论文检索

Bingyi Liu, Jinbo He, Haiyong Shi, Enshu Wang, Weizhen Han, Jingxiang Hao, Peixi Wang, Zhuangzhuang Zhang

Hybrid action space, which combines discrete choices and continuous parameters, is prevalent in domains such as robot control and game AI. However, efficiently modeling and optimizing hybrid discrete-continuous action space remains a fundamental challenge, mainly due to limited policy expressiveness and poor scalability in high-dimensional settings. To address this challenge, we view the hybrid action space problem as a fully cooperative game and propose a Cooperative Hybrid Diffusion Policies (CHDP) framework to solve it. CHDP employs two cooperative agents that leverage a discrete and a continuous diffusion policy, respectively. The continuous policy is conditioned on the discrete action's representation, explicitly modeling the dependency between them. This cooperative design allows the diffusion policies to leverage their expressiveness to capture complex distributions in their respective action spaces. To mitigate the update conflicts arising from simultaneous policy updates in this cooperative setting, we employ a sequential update scheme that fosters co-adaptation. Moreover, to improve scalability when learning in high-dimensional discrete action space, we construct a codebook that embeds the action space into a low-dimensional latent space. This mapping enables the discrete policy to learn in a compact, structured space. Finally, we design a Q-function-based guidance mechanism to align the codebook's embeddings with the discrete policy's representation during training. On challenging hybrid action benchmarks, CHDP outperforms state-of-the-art method by up to 19.3% in success rate.

Jinhao Liang, Sven Koenig, Ferdinando Fioretto

Multi-Robot Motion Planning (MRMP) involves generating collision-free trajectories for multiple robots operating in a shared continuous workspace. While discrete multi-agent path finding (MAPF) methods are broadly adopted due to their scalability, their coarse discretization severely limits trajectory quality. In contrast, continuous optimization-based planners offer higher-quality paths but suffer from the curse of dimensionality, resulting in poor scalability with respect to the number of robots. This paper tackles the limitations of these two approaches by introducing a novel framework that integrates discrete MAPF solvers with constrained generative diffusion models. The resulting framework, called Discrete-Guided Diffusion (DGD), has three key characteristics: (1) it decomposes the original nonconvex MRMP problem into tractable subproblems with convex configuration spaces, (2) it combines discrete MAPF solutions with constrained optimization techniques to guide diffusion models capture complex spatiotemporal dependencies among robots, and (3) it incorporates a lightweight constraint repair mechanism to ensure trajectory feasibility. The proposed method sets a new state-of-the-art performance in large-scale, complex environments, scaling to 100 robots while achieving planning efficiency and high success rates.

Meiju Li, Ruixiang Sun, Xin Li, Mingzhong Wang

Partially observable Markov decision processes (POMDPs) present significant challenges for reinforcement learning, as agents must learn optimal policies while maintaining belief states over unobserved environment states based on partial observations. We observe a compelling analogy: large language models (LLMs) autoregressively generate token probability distributions based on preceding context, mirroring how belief states are maintained and updated in POMDPs. This insight motivates leveraging the rich prior knowledge embedded in pre-trained LLMs for latent states estimation from observation-action histories. However, two critical challenges emerge: on the one hand, modality misalignment prevents LLMs from directly encoding visual observations and discrete actions; on the other hand, semantic misalignment exists between observation-action sequences and token sequences. To address these challenges, we introduce a novel framework ELSLLM that employs a Johnson-Lindenstrauss projection (JLP) module to transform input dimensions while preserving state similarity with theoretical guarantees, and utilizes modern Hopfield networks (MHN) to store all word embeddings from pre-trained LLMs as a knowledge repository. Through retrieval and querying mechanisms, ELSLLM achieves token-level knowledge alignment without requiring fine-tuning of the pre-trained LLMs. Extensive experiments on partially observable environments demonstrate that ELSLLM achieves state-of-the-art performance, significantly outperforming baseline methods with and without LSTM memory mechanisms. Our work opens new avenues for integrating pre-trained LLMs with reinforcement learning in partially observable settings.

