Ming Chen

Ren Yang, Radu Timofte, Xin Li et al.

This paper reviews the Challenge on Super-Resolution of Compressed Image and Video at AIM 2022. This challenge includes two tracks. Track 1 aims at the super-resolution of compressed image, and Track~2 targets the super-resolution of compressed video. In Track 1, we use the popular dataset DIV2K as the training, validation and test sets. In Track 2, we propose the LDV 3.0 dataset, which contains 365 videos, including the LDV 2.0 dataset (335 videos) and 30 additional videos. In this challenge, there are 12 teams and 2 teams that submitted the final results to Track 1 and Track 2, respectively. The proposed methods and solutions gauge the state-of-the-art of super-resolution on compressed image and video. The proposed LDV 3.0 dataset is available at https://github.com/RenYang-home/LDV_dataset. The homepage of this challenge is at https://github.com/RenYang-home/AIM22_CompressSR.

Tianyu Li, Dongchen Han, Zixuan Cao et al.

The long-standing tension between Pre- and Post-Norm remains an open problem in Transformer architecture, reflecting a fundamental trade-off between training stability and representational capacity. Prior attempts to combine their strengths have made progress, but often show limited robustness across training settings, restricting their broader applicability. We revisit this dilemma, showing that single-stream architectures struggle to reconcile Pre-Norm's stable identity-gradient propagation with Post-Norm's normalization of the main residual path. To address this structural tension, we propose SiameseNorm, a simple yet effective two-stream architecture that remains compatible with Pre-Norm training recipes. SiameseNorm couples Pre-Norm-like and Post-Norm-like streams through shared residual blocks, allowing each residual block to receive optimization signals from both pathways with negligible overhead. Extensive experiments on 400M and 1.3B dense language models, 15B MoE models, Vision Transformers, and Diffusion Transformers show that SiameseNorm consistently improves performance while maintaining strong training stability across architectures and modalities. Code is available at https://github.com/Qwen-Applications/SiameseNorm.

Aaditya Singh, Adam Fry, Adam Perelman et al. · berkeley, mila

This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reasoning model for harder problems, and a real-time router that quickly decides which model to use based on conversation type, complexity, tool needs, and explicit intent (for example, if you say 'think hard about this' in the prompt). The router is continuously trained on real signals, including when users switch models, preference rates for responses, and measured correctness, improving over time. Once usage limits are reached, a mini version of each model handles remaining queries. This system card focuses primarily on gpt-5-thinking and gpt-5-main, while evaluations for other models are available in the appendix. The GPT-5 system not only outperforms previous models on benchmarks and answers questions more quickly, but -- more importantly -- is more useful for real-world queries. We've made significant advances in reducing hallucinations, improving instruction following, and minimizing sycophancy, and have leveled up GPT-5's performance in three of ChatGPT's most common uses: writing, coding, and health. All of the GPT-5 models additionally feature safe-completions, our latest approach to safety training to prevent disallowed content. Similarly to ChatGPT agent, we have decided to treat gpt-5-thinking as High capability in the Biological and Chemical domain under our Preparedness Framework, activating the associated safeguards. While we do not have definitive evidence that this model could meaningfully help a novice to create severe biological harm -- our defined threshold for High capability -- we have chosen to take a precautionary approach.

Jingyang Lin, Hang Hua, Ming Chen et al.

Video summarization aims to distill the most important information from a source video to produce either an abridged clip or a textual narrative. Traditionally, different methods have been proposed depending on whether the output is a video or text, thus ignoring the correlation between the two semantically related tasks of visual summarization and textual summarization. We propose a new joint video and text summarization task. The goal is to generate both a shortened video clip along with the corresponding textual summary from a long video, collectively referred to as a cross-modal summary. The generated shortened video clip and text narratives should be semantically well aligned. To this end, we first build a large-scale human-annotated dataset -- VideoXum (X refers to different modalities). The dataset is reannotated based on ActivityNet. After we filter out the videos that do not meet the length requirements, 14,001 long videos remain in our new dataset. Each video in our reannotated dataset has human-annotated video summaries and the corresponding narrative summaries. We then design a novel end-to-end model -- VTSUM-BILP to address the challenges of our proposed task. Moreover, we propose a new metric called VT-CLIPScore to help evaluate the semantic consistency of cross-modality summary. The proposed model achieves promising performance on this new task and establishes a benchmark for future research.

Zangwei Zheng, Pengtai Xu, Xuan Zou et al.

The click-through rate (CTR) prediction task is to predict whether a user will click on the recommended item. As mind-boggling amounts of data are produced online daily, accelerating CTR prediction model training is critical to ensuring an up-to-date model and reducing the training cost. One approach to increase the training speed is to apply large batch training. However, as shown in computer vision and natural language processing tasks, training with a large batch easily suffers from the loss of accuracy. Our experiments show that previous scaling rules fail in the training of CTR prediction neural networks. To tackle this problem, we first theoretically show that different frequencies of ids make it challenging to scale hyperparameters when scaling the batch size. To stabilize the training process in a large batch size setting, we develop the adaptive Column-wise Clipping (CowClip). It enables an easy and effective scaling rule for the embeddings, which keeps the learning rate unchanged and scales the L2 loss. We conduct extensive experiments with four CTR prediction networks on two real-world datasets and successfully scaled 128 times the original batch size without accuracy loss. In particular, for CTR prediction model DeepFM training on the Criteo dataset, our optimization framework enlarges the batch size from 1K to 128K with over 0.1% AUC improvement and reduces training time from 12 hours to 10 minutes on a single V100 GPU. Our code locates at https://github.com/bytedance/LargeBatchCTR.

Ming Chen, Muhammed Tawfiqul Islam, Maria Rodriguez Read et al.

Microservice-based cloud applications face changing workloads, evolving request paths, variable network conditions, interference, and failures. These dynamics couple autoscaling, placement, routing, isolation, and remediation. The survey examines dynamics-aware adaptive management for microservices. Its taxonomy covers control locus, modeled dynamics, adaptation strategy, and evaluation evidence; objectives and telemetry are cross-cutting. A synthesis of 84 system entries and 13 evaluation artifacts shows that production dynamics are often partially modeled. Reported gains also depend on evaluation fidelity. Key future directions include cross-layer coordination, telemetry-to-control abstractions, safe learning-based control, and reproducible dynamic evaluation.

