Honggang Zhang

Runqi Qiao, Qiuna Tan, Guanting Dong et al.

Visual mathematical reasoning, as a fundamental visual reasoning ability, has received widespread attention from the Large Multimodal Models (LMMs) community. Existing benchmarks, such as MathVista and MathVerse, focus more on the result-oriented performance but neglect the underlying principles in knowledge acquisition and generalization. Inspired by human-like mathematical reasoning, we introduce WE-MATH, the first benchmark specifically designed to explore the problem-solving principles beyond end-to-end performance. We meticulously collect and categorize 6.5K visual math problems, spanning 67 hierarchical knowledge concepts and five layers of knowledge granularity. We decompose composite problems into sub-problems according to the required knowledge concepts and introduce a novel four-dimensional metric, namely Insufficient Knowledge (IK), Inadequate Generalization (IG), Complete Mastery (CM), and Rote Memorization (RM), to hierarchically assess inherent issues in LMMs' reasoning process. With WE-MATH, we conduct a thorough evaluation of existing LMMs in visual mathematical reasoning and reveal a negative correlation between solving steps and problem-specific performance. We confirm the IK issue of LMMs can be effectively improved via knowledge augmentation strategies. More notably, the primary challenge of GPT-4o has significantly transitioned from IK to IG, establishing it as the first LMM advancing towards the knowledge generalization stage. In contrast, other LMMs exhibit a marked inclination towards Rote Memorization - they correctly solve composite problems involving multiple knowledge concepts yet fail to answer sub-problems. We anticipate that WE-MATH will open new pathways for advancements in visual mathematical reasoning for LMMs. The WE-MATH data and evaluation code are available at https://github.com/We-Math/We-Math.

Yuntao Liu, Qian Huang, Rongpeng Li et al.

Collaborative perception by leveraging the shared semantic information plays a crucial role in overcoming the individual limitations of isolated agents. However, existing collaborative perception methods tend to focus solely on the spatial features of semantic information, while neglecting the importance of the temporal dimension. Consequently, the potential benefits of collaboration remain underutilized. In this article, we propose Select2Col, a novel collaborative perception framework that takes into account the \underline{s}patial-t\underline{e}mpora\underline{l} importanc\underline{e} of semanti\underline{c} informa\underline{t}ion. Within the Select2Col, we develop a collaborator selection method that utilizes a lightweight graph neural network (GNN) to estimate the importance of semantic information (IoSI) of each collaborator in enhancing perception performance, thereby identifying contributive collaborators while excluding those that potentially bring negative impact. Moreover, we present a semantic information fusion algorithm called HPHA (historical prior hybrid attention), which integrates multi-scale attention and short-term attention modules to capture the IoSI in feature representation from the spatial and temporal dimensions respectively, and assigns IoSI-consistent weights for efficient fusion of information from selected collaborators. Extensive experiments on three open datasets demonstrate that our proposed Select2Col significantly improves the perception performance compared to state-of-the-art approaches. The code associated with this research is publicly available at https://github.com/huangqzj/Select2Col/.

Yuxuan Chen, Rongpeng Li, Zhifeng Zhao et al.

Large language models (LLMs) have triggered tremendous success to empower our daily life by generative information. The personalization of LLMs could further contribute to their applications due to better alignment with human intents. Towards personalized generative services, a collaborative cloud-edge methodology is promising, as it facilitates the effective orchestration of heterogeneous distributed communication and computing resources. In this article, we put forward NetGPT to capably synergize appropriate LLMs at the edge and the cloud based on their computing capacity. In addition, edge LLMs could efficiently leverage location-based information for personalized prompt completion, thus benefiting the interaction with the cloud LLM. In particular, we present the feasibility of NetGPT by leveraging low-rank adaptation-based fine-tuning of open-source LLMs (i.e., GPT-2-base model and LLaMA model), and conduct comprehensive numerical comparisons with alternative cloud-edge collaboration or cloud-only techniques, so as to demonstrate the superiority of NetGPT. Subsequently, we highlight the essential changes required for an artificial intelligence (AI)-native network architecture towards NetGPT, with emphasis on deeper integration of communications and computing resources and careful calibration of logical AI workflow. Furthermore, we demonstrate several benefits of NetGPT, which come as by-products, as the edge LLMs' capability to predict trends and infer intents promises a unified solution for intelligent network management & orchestration. We argue that NetGPT is a promising AI-native network architecture for provisioning beyond personalized generative services.

Shiqiang Lang, Jing Liu, Haoyang He et al.

Multimodal Large Language Models (MLLMs) have advanced image and video understanding and can increasingly handle longer visual inputs. Long-horizon tasks such as autonomous driving and robotic navigation require more than recognizing the current view, as models must remember and retrieve previously observed spatial layouts, routes, viewpoint changes, and object states. To evaluate this capability, we introduce LongSpace-Bench, a room-tour video benchmark for long-horizon spatial memory, covering scene perception, spatial relations, and spatial memory. In this work, we further propose LongSpace, a memory framework for long-video spatial reasoning. LongSpace models long videos as sequential chunks, incorporates 3D structural cues into early decoder layers, and constructs layer-aware memory for question-guided retrieval. Experiments on multiple spatial reasoning benchmarks show that LongSpace improves long-video spatial understanding, further demonstrating explicit spatial memory as a key capability for long-horizon video MLLMs.

Kun Lu, Rongpeng Li, Honggang Zhang

Continuous one-to-many mapping is a less investigated yet important task in both low-level visions and neural image translation. In this paper, we present a new formulation called MonoPix, an unsupervised and contrastive continuous modulation model, and take a step further to enable a pixel-level spatial control which is critical but can not be properly handled previously. The key feature of this work is to model the monotonicity between controlling signals and the domain discriminator with a novel contrastive modulation framework and corresponding monotonicity constraints. We have also introduced a selective inference strategy with logarithmic approximation complexity and support fast domain adaptations. The state-of-the-art performance is validated on a variety of continuous mapping tasks, including AFHQ cat-dog and Yosemite summer-winter translation. The introduced approach also helps to provide a new solution for many low-level tasks like low-light enhancement and natural noise generation, which is beyond the long-established practice of one-to-one training and inference. Code is available at https://github.com/lukun199/MonoPix.

Zhilin Lu, Rongpeng Li, Kun Lu et al.

Along with the springing up of the semantics-empowered communication (SemCom) research, it is now witnessing an unprecedentedly growing interest towards a wide range of aspects (e.g., theories, applications, metrics and implementations) in both academia and industry. In this work, we primarily aim to provide a comprehensive survey on both the background and research taxonomy, as well as a detailed technical tutorial. Specifically, we start by reviewing the literature and answering the "what" and "why" questions in semantic transmissions. Afterwards, we present the ecosystems of SemCom, including history, theories, metrics, datasets and toolkits, on top of which the taxonomy for research directions is presented. Furthermore, we propose to categorize the critical enabling techniques by explicit and implicit reasoning-based methods, and elaborate on how they evolve and contribute to modern content & channel semantics-empowered communications. Besides reviewing and summarizing the latest efforts in SemCom, we discuss the relations with other communication levels (e.g., conventional communications) from a holistic and unified viewpoint. Subsequently, in order to facilitate future developments and industrial applications, we also highlight advanced practical techniques for boosting semantic accuracy, robustness, and large-scale scalability, just to mention a few. Finally, we discuss the technical challenges that shed light on future research opportunities.