Wentao Fan, Chao Zhang, Chunlin Chen, Huaxiong Li

Due to the continuous increase of multimedia data on the internet, online hashing has garnered considerable attention for handling multi-modal data streams. However, most existing online hashing approaches focus solely on data growth of samples, overlooking the dynamics of classes. In this paper, we simultaneously address the challenges of both sample-level and class-level growth, and propose a novel Online Hashing method with Expanding Label Space (OH-ELS) for cross-modal retrieval. In OH-ELS, multi-modal data arrives continuously, and incoming data may introduce new classes. To avoid catastrophic forgetting, we transfer the historical knowledge at both the sample and class levels. At the sample-level, a small subset of anchor codes from old data are replayed to preserve the similarities between new data and old data. At the class-level, a consistency regularizer is applied to new classifiers to leverage the priors of historical classes. To ensure both efficiency and accuracy, a discrete optimization algorithm is proposed to solve the binary-constrained optimization problem without relaxation. Experimental results illustrate the effectiveness and superiority of OH-ELS in class-incremental cross-modal retrieval compared with the state-of-the-art methods.

Changxi Chi, Yufei Huang, Jun Xia, Jiangbin Zheng, Yunfan Liu, Zelin Zang, Stan Z. Li

Predicting single-cell perturbation outcomes directly advances gene function analysis and facilitates drug candidate selection, making it a key driver of both basic and translational biomedical research. However, a major bottleneck in this task is the unpaired nature of single-cell data, as the same cell cannot be observed both before and after perturbation due to the destructive nature of sequencing. Although some neural generative transport models attempt to tackle unpaired single-cell perturbation data, they either lack explicit conditioning or depend on prior spaces for indirect distribution alignment, limiting precise perturbation modeling. In this work, we approximate Schrödinger Bridge (SB), which defines stochastic dynamic mappings recovering the entropy-regularized optimal transport (OT), to directly align the distributions of control and perturbed single-cell populations across different perturbation conditions. Unlike prior SB approximations that rely on bidirectional modeling to infer optimal source-target sample coupling, we leverage Minibatch-OT based pairing to avoid such bidirectional inference and the associated ill-posedness of defining the reverse process. This pairing directly guides bridge learning, yielding a scalable approximation to the SB. We approximate two SB models, one modeling discrete gene activation states and the other continuous expression distributions. Joint training enables accurate perturbation modeling and captures single-cell heterogeneity. Experiments on public genetic and drug perturbation datasets show that our model effectively captures heterogeneous single-cell responses and achieves state-of-the-art performance.

Diana Bolanos, Mohammadmehdi Ataei, Pradeep Kumar Jayaraman

Designing mechanical mechanisms to trace specific paths is a classic yet notoriously difficult engineering problem, characterized by a vast and complex search space of discrete topologies and continuous parameters. We introduce MechaFormer, a Transformer-based model that tackles this challenge by treating mechanism design as a conditional sequence generation task. Our model learns to translate a target curve into a domain-specific language (DSL) string, simultaneously determining the mechanism's topology and geometric parameters in a single, unified process. MechaFormer significantly outperforms existing baselines, achieving state-of-the-art path-matching accuracy and generating a wide diversity of novel and valid designs. We demonstrate a suite of sampling strategies that can dramatically improve solution quality and offer designers valuable flexibility. Furthermore, we show that the high-quality outputs from MechaFormer serve as excellent starting points for traditional optimizers, creating a hybrid approach that finds superior solutions with remarkable efficiency.

Xinyue Yu, Youqing Fang, Pingyu Wu, Guoyang Ye, Wenbo Zhou, Weiming Zhang, Song Xiao

Generating expressive and controllable human speech is one of the core goals of generative artificial intelligence, but its progress has long been constrained by two fundamental challenges: the deep entanglement of speech factors and the coarse granularity of existing control mechanisms. To overcome these challenges, we have proposed a novel framework called MF-Speech, which consists of two core components: MF-SpeechEncoder and MF-SpeechGenerator. MF-SpeechEncoder acts as a factor purifier, adopting a multi-objective optimization strategy to decompose the original speech signal into highly pure and independent representations of content, timbre, and emotion. Subsequently, MF-SpeechGenerator functions as a conductor, achieving precise, composable and fine-grained control over these factors through dynamic fusion and Hierarchical Style Adaptive Normalization (HSAN). Experiments demonstrate that in the highly challenging multi-factor compositional speech generation task, MF-Speech significantly outperforms current state-of-the-art methods, achieving a lower word error rate (WER=4.67%), superior style control (SECS=0.5685, Corr=0.68), and the highest subjective evaluation scores (nMOS=3.96, sMOS_t=3.86, sMOS_e=3.78). Furthermore, the learned discrete factors exhibit strong transferability, demonstrating their significant potential as a general-purpose speech representation.