Jakub Rydzewski, Ming Chen, Tushar K. Ghosh et al.

Enhanced sampling methods are indispensable in computational physics and chemistry, where atomistic simulations cannot exhaustively sample the high-dimensional configuration space of dynamical systems due to the sampling problem. A class of such enhanced sampling methods works by identifying a few slow degrees of freedom, termed collective variables (CVs), and enhancing the sampling along these CVs. Selecting CVs to analyze and drive the sampling is not trivial and often relies on physical and chemical intuition. Despite routinely circumventing this issue using manifold learning to estimate CVs directly from standard simulations, such methods cannot provide mappings to a low-dimensional manifold from enhanced sampling simulations as the geometry and density of the learned manifold are biased. Here, we address this crucial issue and provide a general reweighting framework based on anisotropic diffusion maps for manifold learning that takes into account that the learning data set is sampled from a biased probability distribution. We consider manifold learning methods based on constructing a Markov chain describing transition probabilities between high-dimensional samples. We show that our framework reverts the biasing effect yielding CVs that correctly describe the equilibrium density. This advancement enables the construction of low-dimensional CVs using manifold learning directly from data generated by enhanced sampling simulations. We call our framework reweighted manifold learning. We show that it can be used in many manifold learning techniques on data from both standard and enhanced sampling simulations.

Bo Qin, Aixin Jia, Qiang Wang et al.

This paper describes the submission of the RoyalFlush neural machine translation system for the WMT 2022 translation efficiency task. Unlike the commonly used autoregressive translation system, we adopted a two-stage translation paradigm called Hybrid Regression Translation (HRT) to combine the advantages of autoregressive and non-autoregressive translation. Specifically, HRT first autoregressively generates a discontinuous sequence (e.g., make a prediction every $k$ tokens, $k>1$) and then fills in all previously skipped tokens at once in a non-autoregressive manner. Thus, we can easily trade off the translation quality and speed by adjusting $k$. In addition, by integrating other modeling techniques (e.g., sequence-level knowledge distillation and deep-encoder-shallow-decoder layer allocation strategy) and a mass of engineering efforts, HRT improves 80\% inference speed and achieves equivalent translation performance with the same-capacity AT counterpart. Our fastest system reaches 6k+ words/second on the GPU latency setting, estimated to be about 3.1x faster than the last year's winner.

Yidong Du, Wenshuo Wang, Zhigang Wang et al.

The booming of electric vehicles demands efficient battery disassembly for recycling to be environment-friendly. Currently, battery disassembly is still primarily done by humans, probably assisted by robots, due to the unstructured environment and high uncertainties. It is highly desirable to design autonomous solutions to improve work efficiency and lower human risks in high voltage and toxic environments. This paper proposes a novel neurosymbolic method, which augments the traditional Variational Autoencoder (VAE) model to learn symbolic operators based on raw sensory inputs and their relationships. The symbolic operators include a probabilistic state symbol grounding model and a state transition matrix for predicting states after each execution to enable autonomous task and motion planning. At last, the method's feasibility is verified through test results.

Ming Chen, Sareh Nabi, Marciano Siniscalchi

Contemporary real-world online ad auctions differ from canonical models [Edelman et al., 2007; Varian, 2009] in at least four ways: (1) values and click-through rates can depend upon users' search queries, but advertisers can only partially "tune" their bids to specific queries; (2) advertisers do not know the number, identity, and precise value distribution of competing bidders; (3) advertisers only receive partial, aggregated feedback, and (4) payment rules are only partially known to bidders. These features make it virtually impossible to fully characterize equilibrium bidding behavior. This paper shows that, nevertheless, one can still gain useful insight into modern ad auctions by modeling advertisers as agents governed by an adversarial bandit algorithm, independent of auction mechanism intricacies. To demonstrate our approach, we first simulate "soft-floor" auctions [Zeithammer, 2019], a complex, real-world pricing rule for which no complete equilibrium characterization is known. We find that (i) when values and click-through rates are query-dependent, soft floors can improve revenues relative to standard auction formats even if bidder types are drawn from the same distribution; and (ii) with distributional asymmetries that reflect relevant real-world scenario, we find that soft floors yield lower revenues than suitably chosen reserve prices, even restricting attention to a single query. We then demonstrate how to infer advertiser value distributions from observed bids for a variety of pricing rules, and illustrate our approach with aggregate data from an e-commerce website.

Zining Fang, Chunhui Liu, Bin Xu et al.

Surgical smoke severely degrades intraoperative video quality, obscuring anatomical structures and limiting surgical perception. Existing learning-based desmoking approaches rely on scarce paired supervision and deterministic restoration pipelines, making it difficult to perform exploration or reinforcement-driven refinement under real surgical conditions. We propose PhySe-RPO, a diffusion restoration framework optimized through Physics- and Semantics-Guided Relative Policy Optimization. The core idea is to transform deterministic restoration into a stochastic policy, enabling trajectory-level exploration and critic-free updates via group-relative optimization. A physics-guided reward imposes illumination and color consistency, while a visual-concept semantic reward learned from CLIP-based surgical concepts promotes smoke-free and anatomically coherent restoration. Together with a reference-free perceptual constraint, PhySe-RPO produces results that are physically consistent, semantically faithful, and clinically interpretable across synthetic and real robotic surgical datasets, providing a principled route to robust diffusion-based restoration under limited paired supervision.

Qiang Wang, Rongxiang Weng, Ming Chen

K-Nearest Neighbor Neural Machine Translation (kNN-MT) successfully incorporates external corpus by retrieving word-level representations at test time. Generally, kNN-MT borrows the off-the-shelf context representation in the translation task, e.g., the output of the last decoder layer, as the query vector of the retrieval task. In this work, we highlight that coupling the representations of these two tasks is sub-optimal for fine-grained retrieval. To alleviate it, we leverage supervised contrastive learning to learn the distinctive retrieval representation derived from the original context representation. We also propose a fast and effective approach to constructing hard negative samples. Experimental results on five domains show that our approach improves the retrieval accuracy and BLEU score compared to vanilla kNN-MT.