Xianfu Chen, Zhifeng Zhao, Shiwen Mao et al.

The age of information metric fails to correctly describe the intrinsic semantics of a status update. In an intelligent reflecting surface-aided cooperative relay communication system, we propose the age of semantics (AoS) for measuring semantics freshness of the status updates. Specifically, we focus on the status updating from a source node (SN) to the destination, which is formulated as a Markov decision process (MDP). The objective of the SN is to maximize the expected satisfaction of AoS and energy consumption under the maximum transmit power constraint. To seek the optimal control policy, we first derive an online deep actor-critic (DAC) learning scheme under the on-policy temporal difference learning framework. However, implementing the online DAC in practice poses the key challenge in infinitely repeated interactions between the SN and the system, which can be dangerous particularly during the exploration. We then put forward a novel offline DAC scheme, which estimates the optimal control policy from a previously collected dataset without any further interactions with the system. Numerical experiments verify the theoretical results and show that our offline DAC scheme significantly outperforms the online DAC scheme and the most representative baselines in terms of mean utility, demonstrating strong robustness to dataset quality.

Jianhang Zhu, Rongpeng Li, Guoru Ding et al.

Along with the fast development of network technology and the rapid growth of network equipment, the data throughput is sharply increasing. To handle the problem of backhaul bottleneck in cellular network and satisfy people's requirements about latency, the network architecture like information-centric network (ICN) intends to proactively keep limited popular content at the edge of network based on predicted results. Meanwhile, the interactions between the content (e.g., deep neural network models, Wikipedia-alike knowledge base) and users could be regarded as a dynamic bipartite graph. In this paper, to maximize the cache hit rate, we leverage an effective dynamic graph neural network (DGNN) to jointly learn the structural and temporal patterns embedded in the bipartite graph. Furthermore, in order to have deeper insights into the dynamics within the evolving graph, we propose an age of information (AoI) based attention mechanism to extract valuable historical information while avoiding the problem of message staleness. Combining this aforementioned prediction model, we also develop a cache selection algorithm to make caching decisions in accordance with the prediction results. Extensive results demonstrate that our model can obtain a higher prediction accuracy than other state-of-the-art schemes in two real-world datasets. The results of hit rate further verify the superiority of the caching policy based on our proposed model over other traditional ways.

Bingyan Wang, Rongpeng Li, Jianhang Zhu et al.

In recent years, with the rapid development of deep learning and natural language processing technologies, semantic communication has become a topic of great interest in the field of communication. Although existing deep learning-based semantic communication approaches have shown many advantages, they still do not make sufficient use of prior knowledge. Moreover, most existing semantic communication methods focus on the semantic encoding at the transmitter side, while we believe that the semantic decoding capability of the receiver should also be concerned. In this paper, we propose a knowledge enhanced semantic communication framework in which the receiver can more actively utilize the facts in the knowledge base for semantic reasoning and decoding, on the basis of only affecting the parameters rather than the structure of the neural networks at the transmitter side. Specifically, we design a transformer-based knowledge extractor to find relevant factual triples for the received noisy signal. Extensive simulation results on the WebNLG dataset demonstrate that the proposed receiver yields superior performance on top of the knowledge graph enhanced decoding.

Yue Sun, Honggang Zhang, Zhuoming Huang et al.

Recent research has shown the effectiveness of mmWave radar sensing for object detection in low visibility environments, which makes it an ideal technique in autonomous navigation systems. In this paper, we introduce Radar to Point Cloud (R2P), a deep learning model that generates smooth, dense, and highly accurate point cloud representation of a 3D object with fine geometry details, based on rough and sparse point clouds with incorrect points obtained from mmWave radar. These input point clouds are converted from the 2D depth images that are generated from raw mmWave radar sensor data, characterized by inconsistency, and orientation and shape errors. R2P utilizes an architecture of two sequential deep learning encoder-decoder blocks to extract the essential features of those radar-based input point clouds of an object when observed from multiple viewpoints, and to ensure the internal consistency of a generated output point cloud and its accurate and detailed shape reconstruction of the original object. We implement R2P to replace Stage 2 of our recently proposed 3DRIMR (3D Reconstruction and Imaging via mmWave Radar) system. Our experiments demonstrate the significant performance improvement of R2P over the popular existing methods such as PointNet, PCN, and the original 3DRIMR design.

Yaoting Wang, Peiwen Sun, Yuanchao Li et al.

The Audio-Visual Segmentation (AVS) task aims to segment sounding objects in the visual space using audio cues. However, in this work, it is recognized that previous AVS methods show a heavy reliance on detrimental segmentation preferences related to audible objects, rather than precise audio guidance. We argue that the primary reason is that audio lacks robust semantics compared to vision, especially in multi-source sounding scenes, resulting in weak audio guidance over the visual space. Motivated by the the fact that text modality is well explored and contains rich abstract semantics, we propose leveraging text cues from the visual scene to enhance audio guidance with the semantics inherent in text. Our approach begins by obtaining scene descriptions through an off-the-shelf image captioner and prompting a frozen large language model to deduce potential sounding objects as text cues. Subsequently, we introduce a novel semantics-driven audio modeling module with a dynamic mask to integrate audio features with text cues, leading to representative sounding object features. These features not only encompass audio cues but also possess vivid semantics, providing clearer guidance in the visual space. Experimental results on AVS benchmarks validate that our method exhibits enhanced sensitivity to audio when aided by text cues, achieving highly competitive performance on all three subsets. Project page: \href{https://github.com/GeWu-Lab/Sounding-Object-Segmentation-Preference}{https://github.com/GeWu-Lab/Sounding-Object-Segmentation-Preference}

Xianfu Chen, Celimuge Wu, Yi Shen et al.

This article investigates a control system within the context of six-generation wireless networks. The control performance optimization confronts the technical challenges that arise from the intricate interactions between communication and control sub-systems, asking for a co-design. Accounting for the system dynamics, we formulate the sequential co-design decision-makings of communication and control over the discrete time horizon as a Markov decision process, for which a practical offline learning framework is proposed. Our proposed framework integrates large language models into the elements of reinforcement learning. We present a case study on the age of semantics-aware communication and control co-design to showcase the potentials from our proposed learning framework. Furthermore, we discuss the open issues remaining to make our proposed offline learning framework feasible for real-world implementations, and highlight the research directions for future explorations.

Zhiyu Qu, Lan Yang, Honggang Zhang et al.

Creating multi-view wire art (MVWA), a static 3D sculpture with diverse interpretations from different viewpoints, is a complex task even for skilled artists. In response, we present DreamWire, an AI system enabling everyone to craft MVWA easily. Users express their vision through text prompts or scribbles, freeing them from intricate 3D wire organisation. Our approach synergises 3D Bézier curves, Prim's algorithm, and knowledge distillation from diffusion models or their variants (e.g., ControlNet). This blend enables the system to represent 3D wire art, ensuring spatial continuity and overcoming data scarcity. Extensive evaluation and analysis are conducted to shed insight on the inner workings of the proposed system, including the trade-off between connectivity and visual aesthetics.

