performance with a more effective loss but a simpler model structure. Specifically, we first propose a novel Scale and Location Sensitive (SLS) loss to handle the limitations of existing losses: 1) for scale sensitivity, we compute a weight for the IoU loss based on target scales to help the detector distinguish targets with different scales: 2) for location sensitivity, we introduce a penalty term based on the center points of targets to help the detector localize targets more precisely. Then, we design a simple Multi-Scale Head to the plain U-Net (MSHNet). By applying SLS loss to each scale of the predictions, our MSHNet outperforms existing state-of-the-art methods by a large margin. In addition, the detection performance of existing detectors can be further improved when trained with our SLS loss, demonstrating the effectiveness and generalization of our SLS loss. The code is available at https://github.com/ying-fu/MSHNet.

Zhefan Rao, Bin Zou, Haoxuan Che et al.

Instruction-based video editing is a natural way to control video content with text, but adapting a video generation model into an editor usually appears data-hungry. At the same time, high-quality video editing data remains scarce. In this paper, we show that a video generation backbone can become a strong video editor without large scale video editing data. We present InsEdit, an instruction-based editing model built on HunyuanVideo-1.5. InsEdit combines a visual editing architecture with a video data pipeline based on Mutual Context Attention (MCA), which creates aligned video pairs where edits can begin in the middle of a clip rather than only from the first frame. With only O(100)K video editing data, InsEdit achieves state-of-the-art results among open-source methods on our video instruction editing benchmarks. In addition, because our training recipe also includes image editing data, the final model supports image editing without any modification.

Shaoyuan Chen, Linlin You, Rui Liu et al.

The training of large models, involving fine-tuning, faces the scarcity of high-quality data. Compared to the solutions based on centralized data centers, updating large models in the Internet of Things (IoT) faces challenges in coordinating knowledge from distributed clients by using their private and heterogeneous data. To tackle such a challenge, we propose KOALA (Federated Knowledge Transfer Fine-tuning Large Server Model with Resource-Constrained IoT Clients) to impel the training of large models in IoT. Since the resources obtained by IoT clients are limited and restricted, it is infeasible to locally execute large models and also update them in a privacy-preserving manner. Therefore, we leverage federated learning and knowledge distillation to update large models through collaboration with their small models, which can run locally at IoT clients to process their private data separately and enable large-small model knowledge transfer through iterative learning between the server and clients. Moreover, to support clients with similar or different computing capacities, KOALA is designed with two kinds of large-small model joint learning modes, namely to be homogeneous or heterogeneous. Experimental results demonstrate that compared to the conventional approach, our method can not only achieve similar training performance but also significantly reduce the need for local storage and computing power resources.

Rui Liu, Pratap Tokekar, Ming Lin

Multi-agent systems are increasingly equipped with heterogeneous multimodal sensors, enabling richer perception but introducing modality-specific and agent-dependent uncertainty. Existing multi-agent collaboration frameworks typically reason at the agent level, assume homogeneous sensing, and handle uncertainty implicitly, limiting robustness under sensor corruption. We propose Active Asymmetric Multi-Agent Multimodal Learning under Uncertainty (A2MAML), a principled approach for uncertainty-aware, modality-level collaboration. A2MAML models each modality-specific feature as a stochastic estimate with uncertainty prediction, actively selects reliable agent-modality pairs, and aggregates information via Bayesian inverse-variance weighting. This formulation enables fine-grained, modality-level fusion, supports asymmetric modality availability, and provides a principled mechanism to suppress corrupted or noisy modalities. Extensive experiments on connected autonomous driving scenarios for collaborative accident detection demonstrate that A2MAML consistently outperforms both single-agent and collaborative baselines, achieving up to 18.7% higher accident detection rate.