Yanlong Peng, Zhigang Wang, Yisheng Zhang et al.

The efficient disassembly of end-of-life electric vehicle batteries(EOL-EVBs) is crucial for green manufacturing and sustainable development. The current pre-programmed disassembly conducted by the Autonomous Mobile Manipulator Robot(AMMR) struggles to meet the disassembly requirements in dynamic environments, complex scenarios, and unstructured processes. In this paper, we propose a Battery Disassembly AMMR(BEAM-1) system based on NeuralSymbolic AI. It detects the environmental state by leveraging a combination of multi-sensors and neural predicates and then translates this information into a quasi-symbolic space. In real-time, it identifies the optimal sequence of action primitives through LLM-heuristic tree search, ensuring high-precision execution of these primitives. Additionally, it employs positional speculative sampling using intuitive networks and achieves the disassembly of various bolt types with a meticulously designed end-effector. Importantly, BEAM-1 is a continuously learning embodied intelligence system capable of subjective reasoning like a human, and possessing intuition. A large number of real scene experiments have proved that it can autonomously perceive, decide, and execute to complete the continuous disassembly of bolts in multiple, multi-category, and complex situations, with a success rate of 98.78%. This research attempts to use NeuroSymbolic AI to give robots real autonomous reasoning, planning, and learning capabilities. BEAM-1 realizes the revolution of battery disassembly. Its framework can be easily ported to any robotic system to realize different application scenarios, which provides a ground-breaking idea for the design and implementation of future embodied intelligent robotic systems.

Qiang Wang, Xinhui Hu, Ming Chen

In this work, we empirically confirm that non-autoregressive translation with an iterative refinement mechanism (IR-NAT) suffers from poor acceleration robustness because it is more sensitive to decoding batch size and computing device setting than autoregressive translation (AT). Inspired by it, we attempt to investigate how to combine the strengths of autoregressive and non-autoregressive translation paradigms better. To this end, we demonstrate through synthetic experiments that prompting a small number of AT's predictions can promote one-shot non-autoregressive translation to achieve the equivalent performance of IR-NAT. Following this line, we propose a new two-stage translation prototype called hybrid-regressive translation (HRT). Specifically, HRT first generates discontinuous sequences via autoregression (e.g., make a prediction every k tokens, k>1) and then fills in all previously skipped tokens at once in a non-autoregressive manner. We also propose a bag of techniques to effectively and efficiently train HRT without adding any model parameters. HRT achieves the state-of-the-art BLEU score of 28.49 on the WMT En-De task and is at least 1.5x faster than AT, regardless of batch size and device. In addition, another bonus of HRT is that it successfully inherits the good characteristics of AT in the deep-encoder-shallow-decoder architecture. Concretely, compared to the vanilla HRT with a 6-layer encoder and 6-layer decoder, the inference speed of HRT with a 12-layer encoder and 1-layer decoder is further doubled on both GPU and CPU without BLEU loss.

Rulin Zhou, Guankun Wang, An Wang et al.

Accurate and stable field-of-view (FoV) guidance is critical for safe and efficient minimally invasive surgery, yet existing approaches often conflate visual attention estimation with downstream camera control or rely on direct object-centric assumptions. In this work, we formulate surgical attention tracking as a spatio-temporal learning problem and model surgeon focus as a dense attention heatmap, enabling continuous and interpretable frame-wise FoV guidance. We propose SurgAtt-Tracker, a holistic framework that robustly tracks surgical attention by exploiting temporal coherence through proposal-level reranking and motion-aware refinement, rather than direct regression. To support systematic training and evaluation, we introduce SurgAtt-1.16M, a large-scale benchmark with a clinically grounded annotation protocol that enables comprehensive heatmap-based attention analysis across procedures and institutions. Extensive experiments on multiple surgical datasets demonstrate that SurgAtt-Tracker consistently achieves state-of-the-art performance and strong robustness under occlusion, multi-instrument interference, and cross-domain settings. Beyond attention tracking, our approach provides a frame-wise FoV guidance signal that can directly support downstream robotic FoV planning and automatic camera control.

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.

Rong-Xi Tan, Ming Chen, Ke Xue et al.

The pursuit of universal black-box optimization (BBO) algorithms is a longstanding goal. However, unlike domains such as language or vision, where scaling structured data has driven generalization, progress in offline BBO remains hindered by the lack of unified representations for heterogeneous numerical spaces. Thus, existing offline BBO approaches are constrained to single-task and fixed-dimensional settings, failing to achieve cross-domain universal optimization. Recent advances in language models (LMs) offer a promising path forward: their embeddings capture latent relationships in a unifying way, enabling universal optimization across different data types possible. In this paper, we discuss multiple potential approaches, including an end-to-end learning framework in the form of next-token prediction, as well as prioritizing the learning of latent spaces with strong representational capabilities. To validate the effectiveness of these methods, we collect offline BBO tasks and data from open-source academic works for training. Experiments demonstrate the universality and effectiveness of our proposed methods. Our findings suggest that unifying language model priors and learning string embedding space can overcome traditional barriers in universal BBO, paving the way for general-purpose BBO algorithms. The code is provided at https://github.com/lamda-bbo/universal-offline-bbo.

Yikai Liu, Ming Chen, Guang Lin

Coarse-grained (CG) models play a crucial role in the study of protein structures, protein thermodynamic properties, and protein conformation dynamics. Due to the information loss in the coarse-graining process, backmapping from CG to all-atom configurations is essential in many protein design and drug discovery applications when detailed atomic representations are needed for in-depth studies. Despite recent progress in data-driven backmapping approaches, devising a backmapping method that can be universally applied across various CG models and proteins remains unresolved. In this work, we propose BackDiff, a new generative model designed to achieve generalization and reliability in the protein backmapping problem. BackDiff leverages the conditional score-based diffusion model with geometric representations. Since different CG models can contain different coarse-grained sites which include selected atoms (CG atoms) and simple CG auxiliary functions of atomistic coordinates (CG auxiliary variables), we design a self-supervised training framework to adapt to different CG atoms, and constrain the diffusion sampling paths with arbitrary CG auxiliary variables as conditions. Our method facilitates end-to-end training and allows efficient sampling across different proteins and diverse CG models without the need for retraining. Comprehensive experiments over multiple popular CG models demonstrate BackDiff's superior performance to existing state-of-the-art approaches, and generalization and flexibility that these approaches cannot achieve. A pretrained BackDiff model can offer a convenient yet reliable plug-and-play solution for protein researchers, enabling them to investigate further from their own CG models.