Ruolin Yang, Da Li, Conghui Hu et al.

Reference-based video object segmentation is an emerging topic which aims to segment the corresponding target object in each video frame referred by a given reference, such as a language expression or a photo mask. However, language expressions can sometimes be vague in conveying an intended concept and ambiguous when similar objects in one frame are hard to distinguish by language. Meanwhile, photo masks are costly to annotate and less practical to provide in a real application. This paper introduces a new task of sketch-based video object segmentation, an associated benchmark, and a strong baseline. Our benchmark includes three datasets, Sketch-DAVIS16, Sketch-DAVIS17 and Sketch-YouTube-VOS, which exploit human-drawn sketches as an informative yet low-cost reference for video object segmentation. We take advantage of STCN, a popular baseline of semi-supervised VOS task, and evaluate what the most effective design for incorporating a sketch reference is. Experimental results show sketch is more effective yet annotation-efficient than other references, such as photo masks, language and scribble.

Siyu Tong, Xiaoxue Yu, Rongpeng Li et al.

Semantic communication (SemCom) demonstrates strong superiority over conventional bit-level accurate transmission, by only attempting to recover the essential semantic information of data. In this paper, in order to tackle the non-differentiability of channels, we propose an alternate learning based SemCom system for visual transmission, named SparseSBC. Specially, SparseSBC leverages two separate Deep Neural Network (DNN)-based models at the transmitter and receiver, respectively, and learns the encoding and decoding in an alternate manner, rather than the joint optimization in existing literature, so as to solving the non-differentiability in the channel. In particular, a ``self-critic" training scheme is leveraged for stable training. Moreover, the DNN-based transmitter generates a sparse set of bits in deduced ``semantic bases", by further incorporating a binary quantization module on the basis of minimal detrimental effect to the semantic accuracy. Extensive simulation results validate that SparseSBC shows efficient and effective transmission performance under various channel conditions, and outperforms typical SemCom solutions.

Yuming Xiang, Sizhao Li, Rongpeng Li et al.

Adaptive multi-agent formation control, which requires the formation to flexibly adjust along with the quantity variations of agents in a decentralized manner, belongs to one of the most challenging issues in multi-agent systems, especially under communication-limited constraints. In this paper, we propose a novel Consensus-based Decentralized Adaptive Formation (Cons-DecAF) framework. Specifically, we develop a novel multi-agent reinforcement learning method, Consensus-oriented Multi-Agent Communication (ConsMAC), to enable agents to perceive global information and establish the consensus from local states by effectively aggregating neighbor messages. Afterwards, we leverage policy distillation to accomplish the adaptive formation adjustment. Meanwhile, instead of pre-assigning specific positions of agents, we employ a displacement-based formation by Hausdorff distance to significantly improve the formation efficiency. The experimental results through extensive simulations validate that the proposed method has achieved outstanding performance in terms of both speed and stability.

Peiwen Sun, Shanshan Zhang, Zishan Liu et al.

It has already been observed that audio-visual embedding is more robust than uni-modality embedding for person verification. Here, we proposed a novel audio-visual strategy that considers aggregators from a fusion perspective. First, we introduced weight-enhanced attentive statistics pooling for the first time in face verification. We find that a strong correlation exists between modalities during pooling, so joint attentive pooling is proposed which contains cycle consistency to learn the implicit inter-frame weight. Finally, each modality is fused with a gated attention mechanism to gain robust audio-visual embedding. All the proposed models are trained on the VoxCeleb2 dev dataset and the best system obtains 0.18%, 0.27%, and 0.49% EER on three official trial lists of VoxCeleb1 respectively, which is to our knowledge the best-published results for person verification.

Ziqiong Wang, Tianqi Ren, Rongpeng Li et al.

Separate Source-Channel Coding (SSCC) remains attractive for text transmission due to its modularity and compatibility with mature entropy coders and powerful channel codes. However, SSCC often suffers from a pronounced cliff effect in low Signal-to-Noise Ratio (SNR) regimes, where residual bit errors after channel decoding can catastrophically break lossless source decoding, especially for Arithmetic Coding (AC) driven by Large Language Models (LLMs). This paper proposes a receiver-side In-Context Decoding (ICD) framework that enhances SSCC robustness without modifying the transmitter. ICD leverages an Error Correction Code Transformer (ECCT) to obtain bit-wise reliability for the decoded information bits. Based on the context-consistent bitstream, ICD constructs a confidence-ranked candidate pool via reliability-guided bit flipping, samples a compact yet diverse subset of candidates, and applies an LLM-based arithmetic decoder to obtain both reconstructions and sequence-level log-likelihoods. A reliability-likelihood fusion rule then selects the final output. We further provide theoretical guarantees on the stability and convergence of the proposed sampling procedure. Extensive experiments over Additive White Gaussian Noise (AWGN) and Rayleigh fading channels demonstrate consistent gains compared with conventional SSCC baselines and representative Joint Source-Channel Coding (JSCC) schemes.

Yaoting Wang, Peiwen Sun, Dongzhan Zhou et al.

Traditional reference segmentation tasks have predominantly focused on silent visual scenes, neglecting the integral role of multimodal perception and interaction in human experiences. In this work, we introduce a novel task called Reference Audio-Visual Segmentation (Ref-AVS), which seeks to segment objects within the visual domain based on expressions containing multimodal cues. Such expressions are articulated in natural language forms but are enriched with multimodal cues, including audio and visual descriptions. To facilitate this research, we construct the first Ref-AVS benchmark, which provides pixel-level annotations for objects described in corresponding multimodal-cue expressions. To tackle the Ref-AVS task, we propose a new method that adequately utilizes multimodal cues to offer precise segmentation guidance. Finally, we conduct quantitative and qualitative experiments on three test subsets to compare our approach with existing methods from related tasks. The results demonstrate the effectiveness of our method, highlighting its capability to precisely segment objects using multimodal-cue expressions. Dataset is available at \href{https://gewu-lab.github.io/Ref-AVS}{https://gewu-lab.github.io/Ref-AVS}.

Sizhao Li, Yuming Xiang, Rongpeng Li et al.

Multi-Robot System (MRS) has garnered widespread research interest and fostered tremendous interesting applications, especially in cooperative control fields. Yet little light has been shed on the compound ability of formation, monitoring and defence in decentralized large-scale MRS for pursuit avoidance, which puts stringent requirements on the capability of coordination and adaptability. In this paper, we put forward a decentralized Imitation learning based Alternative Multi-Agent Proximal Policy Optimization (IA-MAPPO) algorithm to provide a flexible and communication-economic solution to execute the pursuit avoidance task in well-formed swarm. In particular, a policy-distillation based MAPPO executor is firstly devised to capably accomplish and swiftly switch between multiple formations in a centralized manner. Furthermore, we utilize imitation learning to decentralize the formation controller, so as to reduce the communication overheads and enhance the scalability. Afterwards, alternative training is leveraged to compensate the performance loss incurred by decentralization. The simulation results validate the effectiveness of IA-MAPPO and extensive ablation experiments further show the performance comparable to a centralized solution with significant decrease in communication overheads.

Yue Sun, Zhuoming Huang, Honggang Zhang et al.