Zeyi Li, Yushi Yang, Shawn Xie et al.

Household environments present one of the most common, impactful yet challenging application domains for robotics. Within household scenarios, manipulating deformable objects is particularly difficult, both in simulation and real-world execution, due to varied categories and shapes, complex dynamics, and diverse material properties, as well as the lack of reliable deformable-object support in existing simulations. We introduce LeHome, a comprehensive simulation environment designed for deformable object manipulation in household scenarios. LeHome covers a wide spectrum of deformable objects, such as garments and food items, offering high-fidelity dynamics and realistic interactions that existing simulators struggle to simulate accurately. Moreover, LeHome supports multiple robotic embodiments and emphasizes low-cost robots as a core focus, enabling end-to-end evaluation of household tasks on resource-constrained hardware. By bridging the gap between realistic deformable object simulation and practical robotic platforms, LeHome provides a scalable testbed for advancing household robotics. Webpage: https://lehome-web.github.io/ .

Zhenxing Xu, Yizhe Zhang, Weidong Bao et al.

Dynamically configuring algorithm hyperparameters is a fundamental challenge in computational intelligence. While learning-based methods offer automation, they suffer from prohibitive sample complexity and poor generalization. We introduce AutoEP, a novel framework that bypasses training entirely by leveraging Large Language Models (LLMs) as zero-shot reasoning engines for algorithm control. AutoEP's core innovation lies in a tight synergy between two components: (1) an online Exploratory Landscape Analysis (ELA) module that provides real-time, quantitative feedback on the search dynamics, and (2) a multi-LLM reasoning chain that interprets this feedback to generate adaptive hyperparameter strategies. This approach grounds high-level reasoning in empirical data, mitigating hallucination. Evaluated on three distinct metaheuristics across diverse combinatorial optimization benchmarks, AutoEP consistently outperforms state-of-the-art tuners, including neural evolution and other LLM-based methods. Notably, our framework enables open-source models like Qwen3-30B to match the performance of GPT-4, demonstrating a powerful and accessible new paradigm for automated hyperparameter design. Our code is available at https://anonymous.4open.science/r/AutoEP-3E11

Ranfei Chen, Ming Chen

Diffusion large language models (dLLMs) have emerged as a new architecture following auto regressive models. Their denoising process offers a powerful generative advantage, but they present significant challenges in learning and understanding numerically sensitive mathematical and order-sensitive logical tasks. Current training methods, including pre-training, fine-tuning, and reinforcement learning, focus primarily on improving general knowledge retention and reasoning abilities, but lack a comprehensive understanding of mathematical and logical patterns. We propose DSFT, a simple yet effective Diffusion SFT strategy, by adjusting the masking strategy and loss function, guiding models to understand mathematical and logical patterns. This strategy can be flexibly combined with pre-training, reinforcement learning, and other training methods. Validated on models such as LLaDA and Dream series, we prove that DSFT on small-scale data can achieve improvements of 5-10% and approximately 2% on mathematical and logical problems, respectively. This inspiring masking approach offers insights for future learning of specific patterns, which can be easily and efficiently combined with other training methods and applied to various dLLMs. Our code is publicly available at https://anonymous.4open.science/r/DSFT-0FFB/

Ming Chen, Yuxuan Cheng, Xinwei He et al.

Integrating visible and infrared images into one high-quality image, also known as visible and infrared image fusion, is a challenging yet critical task for many downstream vision tasks. Most existing works utilize pretrained deep neural networks or design sophisticated frameworks with strong priors for this task, which may be unsuitable or lack flexibility. This paper presents SimpleFusion, a simple yet effective framework for visible and infrared image fusion. Our framework follows the decompose-and-fusion paradigm, where the visible and the infrared images are decomposed into reflectance and illumination components via Retinex theory and followed by the fusion of these corresponding elements. The whole framework is designed with two plain convolutional neural networks without downsampling, which can perform image decomposition and fusion efficiently. Moreover, we introduce decomposition loss and a detail-to-semantic loss to preserve the complementary information between the two modalities for fusion. We conduct extensive experiments on the challenging benchmarks, verifying the superiority of our method over previous state-of-the-arts. Code is available at \href{https://github.com/hxwxss/SimpleFusion-A-Simple-Fusion-Framework-for-Infrared-and-Visible-Images}{https://github.com/hxwxss/SimpleFusion-A-Simple-Fusion-Framework-for-Infrared-and-Visible-Images}

Ming Chen, Zhewei Wei, Bolin Ding et al.

Graph Neural Networks (GNN) is an emerging field for learning on non-Euclidean data. Recently, there has been increased interest in designing GNN that scales to large graphs. Most existing methods use "graph sampling" or "layer-wise sampling" techniques to reduce training time. However, these methods still suffer from degrading performance and scalability problems when applying to graphs with billions of edges. This paper presents GBP, a scalable GNN that utilizes a localized bidirectional propagation process from both the feature vectors and the training/testing nodes. Theoretical analysis shows that GBP is the first method that achieves sub-linear time complexity for both the precomputation and the training phases. An extensive empirical study demonstrates that GBP achieves state-of-the-art performance with significantly less training/testing time. Most notably, GBP can deliver superior performance on a graph with over 60 million nodes and 1.8 billion edges in less than half an hour on a single machine. The codes of GBP can be found at https://github.com/chennnM/GBP .

Ming Chen, Zhewei Wei, Zengfeng Huang et al.