In this paper, we explore the feasibility of utilizing a mmWave radar sensor installed on a UAV to reconstruct the 3D shapes of multiple objects in a space. The UAV hovers at various locations in the space, and its onboard radar senor collects raw radar data via scanning the space with Synthetic Aperture Radar (SAR) operation. The radar data is sent to a deep neural network model, which outputs the point cloud reconstruction of the multiple objects in the space. We evaluate two different models. Model 1 is our recently proposed 3DRIMR/R2P model, and Model 2 is formed by adding a segmentation stage in the processing pipeline of Model 1. Our experiments have demonstrated that both models are promising in solving the multiple object reconstruction problem. We also show that Model 2, despite producing denser and smoother point clouds, can lead to higher reconstruction loss or even loss of objects. In addition, we find that both models are robust to the highly noisy radar data obtained by unstable SAR operation due to the instability or vibration of a small UAV hovering at its intended scanning point. Our exploratory study has shown a promising direction of applying mmWave radar sensing in 3D object reconstruction.

Peiwen Sun, Honggang Zhang, Di Hu

Community researchers have developed a range of advanced audio-visual segmentation models aimed at improving the quality of sounding objects' masks. While masks created by these models may initially appear plausible, they occasionally exhibit anomalies with incorrect grounding logic. We attribute this to real-world inherent preferences and distributions as a simpler signal for learning than the complex audio-visual grounding, which leads to the disregard of important modality information. Generally, the anomalous phenomena are often complex and cannot be directly observed systematically. In this study, we made a pioneering effort with the proper synthetic data to categorize and analyze phenomena as two types "audio priming bias" and "visual prior" according to the source of anomalies. For audio priming bias, to enhance audio sensitivity to different intensities and semantics, a perception module specifically for audio perceives the latent semantic information and incorporates information into a limited set of queries, namely active queries. Moreover, the interaction mechanism related to such active queries in the transformer decoder is customized to adapt to the need for interaction regulating among audio semantics. For visual prior, multiple contrastive training strategies are explored to optimize the model by incorporating a biased branch, without even changing the structure of the model. During experiments, observation demonstrates the presence and the impact that has been produced by the biases of the existing model. Finally, through experimental evaluation of AVS benchmarks, we demonstrate the effectiveness of our methods in handling both types of biases, achieving competitive performance across all three subsets.

Minghan Yang, Lan Yang, Ke Li et al.

Reconstructing dynamic visual experiences from brain activity provides a compelling avenue for exploring the neural mechanisms of human visual perception. While recent progress in fMRI-based image reconstruction has been notable, extending this success to video reconstruction remains a significant challenge. Current fMRI-to-video reconstruction approaches consistently encounter two major shortcomings: (i) inconsistent visual representations of salient objects across frames, leading to appearance mismatches; (ii) poor temporal coherence, resulting in motion misalignment or abrupt frame transitions. To address these limitations, we introduce SemVideo, a novel fMRI-to-video reconstruction framework guided by hierarchical semantic information. At the core of SemVideo is SemMiner, a hierarchical guidance module that constructs three levels of semantic cues from the original video stimulus: static anchor descriptions, motion-oriented narratives, and holistic summaries. Leveraging this semantic guidance, SemVideo comprises three key components: a Semantic Alignment Decoder that aligns fMRI signals with CLIP-style embeddings derived from SemMiner, a Motion Adaptation Decoder that reconstructs dynamic motion patterns using a novel tripartite attention fusion architecture, and a Conditional Video Render that leverages hierarchical semantic guidance for video reconstruction. Experiments conducted on the CC2017 and HCP datasets demonstrate that SemVideo achieves superior performance in both semantic alignment and temporal consistency, setting a new state-of-the-art in fMRI-to-video reconstruction.

Karmesh Siddharam Chaudhari, Youxiang Zhu, Amy Feng et al.

The increasing use of Online Vision Language Models (OVLMs) for processing images has introduced significant privacy risks, as individuals frequently upload images for various utilities, unaware of the potential for privacy violations. Images contain relationships that relate to Personally Identifiable Information (PII), where even seemingly harmless details can indirectly reveal sensitive information through surrounding clues. This paper explores the critical issue of PII disclosure in images uploaded to OVLMs and its implications for user privacy. We investigate how the extraction of contextual relationships from images can lead to direct (explicit) or indirect (implicit) exposure of PII, significantly compromising personal privacy. Furthermore, we propose methods to protect privacy while preserving the intended utility of the images in Vision Language Model (VLM)-based applications. Our evaluation demonstrates the efficacy of these techniques, highlighting the delicate balance between maintaining utility and protecting privacy in online image processing environments. Index Terms-Personally Identifiable Information (PII), Privacy, Utility, privacy concerns, sensitive information

Hong Li, Zhen Zhou, Honggang Zhang et al.

Data-parallel (DP) training with synchronous all-reduce is a dominant paradigm for full-parameter fine-tuning of large language models (LLMs). While parameter synchronization guarantees numerical equivalence of model weights after each iteration, it does not necessarily imply alignment of worker-level optimization dynamics before gradient aggregation. This paper identifies and studies this latent mismatch, termed \emph{silent inconsistency}, where cross-worker divergence in losses and gradients can remain invisible under conventional aggregated monitoring signals. We propose a lightweight, model-agnostic diagnostic framework that quantifies worker-level consistency using training signals readily available in standard pipelines. Specifically, we introduce three complementary metrics: loss dispersion, gradient-norm dispersion, and gradient-direction consistency measured by inter-worker cosine similarity. The proposed metrics incur negligible overhead and require no modification to model architecture, synchronization mechanisms, or optimization algorithms. We validate the framework by fully fine-tuning the 1B-parameter \texttt{openPangu-Embedded-1B-V1.1} model on the \texttt{tatsu-lab/alpaca} dataset using an 8-NPU DP setup, under controlled perturbations of cross-rank stochasticity. Experimental results show that progressively desynchronized data shuffling and random seeds lead to substantial increases in loss/gradient dispersion and reduced directional alignment, despite smooth globally averaged loss curves. These findings demonstrate that the proposed indicators provide actionable visibility into hidden instability modes in large-scale DP fine-tuning, enabling more reliable diagnosis and configuration assessment.

Haoyang He, Zihua Rong, Kun Ji et al.

Reinforcement learning (RL) has recently become the dominant paradigm for strengthening the reasoning abilities of large language models (LLMs). Yet the rule-based reward functions commonly used on mathematical or programming benchmarks assess only answer format and correctness, providing no signal as to whether the induced Chain-of-Thought (CoT) actually improves the answer. Furthermore, such task-specific training offers limited control over logical depth and therefore may fail to reveal a model's genuine reasoning capacity. We propose Dynamic Reasoning Efficiency Reward (DRER) -- a plug-and-play RL reward framework that reshapes both reward and advantage signals. (i) A Reasoning Quality Reward assigns fine-grained credit to those reasoning chains that demonstrably raise the likelihood of the correct answer, directly incentivising the trajectories with beneficial CoT tokens. (ii) A Dynamic Length Advantage decays the advantage of responses whose length deviates from a validation-derived threshold, stabilising training. To facilitate rigorous assessment, we also release Logictree, a dynamically constructed deductive reasoning dataset that functions both as RL training data and as a comprehensive benchmark. Experiments confirm the effectiveness of DRER: our 7B model attains GPT-o3-mini level performance on Logictree with 400 trianing steps, while the average confidence of CoT-augmented answers rises by 30%. The model further exhibits generalisation across diverse logical-reasoning datasets, and the mathematical benchmark AIME24. These results illuminate how RL shapes CoT behaviour and chart a practical path toward enhancing formal-reasoning skills in large language models. All code and data are available in repository https://github.com/Henryhe09/DRER.

Lan Yang, Kaiyue Pang, Honggang Zhang et al.

As lovely as bunnies are, your sketched version would probably not do them justice (Fig.~\ref{fig:intro}). This paper recognises this very problem and studies sketch quality assessment for the first time -- letting you find these badly drawn ones. Our key discovery lies in exploiting the magnitude ($L_2$ norm) of a sketch feature as a quantitative quality metric. We propose Geometry-Aware Classification Layer (GACL), a generic method that makes feature-magnitude-as-quality-metric possible and importantly does it without the need for specific quality annotations from humans. GACL sees feature magnitude and recognisability learning as a dual task, which can be simultaneously optimised under a neat cross-entropy classification loss with theoretic guarantee. This gives GACL a nice geometric interpretation (the better the quality, the easier the recognition), and makes it agnostic to both network architecture changes and the underlying sketch representation. Through a large scale human study of 160,000 \doublecheck{trials}, we confirm the agreement between our GACL-induced metric and human quality perception. We further demonstrate how such a quality assessment capability can for the first time enable three practical sketch applications. Interestingly, we show GACL not only works on abstract visual representations such as sketch but also extends well to natural images on the problem of image quality assessment (IQA). Last but not least, we spell out the general properties of GACL as general-purpose data re-weighting strategy and demonstrate its applications in vertical problems such as noisy label cleansing. Code will be made publicly available at github.com/yanglan0225/SketchX-Quantifying-Sketch-Quality.

Runqi Qiao, Qiuna Tan, Minghan Yang et al.

Empowering Large Multimodal Models (LMMs) to deeply integrate image interaction with long-horizon reasoning capabilities remains a long-standing challenge in this field. Recent advances in vision-centric reasoning explore a promising "Thinking with Images" paradigm for LMMs, marking a shift from image-assisted reasoning to image-interactive thinking. While this milestone enables models to focus on fine-grained image regions, progress remains constrained by limited visual tool spaces and task-specific workflow designs. To bridge this gap, we present V-Thinker, a general-purpose multimodal reasoning assistant that enables interactive, vision-centric thinking through end-to-end reinforcement learning. V-Thinker comprises two key components: (1) a Data Evolution Flywheel that automatically synthesizes, evolves, and verifies interactive reasoning datasets across three dimensions-diversity, quality, and difficulty; and (2) a Visual Progressive Training Curriculum that first aligns perception via point-level supervision, then integrates interactive reasoning through a two-stage reinforcement learning framework. Furthermore, we introduce VTBench, an expert-verified benchmark targeting vision-centric interactive reasoning tasks. Extensive experiments demonstrate that V-Thinker consistently outperforms strong LMM-based baselines in both general and interactive reasoning scenarios, providing valuable insights for advancing image-interactive reasoning applications.

Hongju Su, Ke Li, Lan Yang et al.

Existing state-of-the-art symbolic music generation models predominantly adopt autoregressive or hierarchical autoregressive architectures, modelling symbolic music as a sequence of attribute tokens with unidirectional temporal dependencies, under the assumption of a fixed, strict dependency structure among these attributes. However, we observe that using different attributes as the initial token in these models leads to comparable performance. This suggests that the attributes of a musical note are, in essence, a concurrent and unordered set, rather than a temporally dependent sequence. Based on this insight, we introduce Amadeus, a novel symbolic music generation framework. Amadeus adopts a two-level architecture: an autoregressive model for note sequences and a bidirectional discrete diffusion model for attributes. To enhance performance, we propose Music Latent Space Discriminability Enhancement Strategy(MLSDES), incorporating contrastive learning constraints that amplify discriminability of intermediate music representations. The Conditional Information Enhancement Module (CIEM) simultaneously strengthens note latent vector representation via attention mechanisms, enabling more precise note decoding. We conduct extensive experiments on unconditional and text-conditioned generation tasks. Amadeus significantly outperforms SOTA models across multiple metrics while achieving at least 4$\times$ speed-up. Furthermore, we demonstrate training-free, fine-grained note attribute control feasibility using our model. To explore the upper performance bound of the Amadeus architecture, we compile the largest open-source symbolic music dataset to date, AMD (Amadeus MIDI Dataset), supporting both pre-training and fine-tuning.

Yuxuan Chen, Rongpeng Li, Xiaoxue Yu et al.

Optimizing the deployment of large language models (LLMs) in edge computing environments is critical for enhancing privacy and computational efficiency. Toward efficient wireless LLM inference in edge computing, this study comprehensively analyzes the impact of different splitting points in mainstream open-source LLMs. On this basis, this study introduces a framework taking inspiration from model-based reinforcement learning (MBRL) to determine the optimal splitting point across the edge and user equipment (UE). By incorporating a reward surrogate model, our approach significantly reduces the computational cost of frequent performance evaluations. Extensive simulations demonstrate that this method effectively balances inference performance and computational load under varying network conditions, providing a robust solution for LLM deployment in decentralized settings.

Haoyang He, Zihua Rong, Liangjie Zhao et al.

Test-time Training enables model adaptation using only test questions and offers a promising paradigm for improving the reasoning ability of large language models (LLMs). However, it faces two major challenges: test questions are often highly difficult, making self-generated pseudo-labels unreliable, and existing methods lack effective mechanisms to adapt to a model's specific reasoning weaknesses, leading to inefficient learning. To address these issues, we propose \textbf{TTSR}, a self-reflective test-time self-evolving training framework. TTSR employs a single pretrained language model that alternates between the roles of a \textit{Student} and a \textit{Teacher} at test time. The Student focuses on solving problems and learning from synthesized variant questions, while the Teacher analyzes the Student's failed reasoning trajectories, summarizes recurring reasoning weaknesses, and synthesizes targeted variant questions accordingly. This process guides the model to improve within a learnable regime through a continual self-evolving loop. Experimental results on multiple challenging mathematical reasoning benchmarks show that TTSR consistently improves reasoning performance and generalizes well across different model backbones and general-domain reasoning tasks. These findings suggest that teacher-mediated self-reflection provides an effective pathway for stable and continual reasoning improvement at test time.

Peiwen Sun, Sitong Cheng, Xiangtai Li et al.

Recently, diffusion models have achieved great success in mono-channel audio generation. However, when it comes to stereo audio generation, the soundscapes often have a complex scene of multiple objects and directions. Controlling stereo audio with spatial contexts remains challenging due to high data costs and unstable generative models. To the best of our knowledge, this work represents the first attempt to address these issues. We first construct a large-scale, simulation-based, and GPT-assisted dataset, BEWO-1M, with abundant soundscapes and descriptions even including moving and multiple sources. Beyond text modality, we have also acquired a set of images and rationally paired stereo audios through retrieval to advance multimodal generation. Existing audio generation models tend to generate rather random and indistinct spatial audio. To provide accurate guidance for Latent Diffusion Models, we introduce the SpatialSonic model utilizing spatial-aware encoders and azimuth state matrices to reveal reasonable spatial guidance. By leveraging spatial guidance, our model not only achieves the objective of generating immersive and controllable spatial audio from text but also extends to other modalities as the pioneer attempt. Finally, under fair settings, we conduct subjective and objective evaluations on simulated and real-world data to compare our approach with prevailing methods. The results demonstrate the effectiveness of our method, highlighting its capability to generate spatial audio that adheres to physical rules.