Graph convolutional networks (GCNs) are a powerful deep learning approach for graph-structured data. Recently, GCNs and subsequent variants have shown superior performance in various application areas on real-world datasets. Despite their success, most of the current GCN models are shallow, due to the {\em over-smoothing} problem. In this paper, we study the problem of designing and analyzing deep graph convolutional networks. We propose the GCNII, an extension of the vanilla GCN model with two simple yet effective techniques: {\em Initial residual} and {\em Identity mapping}. We provide theoretical and empirical evidence that the two techniques effectively relieves the problem of over-smoothing. Our experiments show that the deep GCNII model outperforms the state-of-the-art methods on various semi- and full-supervised tasks. Code is available at https://github.com/chennnM/GCNII .

Xinyue Peng, Yanming Liu, Yihan Cang et al.

Solving non-convex resource allocation problems poses significant challenges in wireless communication systems, often beyond the capability of traditional optimization techniques. To address this issue, we propose LLM-OptiRA, the first framework that leverages large language models (LLMs) to automatically detect and transform non-convex components into solvable forms, enabling fully automated resolution of non-convex resource allocation problems in wireless communication systems. LLM-OptiRA not only simplifies problem-solving by reducing reliance on expert knowledge, but also integrates error correction and feasibility validation mechanisms to ensure robustness. Experimental results show that LLM-OptiRA achieves an execution rate of 96% and a success rate of 80% on GPT-4, significantly outperforming baseline approaches in complex optimization tasks across diverse scenarios.

Dexin Kong, Xu Yan, Ming Chen et al.

Different from traditional Business-to-Consumer e-commerce platforms~(e.g., Amazon), online fleamarket platforms~(e.g., Craigslist) mainly focus on individual sellers who are lack of time investment and business proficiency. Individual sellers often struggle with the bargaining process and thus the deal is unaccomplished. Recent advancements in Large Language Models(LLMs) demonstrate huge potential in various dialogue tasks, but those tasks are mainly in the form of passively following user's instruction. Bargaining, as a form of proactive dialogue task, represents a distinct art of dialogue considering the dynamism of environment and uncertainty of adversary strategies. In this paper, we propose an LLM-empowered bargaining agent designed for online fleamarket platform sellers, named as FishBargain. Specifically, FishBargain understands the chat context and product information, chooses both action and language skill considering possible adversary actions and generates utterances. FishBargain has been tested by thousands of individual sellers on one of the largest online fleamarket platforms~(Xianyu) in China. Both qualitative and quantitative experiments demonstrate that FishBargain can effectively help sellers make more deals.

Yikai Liu, Tushar K. Ghosh, Guang Lin et al.

Biased enhanced sampling methods utilizing collective variables (CVs) are powerful tools for sampling conformational ensembles. Due to high intrinsic dimensions, efficiently generating conformational ensembles for complex systems requires enhanced sampling on high-dimensional free energy surfaces. While methods like temperature-accelerated molecular dynamics (TAMD) can adopt many CVs in a simulation, unbiasing the simulation requires accurate modeling of a high-dimensional CV probability distribution, which is challenging for traditional density estimation techniques. Here we propose an unbiasing method based on the score-based diffusion model, a deep generative learning method that excels in density estimation across complex data landscapes. We test the score-based diffusion unbiasing method on TAMD simulations. The results demonstrate that this unbiasing approach significantly outperforms traditional unbiasing methods, and can generate accurate unbiased conformational ensembles for simulations with a number of CVs higher than usual ranges.

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.

Yanlong Peng, Zhigang Wang, Yisheng Zhang et al.

Task and Motion Planning (TAMP) is essential for robots to interact with the world and accomplish complex tasks. The TAMP problem involves a critical gap: exploring the robot's configuration parameters (such as chassis position and robotic arm joint angles) within continuous space to ensure that task-level global constraints are met while also enhancing the efficiency of subsequent motion planning. Existing methods still have significant room for improvement in terms of efficiency. Recognizing that robot kinematics is a key factor in motion planning, we propose a framework called the Robotic Kinematics Informed Neural Network (RobKiNet) as a bridge between task and motion layers. RobKiNet integrates kinematic knowledge into neural networks to train models capable of efficient configuration prediction. We designed a Chassis Motion Predictor(CMP) and a Full Motion Predictor(FMP) using RobKiNet, which employed two entirely different sets of forward and inverse kinematics constraints to achieve loosely coupled control and whole-body control, respectively. Experiments demonstrate that CMP and FMP can predict configuration parameters with 96.67% and 98% accuracy, respectively. That means that the corresponding motion planning can achieve a speedup of 24.24x and 153x compared to random sampling. Furthermore, RobKiNet demonstrates remarkable data efficiency. CMP only requires 1/71 and FMP only requires 1/15052 of the training data for the same prediction accuracy compared to other deep learning methods. These results demonstrate the great potential of RoboKiNet in robot applications.

Yikang Ding, Jiwen Liu, Wenyuan Zhang et al.

Recent advances in audio-driven avatar video generation have significantly enhanced audio-visual realism. However, existing methods treat instruction conditioning merely as low-level tracking driven by acoustic or visual cues, without modeling the communicative purpose conveyed by the instructions. This limitation compromises their narrative coherence and character expressiveness. To bridge this gap, we introduce Kling-Avatar, a novel cascaded framework that unifies multimodal instruction understanding with photorealistic portrait generation. Our approach adopts a two-stage pipeline. In the first stage, we design a multimodal large language model (MLLM) director that produces a blueprint video conditioned on diverse instruction signals, thereby governing high-level semantics such as character motion and emotions. In the second stage, guided by blueprint keyframes, we generate multiple sub-clips in parallel using a first-last frame strategy. This global-to-local framework preserves fine-grained details while faithfully encoding the high-level intent behind multimodal instructions. Our parallel architecture also enables fast and stable generation of long-duration videos, making it suitable for real-world applications such as digital human livestreaming and vlogging. To comprehensively evaluate our method, we construct a benchmark of 375 curated samples covering diverse instructions and challenging scenarios. Extensive experiments demonstrate that Kling-Avatar is capable of generating vivid, fluent, long-duration videos at up to 1080p and 48 fps, achieving superior performance in lip synchronization accuracy, emotion and dynamic expressiveness, instruction controllability, identity preservation, and cross-domain generalization. These results establish Kling-Avatar as a new benchmark for semantically grounded, high-fidelity audio-driven avatar synthesis.

Ranfei Chen, Ming Chen, Kaifei Wang

Diffusion Large Language Models (dLLMs) are rapidly emerging alongside autoregressive models as a powerful paradigm for complex reasoning, with reinforcement learning increasingly used for downstream alignment. Existing trajectory-based RL methods uniformly allocate policy gradients across denoising steps, implicitly treating all steps as equally important. We challenge this assumption by analyzing trajectories with several step-level metrics: entropy-based uncertainty, Confidence-Margin (CM) uncertainty, and Rate of Entropy Change (RoEC). These reveal structured "zones of confusion": transient spikes in uncertainty and instability that strongly predict final success or failure, while most steps remain stable. We propose Adaptive Trajectory Policy Optimization (ATPO), a lightweight step-selection strategy that dynamically reallocates gradient updates to these high-leverage steps without changing the RL objective, rewards, or compute budget. Using a hybrid RoEC+CM rule, ATPO delivers substantial gains in reasoning accuracy and training stability across benchmarks, showing that exploiting trajectory dynamics is key to advancing dLLM RL.

Ziwen He, Zhigang Wang, Yanlong Peng et al.

With the rapid development of the new energy vehicle industry, the efficient disassembly and recycling of power batteries have become a critical challenge for the circular economy. In current unstructured disassembly scenarios, the dynamic nature of the environment severely limits the robustness of robotic perception, posing a significant barrier to autonomous disassembly in industrial applications. This paper proposes a continual learning framework based on Neuro-Symbolic task and motion planning (TAMP) to enhance the adaptability of embodied intelligence systems in dynamic environments. Our approach integrates a multimodal perception cross-validation mechanism into a bidirectional reasoning flow: the forward working flow dynamically refines and optimizes action strategies, while the backward learning flow autonomously collects effective data from historical task executions to facilitate continual system learning, enabling self-optimization. Experimental results show that the proposed framework improves the task success rate in dynamic disassembly scenarios from 81.68% to 100%, while reducing the average number of perception misjudgments from 3.389 to 1.128. This research provides a new paradigm for enhancing the robustness and adaptability of embodied intelligence in complex industrial environments.

Issue Yishu Wang, Kakam Chong, Xiaofeng Wang et al.

In online second-hand marketplaces, multi-turn bargaining is a crucial part of seller-buyer interactions. Large Language Models (LLMs) can act as seller agents, negotiating with buyers on behalf of sellers under given business constraints. A critical ability for such agents is to track and accurately interpret cumulative buyer intents across long negotiations, which directly impacts bargaining effectiveness. We introduce a multi-turn evaluation framework for measuring the bargaining ability of seller agents in e-commerce dialogues. The framework tests whether an agent can extract and track buyer intents. Our contributions are: (1) a large-scale e-commerce bargaining benchmark spanning 622 categories, 9,892 products, and 3,014 tasks; (2) a turn-level evaluation framework grounded in Theory of Mind (ToM) with annotated buyer intents, moving beyond outcome-only metrics; and (3) an automated pipeline that extracts reliable intent from massive dialogue data.

Cong Chen, Ming Chen, Hoileong Lee et al.

Surface defect detection of steel, especially the recognition of multi-scale defects, has always been a major challenge in industrial manufacturing. Steel surfaces not only have defects of various sizes and shapes, which limit the accuracy of traditional image processing and detection methods in complex environments. However, traditional defect detection methods face issues of insufficient accuracy and high miss-detection rates when dealing with small target defects. To address this issue, this study proposes a detection framework based on deep learning, specifically YOLOv9s, combined with the C3Ghost module, SCConv module, and CARAFE upsampling operator, to improve detection accuracy and model performance. First, the SCConv module is used to reduce feature redundancy and optimize feature representation by reconstructing the spatial and channel dimensions. Second, the C3Ghost module is introduced to enhance the model's feature extraction ability by reducing redundant computations and parameter volume, thereby improving model efficiency. Finally, the CARAFE upsampling operator, which can more finely reorganize feature maps in a content-aware manner, optimizes the upsampling process and ensures detailed restoration of high-resolution defect regions. Experimental results demonstrate that the proposed model achieves higher accuracy and robustness in steel surface defect detection tasks compared to other methods, effectively addressing defect detection problems.

Yongjie Wang, Jonathan Cyril Leung, Ming Chen et al.

The population of older adults is steadily increasing, with a strong preference for aging-in-place rather than moving to care facilities. Consequently, supporting this growing demographic has become a significant global challenge. However, facilitating successful aging-in-place is challenging, requiring consideration of multiple factors such as data privacy, health status monitoring, and living environments to improve health outcomes. In this paper, we propose an unobtrusive sensor system designed for installation in older adults' homes. Using data from the sensors, our system constructs a digital twin, a virtual representation of events and activities that occurred in the home. The system uses neural network models and decision rules to capture residents' activities and living environments. This digital twin enables continuous health monitoring by providing actionable insights into residents' well-being. Our system is designed to be low-cost and privacy-preserving, with the aim of providing green and safe monitoring for the health of older adults. We have successfully deployed our system in two homes over a time period of two months, and our findings demonstrate the feasibility and effectiveness of digital twin technology in supporting independent living for older adults. This study highlights that our system could revolutionize elder care by enabling personalized interventions, such as lifestyle adjustments, medical treatments, or modifications to the residential environment, to enhance health outcomes.

Huiming Sun, Yikang Li, Kangning Yang et al.

Inpainting for real-world human and pedestrian removal in high-resolution video clips presents significant challenges, particularly in achieving high-quality outcomes, ensuring temporal consistency, and managing complex object interactions that involve humans, their belongings, and their shadows. In this paper, we introduce VIP (Video Inpainting Pipeline), a novel promptless video inpainting framework for real-world human removal applications. VIP enhances a state-of-the-art text-to-video model with a motion module and employs a Variational Autoencoder (VAE) for progressive denoising in the latent space. Additionally, we implement an efficient human-and-belongings segmentation for precise mask generation. Sufficient experimental results demonstrate that VIP achieves superior temporal consistency and visual fidelity across diverse real-world scenarios, surpassing state-of-the-art methods on challenging datasets. Our key contributions include the development of the VIP pipeline, a reference frame integration technique, and the Dual-Fusion Latent Segment Refinement method, all of which address the complexities of inpainting in long, high-resolution video sequences.