Runqi Qiao, Qiuna Tan, Peiqing Yang et al.

Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various tasks, but still struggle with complex mathematical reasoning. Existing research primarily focuses on dataset construction and method optimization, often overlooking two critical aspects: comprehensive knowledge-driven design and model-centric data space modeling. In this paper, we introduce We-Math 2.0, a unified system that integrates a structured mathematical knowledge system, model-centric data space modeling, and a reinforcement learning (RL)-based training paradigm to comprehensively enhance the mathematical reasoning abilities of MLLMs. The key contributions of We-Math 2.0 are fourfold: (1) MathBook Knowledge System: We construct a five-level hierarchical system encompassing 491 knowledge points and 1,819 fundamental principles. (2) MathBook-Standard & Pro: We develop MathBook-Standard, a dataset that ensures broad conceptual coverage and flexibility through dual expansion. Additionally, we define a three-dimensional difficulty space and generate 7 progressive variants per problem to build MathBook-Pro, a challenging dataset for robust training. (3) MathBook-RL: We propose a two-stage RL framework comprising: (i) Cold-Start Fine-tuning, which aligns the model with knowledge-oriented chain-of-thought reasoning; and (ii) Progressive Alignment RL, leveraging average-reward learning and dynamic data scheduling to achieve progressive alignment across difficulty levels. (4) MathBookEval: We introduce a comprehensive benchmark covering all 491 knowledge points with diverse reasoning step distributions. Experimental results show that MathBook-RL performs competitively with existing baselines on four widely-used benchmarks and achieves strong results on MathBookEval, suggesting promising generalization in mathematical reasoning.

Renxuan Tan, Rongpeng Li, Zhifeng Zhao et al.

Transcending the single-preference paradigm, aligning LLMs with diverse human values is pivotal for robust deployment. Contemporary Multi-Objective Preference Alignment (MPA) approaches predominantly rely on static linear scalarization or rigid gradient projection to navigate these trade-offs. However, by enforcing strict conflict avoidance or simultaneous descent, these paradigms often prematurely converge to local stationary points. While mathematically stable, these points represent a conservative compromise where the model sacrifices potential global Pareto improvements to avoid transient local trade-offs. To break this deadlock, we propose Pareto-Lenient Consensus (PLC), a game-theoretic framework that reimagines alignment as a dynamic negotiation process. Unlike rigid approaches, PLC introduces consensus-driven lenient gradient rectification, which dynamically tolerates local degradation provided there is a sufficient dominant coalition surplus, thereby empowering the optimization trajectory to escape local suboptimal equilibrium and explore the distal Pareto-optimal frontier. Theoretical analysis validates PLC can facilitate stalemate escape and asymptotically converge to a Pareto consensus equilibrium. Moreover, extensive experiments show that PLC surpasses baselines in both fixed-preference alignment and global Pareto frontier quality. This work highlights the potential of negotiation-driven alignment as a promising avenue for MPA. Our codes are available at https://anonymous.4open.science/r/aaa-6BB8.

Ruolin Yang, Da Li, Honggang Zhang et al.

Sketching is a uniquely human tool for expressing ideas and creativity. The animation of sketches infuses life into these static drawings, opening a new dimension for designers. Animating sketches is a time-consuming process that demands professional skills and extensive experience, often proving daunting for amateurs. In this paper, we propose a novel sketch animation model SketchAnimator, which enables adding creative motion to a given sketch, like "a jumping car''. Namely, given an input sketch and a reference video, we divide the sketch animation into three stages: Appearance Learning, Motion Learning and Video Prior Distillation. In stages 1 and 2, we utilize LoRA to integrate sketch appearance information and motion dynamics from the reference video into the pre-trained T2V model. In the third stage, we utilize Score Distillation Sampling (SDS) to update the parameters of the Bezier curves in each sketch frame according to the acquired motion information. Consequently, our model produces a sketch video that not only retains the original appearance of the sketch but also mirrors the dynamic movements of the reference video. We compare our method with alternative approaches and demonstrate that it generates the desired sketch video under the challenge of one-shot motion customization.

Yunshen Wang, Yicheng Liu, Tianyuan Yuan et al.

Accurately predicting 3D occupancy grids from visual inputs is critical for autonomous driving, but current discriminative methods struggle with noisy data, incomplete observations, and the complex structures inherent in 3D scenes. In this work, we reframe 3D occupancy prediction as a generative modeling task using diffusion models, which learn the underlying data distribution and incorporate 3D scene priors. This approach enhances prediction consistency, noise robustness, and better handles the intricacies of 3D spatial structures. Our extensive experiments show that diffusion-based generative models outperform state-of-the-art discriminative approaches, delivering more realistic and accurate occupancy predictions, especially in occluded or low-visibility regions. Moreover, the improved predictions significantly benefit downstream planning tasks, highlighting the practical advantages of our method for real-world autonomous driving applications.

Lan Yang, Minghan Yang, Ke Li et al.

Recent advances in fMRI-based image reconstruction have achieved remarkable photo-realistic fidelity. Yet, a persistent limitation remains: while reconstructed images often appear naturalistic and holistically similar to the target stimuli, they frequently suffer from severe semantic misalignment -- salient objects are often replaced or hallucinated despite high visual quality. In this work, we address this limitation by rethinking the role of explicit semantic interpretation in fMRI decoding. We argue that existing methods rely too heavily on entangled visual embeddings which prioritize low-level appearance cues -- such as texture and global gist -- over explicit semantic identity. To overcome this, we parse fMRI signals into rich, sentence-level semantic descriptions that mirror the hierarchical and compositional nature of human visual understanding. We achieve this by leveraging grounded VLMs to generate synthetic, human-like, multi-granularity textual representations that capture object identities and spatial organization. Built upon this foundation, we propose SynMind, a framework that integrates these explicit semantic encodings with visual priors to condition a pretrained diffusion model. Extensive experiments demonstrate that SynMind outperforms state-of-the-art methods across most quantitative metrics. Notably, by offloading semantic reasoning to our text-alignment module, SynMind surpasses competing methods based on SDXL while using the much smaller Stable Diffusion 1.4 and a single consumer GPU. Large-scale human evaluations further confirm that SynMind produces reconstructions more consistent with human visual perception. Neurovisualization analyses reveal that SynMind engages broader and more semantically relevant brain regions, mitigating the over-reliance on high-level visual areas.

Shiyi Yang, Xiaoxue Yu, Rongpeng Li et al.