Xukun Zhou, Fengxin Li, Ming Chen et al.

Audio-driven human gesture synthesis is a crucial task with broad applications in virtual avatars, human-computer interaction, and creative content generation. Despite notable progress, existing methods often produce gestures that are coarse, lack expressiveness, and fail to fully align with audio semantics. To address these challenges, we propose ExGes, a novel retrieval-enhanced diffusion framework with three key designs: (1) a Motion Base Construction, which builds a gesture library using training dataset; (2) a Motion Retrieval Module, employing constrative learning and momentum distillation for fine-grained reference poses retreiving; and (3) a Precision Control Module, integrating partial masking and stochastic masking to enable flexible and fine-grained control. Experimental evaluations on BEAT2 demonstrate that ExGes reduces Fréchet Gesture Distance by 6.2\% and improves motion diversity by 5.3\% over EMAGE, with user studies revealing a 71.3\% preference for its naturalness and semantic relevance. Code will be released upon acceptance.

Ping Yu, Kaitao Song, Fengchen He et al.

The recently unprecedented advancements in Large Language Models (LLMs) have propelled the medical community by establishing advanced medical-domain models. However, due to the limited collection of medical datasets, there are only a few comprehensive benchmarks available to gauge progress in this area. In this paper, we introduce a new medical question-answering (QA) dataset that contains massive manual instruction for solving Traditional Chinese Medicine examination tasks, called TCMD. Specifically, our TCMD collects massive questions across diverse domains with their annotated medical subjects and thus supports us in comprehensively assessing the capability of LLMs in the TCM domain. Extensive evaluation of various general LLMs and medical-domain-specific LLMs is conducted. Moreover, we also analyze the robustness of current LLMs in solving TCM QA tasks by introducing randomness. The inconsistency of the experimental results also reveals the shortcomings of current LLMs in solving QA tasks. We also expect that our dataset can further facilitate the development of LLMs in the TCM area.

Jialin Yu, Huogen Wang, Ming Chen

We improved an existing end-to-end polyp detection model with better average precision validated by different data sets with trivial cost on detection speed. Our previous work on detecting polyps within colonoscopy provided an efficient end-to-end solution to alleviate doctor's examination overhead. However, our later experiments found this framework is not as robust as before as the condition of polyp capturing varies. In this work, we conducted several studies on data set, identifying main issues that causes low precision rate in the task of polyp detection. We used an optimized anchor generation methods to get better anchor box shape and more boxes are used for detection as we believe this is necessary for small object detection. An alternative backbone is used to compensate the heavy time cost introduced by dense anchor box regression. With use of the attention gate module, our model can achieve state-of-the-art polyp detection performance while still maintain real-time detection speed.

Christian Bock, François-Xavier Aubet, Jan Gasthaus et al.

We propose r-ssGPFA, an unsupervised online anomaly detection model for uni- and multivariate time series building on the efficient state space formulation of Gaussian processes. For high-dimensional time series, we propose an extension of Gaussian process factor analysis to identify the common latent processes of the time series, allowing us to detect anomalies efficiently in an interpretable manner. We gain explainability while speeding up computations by imposing an orthogonality constraint on the mapping from the latent to the observed. Our model's robustness is improved by using a simple heuristic to skip Kalman updates when encountering anomalous observations. We investigate the behaviour of our model on synthetic data and show on standard benchmark datasets that our method is competitive with state-of-the-art methods while being computationally cheaper.

Lin Guan, Xia Xiao, Ming Chen et al.

Feature selection has been an essential step in developing industry-scale deep Click-Through Rate (CTR) prediction systems. The goal of neural feature selection (NFS) is to choose a relatively small subset of features with the best explanatory power as a means to remove redundant features and reduce computational cost. Inspired by gradient-based neural architecture search (NAS) and network pruning methods, people have tackled the NFS problem with Gating approach that inserts a set of differentiable binary gates to drop less informative features. The binary gates are optimized along with the network parameters in an efficient end-to-end manner. In this paper, we analyze the gradient-based solution from an exploration-exploitation perspective and use empirical results to show that Gating approach might suffer from insufficient exploration. To improve the exploration capacity of gradient-based solutions, we propose a simple but effective ensemble learning approach, named Ensemble Gating. We choose two public datasets, namely Avazu and Criteo, to evaluate this approach. Our experiments show that, without adding any computational overhead or introducing any hyper-parameter (except the size of the ensemble), our method is able to consistently improve Gating approach and find a better subset of features on the two datasets with three different underlying deep CTR prediction models.

Yunhe Gao, Rui Huang, Yiwei Yang et al.

Radiotherapy is a treatment where radiation is used to eliminate cancer cells. The delineation of organs-at-risk (OARs) is a vital step in radiotherapy treatment planning to avoid damage to healthy organs. For nasopharyngeal cancer, more than 20 OARs are needed to be precisely segmented in advance. The challenge of this task lies in complex anatomical structure, low-contrast organ contours, and the extremely imbalanced size between large and small organs. Common segmentation methods that treat them equally would generally lead to inaccurate small-organ labeling. We propose a novel two-stage deep neural network, FocusNetv2, to solve this challenging problem by automatically locating, ROI-pooling, and segmenting small organs with specifically designed small-organ localization and segmentation sub-networks while maintaining the accuracy of large organ segmentation. In addition to our original FocusNet, we employ a novel adversarial shape constraint on small organs to ensure the consistency between estimated small-organ shapes and organ shape prior knowledge. Our proposed framework is extensively tested on both self-collected dataset of 1,164 CT scans and the MICCAI Head and Neck Auto Segmentation Challenge 2015 dataset, which shows superior performance compared with state-of-the-art head and neck OAR segmentation methods.