Operating Large Language Models (LLMs) on edge devices is increasingly challenged by limited communication bandwidth and strained computational and memory costs. Thus, cloud-assisted remote fine-tuning becomes indispensable. Nevertheless, existing Low-Rank Adaptation (LoRA) approaches typically employ fixed or heuristic rank configurations, and the subsequent over-the-air transmission of all LoRA parameters could be rather inefficient. To address this limitation, we develop AirLLM, a hierarchical diffusion policy framework for communication-aware LoRA adaptation. Specifically, AirLLM models the rank configuration as a structured action vector that spans all LoRA-inserted projections. To solve the underlying high-dimensional sequential decision-making problem, a Proximal Policy Optimization (PPO) agent generates coarse-grained decisions by jointly observing wireless states and linguistic complexity, which are then refined via Denoising Diffusion Implicit Models (DDIM) to produce high-resolution, task- and channel-adaptive rank vectors. The two modules are optimized alternatively, with the DDIM trained under the Classifier-Free Guidance (CFG) paradigm to maintain alignment with PPO rewards. Experiments under varying signal-to-noise ratios demonstrate that AirLLM consistently enhances fine-tuning performance while significantly reducing transmission costs, highlighting the effectiveness of reinforcement-driven, diffusion-refined rank adaptation for scalable and efficient remote fine-tuning over the air.

Yuxuan Chen, Rongpeng Li, Zhifeng Zhao et al.

We present MERLOT, a scalable mixture-of-expert (MoE) based refinement of distilled large language model optimized for encrypted traffic classification. By applying model distillation techniques in a teacher-student paradigm, compact models derived from GPT-2-base retain high classification accuracy while minimizing computational costs. These models function as specialized experts in an MoE architecture, dynamically assigned via a gating network. Unlike generation-based methods, our approach directly classifies encrypted traffic using the final decoder token with contextual feature embedding as input. Experiments on 10 datasets show superior or competitive performance over the state-of-the-art models while significantly reducing resource demands, underscoring its effectiveness and robustness.

Renxuan Tan, Rongpeng Li, Fei Wang et al.

Medium Access Control (MAC) protocols, essential for wireless networks, are typically manually configured. While deep reinforcement learning (DRL)-based protocols enhance task-specified network performance, they suffer from poor generalizability and resilience, demanding costly retraining to adapt to dynamic environments. To overcome this limitation, we introduce a game-theoretic LLM-empowered multi-agent DRL (MARL) framework, in which the uplink transmission between a base station and a varying number of user equipments is modeled as a dynamic multi-follower Stackelberg game (MFSG), capturing the network's natural hierarchical structure. Within this game, LLM-driven agents, coordinated through proximal policy optimization (PPO), synthesize adaptive, semantic MAC protocols in response to network dynamics. Protocol action grammar (PAG) is employed to ensure the reliability and efficiency of this process. Under this system, we further analyze the existence and convergence behavior in terms of a Stackelberg equilibrium by studying the learning dynamics of LLM-empowered unified policies in response to changing followers. Simulations corroborate that our framework achieves a 77.6% greater throughput and a 65.2% fairness improvement over conventional baselines. Besides, our framework generalizes excellently to a fluctuating number of users without requiring retraining or architectural changes.

Ziyao Wang, Rongpeng Li, Sizhao Li et al.

Intelligent control of Unmanned Aerial Vehicles (UAVs) swarms has emerged as a critical research focus, and it typically requires the swarm to navigate effectively while avoiding obstacles and achieving continuous coverage over multiple mission targets. Although traditional Multi-Agent Reinforcement Learning (MARL) approaches offer dynamic adaptability, they are hindered by the semantic gap in numerical communication and the rigidity of homogeneous role structures, resulting in poor generalization and limited task scalability. Recent advances in Large Language Model (LLM)-based control frameworks demonstrate strong semantic reasoning capabilities by leveraging extensive prior knowledge. However, due to the lack of online learning and over-reliance on static priors, these works often struggle with effective exploration, leading to reduced individual potential and overall system performance. To address these limitations, we propose a Role-Adaptive LLM-Driven Yoked navigation algorithm RALLY. Specifically, we first develop an LLM-driven semantic decision framework that uses structured natural language for efficient semantic communication and collaborative reasoning. Afterward, we introduce a dynamic role-heterogeneity mechanism for adaptive role switching and personalized decision-making. Furthermore, we propose a Role-value Mixing Network (RMIX)-based assignment strategy that integrates LLM offline priors with MARL online policies to enable semi-offline training of role selection strategies. Experiments in the Multi-Agent Particle Environment (MPE) environment and a Software-In-The-Loop (SITL) platform demonstrate that RALLY outperforms conventional approaches in terms of task coverage, convergence speed, and generalization, highlighting its strong potential for collaborative navigation in agentic multi-UAV systems.

Rongpeng Li, Jianhang Zhu, Jiahao Huang et al.

Intelligent Transportation Systems (ITSs) have emerged as a promising solution towards ameliorating urban traffic congestion, with Traffic Signal Control (TSC) identified as a critical component. Although Multi-Agent Reinforcement Learning (MARL) algorithms have shown potential in optimizing TSC through real-time decision-making, their scalability and effectiveness often suffer from large-scale and complex environments. Typically, these limitations primarily stem from a fundamental mismatch between the exponential growth of the state space driven by the environmental heterogeneities and the limited modeling capacity of current solutions. To address these issues, this paper introduces a novel MARL framework that integrates Dynamic Graph Neural Networks (DGNNs) and Topological Data Analysis (TDA), aiming to enhance the expressiveness of environmental representations and improve agent coordination. Furthermore, inspired by the Mixture of Experts (MoE) architecture in Large Language Models (LLMs), a topology-assisted spatial pattern disentangling (TSD)-enhanced MoE is proposed, which leverages topological signatures to decouple graph features for specialized processing, thus improving the model's ability to characterize dynamic and heterogeneous local observations. The TSD module is also integrated into the policy and value networks of the Multi-agent Proximal Policy Optimization (MAPPO) algorithm, further improving decision-making efficiency and robustness. Extensive experiments conducted on real-world traffic scenarios, together with comprehensive theoretical analysis, validate the superior performance of the proposed framework, highlighting the model's scalability and effectiveness in addressing the complexities of large-scale TSC tasks.

YiFan Zhang, Shanglin Lei, Runqi Qiao et al.

The rapidly developing field of large multimodal models (LMMs) has led to the emergence of diverse models with remarkable capabilities. However, existing benchmarks fail to comprehensively, objectively and accurately evaluate whether LMMs align with the diverse needs of humans in real-world scenarios. To bridge this gap, we propose the Multi-Dimensional Insights (MDI) benchmark, which includes over 500 images covering six common scenarios of human life. Notably, the MDI-Benchmark offers two significant advantages over existing evaluations: (1) Each image is accompanied by two types of questions: simple questions to assess the model's understanding of the image, and complex questions to evaluate the model's ability to analyze and reason beyond basic content. (2) Recognizing that people of different age groups have varying needs and perspectives when faced with the same scenario, our benchmark stratifies questions into three age categories: young people, middle-aged people, and older people. This design allows for a detailed assessment of LMMs' capabilities in meeting the preferences and needs of different age groups. With MDI-Benchmark, the strong model like GPT-4o achieve 79% accuracy on age-related tasks, indicating that existing LMMs still have considerable room for improvement in addressing real-world applications. Looking ahead, we anticipate that the MDI-Benchmark will open new pathways for aligning real-world personalization in LMMs. The MDI-Benchmark data and evaluation code are available at https://mdi-benchmark.github.io/

Zhipeng Chen, Lan Yang, Yonggang Qi et al.