Chunyan Ji, Ming Chen, Bin Li et al.

We propose an approach of graph convolutional networks for robust infant cry classification. We construct non-fully connected graphs based on the similarities among the relevant nodes in both supervised and semi-supervised node classification with convolutional neural networks to consider the short-term and long-term effects of infant cry signals related to inner-class and inter-class messages. The approach captures the diversity of variations within infant cries, especially for limited training samples. The effectiveness of this approach is evaluated on Baby Chillanto Database and Baby2020 database. With as limited as 20% of labeled training data, our model outperforms that of CNN model with 80% labeled training data and the accuracy stably improves as the number of labeled training samples increases. The best results give significant improvements of 7.36% and 3.59% compared with the results of the CNN models on Baby Chillanto database and Baby2020 database respectively.

Fandong Meng, Jianhao Yan, Yijin Liu et al.

We participate in the WMT 2020 shared news translation task on Chinese to English. Our system is based on the Transformer (Vaswani et al., 2017a) with effective variants and the DTMT (Meng and Zhang, 2019) architecture. In our experiments, we employ data selection, several synthetic data generation approaches (i.e., back-translation, knowledge distillation, and iterative in-domain knowledge transfer), advanced finetuning approaches and self-bleu based model ensemble. Our constrained Chinese to English system achieves 36.9 case-sensitive BLEU score, which is the highest among all submissions.

Luyang Kong, Lifan Chen, Ming Chen et al.

Anomaly detectors are often designed to catch statistical anomalies. End-users typically do not have interest in all of the detected outliers, but only those relevant to their application. Given an existing black-box sequential anomaly detector, this paper proposes a method to improve its user relevancy using a small number of human feedback. As our first contribution, the method is agnostic to the detector: it only assumes access to its anomaly scores, without requirement on any additional information inside it. Inspired by a fact that anomalies are of different types, our approach identifies these types and utilizes user feedback to assign relevancy to types. This relevancy score, as our second contribution, is used to adjust the subsequent anomaly selection process. Empirical results on synthetic and real-world datasets show that our approach yields significant improvements on precision and recall over a range of anomaly detectors.

Tao Jin, Siyu Huang, Ming Chen et al.

In this paper, we focus on the problem of applying the transformer structure to video captioning effectively. The vanilla transformer is proposed for uni-modal language generation task such as machine translation. However, video captioning is a multimodal learning problem, and the video features have much redundancy between different time steps. Based on these concerns, we propose a novel method called sparse boundary-aware transformer (SBAT) to reduce the redundancy in video representation. SBAT employs boundary-aware pooling operation for scores from multihead attention and selects diverse features from different scenarios. Also, SBAT includes a local correlation scheme to compensate for the local information loss brought by sparse operation. Based on SBAT, we further propose an aligned cross-modal encoding scheme to boost the multimodal interaction. Experimental results on two benchmark datasets show that SBAT outperforms the state-of-the-art methods under most of the metrics.

Xiangyu Zhao, Chong Wang, Ming Chen et al.

Deep learning based recommender systems (DLRSs) often have embedding layers, which are utilized to lessen the dimensionality of categorical variables (e.g. user/item identifiers) and meaningfully transform them in the low-dimensional space. The majority of existing DLRSs empirically pre-define a fixed and unified dimension for all user/item embeddings. It is evident from recent researches that different embedding sizes are highly desired for different users/items according to their popularity. However, manually selecting embedding sizes in recommender systems can be very challenging due to the large number of users/items and the dynamic nature of their popularity. Thus, in this paper, we propose an AutoML based end-to-end framework (AutoEmb), which can enable various embedding dimensions according to the popularity in an automated and dynamic manner. To be specific, we first enhance a typical DLRS to allow various embedding dimensions; then we propose an end-to-end differentiable framework that can automatically select different embedding dimensions according to user/item popularity; finally we propose an AutoML based optimization algorithm in a streaming recommendation setting. The experimental results based on widely used benchmark datasets demonstrate the effectiveness of the AutoEmb framework.

Yunhe Gao, Rui Huang, Ming Chen et al.

In this paper, we propose an end-to-end deep neural network for solving the problem of imbalanced large and small organ segmentation in head and neck (HaN) CT images. To conduct radiotherapy planning for nasopharyngeal cancer, more than 10 organs-at-risk (normal organs) need to be precisely segmented in advance. However, the size ratio between large and small organs in the head could reach hundreds. Directly using such imbalanced organ annotations to train deep neural networks generally leads to inaccurate small-organ label maps. We propose a novel end-to-end deep neural network to solve this challenging problem by automatically locating, ROI-pooling, and segmenting small organs with specifically designed small-organ sub-networks while maintaining the accuracy of large organ segmentation. A strong main network with densely connected atrous spatial pyramid pooling and squeeze-and-excitation modules is used for segmenting large organs, where large organs' label maps are directly output. For small organs, their probabilistic locations instead of label maps are estimated by the main network. High-resolution and multi-scale feature volumes for each small organ are ROI-pooled according to their locations and are fed into small-organ networks for accurate segmenting small organs. Our proposed network is extensively tested on both collected real data and the \emph{MICCAI Head and Neck Auto Segmentation Challenge 2015} dataset, and shows superior performance compared with state-of-the-art segmentation methods.

Jing Zhang, Ming Chen

Collective variable (CV) or order parameter based enhanced sampling algorithms have achieved great success due to their ability to efficiently explore the rough potential energy landscapes of complex systems. However, the degeneracy of microscopic configurations, originating from the orthogonal space perpendicular to the CVs, is likely to shadow "hidden barriers" and greatly reduce the efficiency of CV-based sampling. Here we demonstrate that systematic machine learning CV, through enhanced sampling, can iteratively lift such degeneracies on the fly. We introduce an active learning scheme that consists of a parametric CV learner based on deep neural network and a CV-based enhanced sampler. Our active enhanced sampling (AES) algorithm is capable of identifying the least informative regions based on a historical sample, forming a positive feedback loop between the CV learner and sampler. This approach is able to globally preserve kinetic characteristics by incrementally enhancing both sample completeness and CV quality.