Despite the rapid advancements in text-to-image (T2I) synthesis, enabling precise visual control remains a significant challenge. Existing works attempted to incorporate multi-facet controls (text and sketch), aiming to enhance the creative control over generated images. However, our pilot study reveals that the expressive power of humans far surpasses the capabilities of current methods. Users desire a more versatile approach that can accommodate their diverse creative intents, ranging from controlling individual subjects to manipulating the entire scene composition. We present VersaGen, a generative AI agent that enables versatile visual control in T2I synthesis. VersaGen admits four types of visual controls: i) single visual subject; ii) multiple visual subjects; iii) scene background; iv) any combination of the three above or merely no control at all. We train an adaptor upon a frozen T2I model to accommodate the visual information into the text-dominated diffusion process. We introduce three optimization strategies during the inference phase of VersaGen to improve generation results and enhance user experience. Comprehensive experiments on COCO and Sketchy validate the effectiveness and flexibility of VersaGen, as evidenced by both qualitative and quantitative results.

Xiaoxue Yu, Xingfu Yi, Rongpeng Li et al.

In the evolution towards 6G, integrating Artificial Intelligence (AI) with advanced network infrastructure emerges as a pivotal strategy for enhancing network intelligence and resource utilization. Existing distributed learning frameworks like Federated Learning and Split Learning often struggle with significant challenges in dynamic network environments including high synchronization demands, costly communication overhead, severe computing resource consumption, and data heterogeneity across network nodes. These obstacles hinder the applications of ubiquitous computing capabilities of 6G networks, especially in light of the trend of escalating model parameters and training data volumes. To address these challenges effectively, this paper introduces ``Snake Learning", a cost-effective distributed learning framework. Specifically, Snake Learning respects the heterogeneity of inter-node computing capability and local data distribution in 6G networks, and sequentially trains the designated part of model layers on individual nodes. This layer-by-layer serpentine update mechanism contributes to significantly reducing the requirements for storage, memory and communication during the model training phase, and demonstrates superior adaptability and efficiency for both classification and fine-tuning tasks across homogeneous and heterogeneous data distributions.

Fei Ni, Bingyan Wang, Rongpeng Li et al.

In the swiftly advancing realm of communication technologies, Semantic Communication (SemCom), which emphasizes knowledge understanding and processing, has emerged as a hot topic. By integrating artificial intelligence technologies, SemCom facilitates a profound understanding, analysis and transmission of communication content. In this chapter, we clarify the means of knowledge learning in SemCom with a particular focus on the utilization of Knowledge Graphs (KGs). Specifically, we first review existing efforts that combine SemCom with knowledge learning. Subsequently, we introduce a KG-enhanced SemCom system, wherein the receiver is carefully calibrated to leverage knowledge from its static knowledge base for ameliorating the decoding performance. Contingent upon this framework, we further explore potential approaches that can empower the system to operate in evolving knowledge base more effectively. Furthermore, we investigate the possibility of integration with Large Language Models (LLMs) for data augmentation, offering additional perspective into the potential implementation means of SemCom. Extensive numerical results demonstrate that the proposed framework yields superior performance on top of the KG-enhanced decoding and manifests its versatility under different scenarios.

Peiwen Sun, Yifan Zhang, Zishan Liu et al.

The vanilla fusion methods still dominate a large percentage of mainstream audio-visual tasks. However, the effectiveness of vanilla fusion from a theoretical perspective is still worth discussing. Thus, this paper reconsiders the signal fused in the multimodal case from a bionics perspective and proposes a simple, plug-and-play, attention module for vanilla fusion based on fundamental signal theory and uncertainty theory. In addition, previous work on multimodal dynamic gradient modulation still relies on decoupling the modalities. So, a decoupling-free gradient modulation scheme has been designed in conjunction with the aforementioned attention module, which has various advantages over the decoupled one. Experiment results show that just a few lines of code can achieve up to 2.0% performance improvements to several multimodal classification methods. Finally, quantitative evaluation of other fusion tasks reveals the potential for additional application scenarios.

Xing Xu, Rongpeng Li, Zhifeng Zhao et al.

The paper considers independent reinforcement learning (IRL) for multi-agent decision-making process in the paradigm of federated learning (FL). We show that FL can clearly improve the policy performance of IRL in terms of training efficiency and stability. However, since the policy parameters are trained locally and aggregated iteratively through a central server in FL, frequent information exchange incurs a large amount of communication overheads. To reach a good balance between improving the model's convergence performance and reducing the required communication and computation overheads, this paper proposes a system utility function and develops a consensus-based optimization scheme on top of the periodic averaging method, which introduces the consensus algorithm into FL for the exchange of a model's local gradients. This paper also provides novel convergence guarantees for the developed method, and demonstrates its superior effectiveness and efficiency in improving the system utility value through theoretical analyses and numerical simulation results.

Luya Wang, Feng Liang, Yangguang Li et al.

Recently, self-supervised vision transformers have attracted unprecedented attention for their impressive representation learning ability. However, the dominant method, contrastive learning, mainly relies on an instance discrimination pretext task, which learns a global understanding of the image. This paper incorporates local feature learning into self-supervised vision transformers via Reconstructive Pre-training (RePre). Our RePre extends contrastive frameworks by adding a branch for reconstructing raw image pixels in parallel with the existing contrastive objective. RePre is equipped with a lightweight convolution-based decoder that fuses the multi-hierarchy features from the transformer encoder. The multi-hierarchy features provide rich supervisions from low to high semantic information, which are crucial for our RePre. Our RePre brings decent improvements on various contrastive frameworks with different vision transformer architectures. Transfer performance in downstream tasks outperforms supervised pre-training and state-of-the-art (SOTA) self-supervised counterparts.

Yue Sun, Honggang Zhang, Zhuoming Huang et al.

Recent research has shown that mmWave radar sensing is effective for object detection in low visibility environments, which makes it an ideal technique in autonomous navigation systems such as autonomous vehicles. However, due to the characteristics of radar signals such as sparsity, low resolution, specularity, and high noise, it is still quite challenging to reconstruct 3D object shapes via mmWave radar sensing. Built on our recent proposed 3DRIMR (3D Reconstruction and Imaging via mmWave Radar), we introduce in this paper DeepPoint, a deep learning model that generates 3D objects in point cloud format that significantly outperforms the original 3DRIMR design. The model adopts a conditional Generative Adversarial Network (GAN) based deep neural network architecture. It takes as input the 2D depth images of an object generated by 3DRIMR's Stage 1, and outputs smooth and dense 3D point clouds of the object. The model consists of a novel generator network that utilizes a sequence of DeepPoint blocks or layers to extract essential features of the union of multiple rough and sparse input point clouds of an object when observed from various viewpoints, given that those input point clouds may contain many incorrect points due to the imperfect generation process of 3DRIMR's Stage 1. The design of DeepPoint adopts a deep structure to capture the global features of input point clouds, and it relies on an optimally chosen number of DeepPoint blocks and skip connections to achieve performance improvement over the original 3DRIMR design. Our experiments have demonstrated that this model significantly outperforms the original 3DRIMR and other standard techniques in reconstructing 3D objects.