Salam Afiouni, Jakub Černý, Chun Kai Ling, Christian Kroer

We study a class of two-player zero-sum Colonel Blotto games in which, after allocating soldiers across battlefields, players engage in (possibly distinct) normal-form games on each battlefield. Per-battlefield payoffs are parameterized by the soldier allocations. This generalizes the classical Blotto setting, where outcomes depend only on relative soldier allocations. We consider both discrete and continuous allocation models and examine two types of aggregate objectives: linear aggregation and worst-case battlefield value. For each setting, we analyze the existence and computability of Nash equilibrium. The general problem is not convex-concave, which limits the applicability of standard convex optimization techniques. However, we show that in several settings it is possible to reformulate the strategy space in a way where convex-concave structure is recovered. We evaluate the proposed methods on synthetic and real-world instances inspired by security applications, suggesting that our approaches scale well in practice.

Huayang Xu, Huanhuan Yuan, Guanfeng Liu, Junhua Fang, Lei Zhao, Pengpeng Zhao

Sequential recommendation has garnered significant attention for its ability to capture dynamic preferences by mining users’ historical interaction data. Given that users’ complex and intertwined periodic preferences are difficult to disentangle in the time domain, recent research is exploring frequency domain analysis to identify these hidden patterns. However, current frequency-domain-based methods suffer from two key limitations: (i) They primarily employ static filters with fixed characteristics, overlooking the personalized nature of behavioral patterns; (ii) While the global discrete Fourier transform excels at modeling long-range dependencies, it can blur non-stationary signals and short-term fluctuations. To overcome these limitations, we propose a novel method called Wavelet Enhanced Adaptive Frequency Filter for Sequential Recommendation (WEARec). Specifically, it consists of two vital modules: dynamic frequency-domain filtering and wavelet feature enhancement. The former is used to dynamically adjust filtering operations based on behavioral sequences to extract personalized global information, and the latter integrates wavelet transform to reconstruct sequences, enhancing blurred non-stationary signals and short-term fluctuations. Finally, these two modules work synergistically to achieve comprehensive performance and efficiency optimization in long sequential recommendation scenarios. Extensive experiments on four widely-used benchmark datasets demonstrate the superiority of WEARec.

Yu Hou, Won-Yong Shin

Large language model (LLM)-based recommender systems have achieved high-quality performance by bridging the discrepancy between the item space and the language space through item tokenization. However, existing item tokenization methods typically require training separate models for each item domain, limiting generalization. Moreover, the diverse distributions and semantics across item domains make it difficult to construct a unified tokenization that preserves domain-specific information. To address these challenges, we propose UniTok, a Unified item Tokenization framework that integrates our own mixture-of-experts (MoE) architecture with a series of codebooks to convert items into discrete tokens, enabling scalable tokenization while preserving semantic information across multiple item domains. Specifically, items from different domains are first projected into a unified latent space through a shared encoder. They are then routed to domain-specific experts to capture the unique semantics, while a shared expert, which is always active, encodes common knowledge transferable across domains. Additionally, to mitigate semantic imbalance across domains, we present a mutual information calibration mechanism, which guides the model towards retaining similar levels of semantic information for each domain. Comprehensive experiments on wide-ranging real-world datasets demonstrate that the proposed UniTok framework is (a) highly effective: achieving up to 51.89% improvements over strong benchmarks, (b) theoretically sound: showing the analytical validity of our architectural design and optimization; and (c) highly generalizable: demonstrating robust performance across diverse domains without requiring per-domain retraining, a capability not supported by existing baselines.

Pierre Talbot

Machine learning has tremendously benefited from graphics processing units (GPUs) to accelerate training and inference by several orders of magnitude. However, this success has not been replicated in general and exact combinatorial optimization. Our key contribution is to propose a general-purpose discrete constraint programming solver fully implemented on GPU. It is based on integer interval bound propagation and backtracking search. The two main ingredients are (1) ternary constraint network optimized for GPU architectures, and (2) an on-demand subproblems generation strategy. Our constraint solving algorithm is significantly simpler than those found in optimized CPU constraint solvers, yet is competitive with sequential solvers in the MiniZinc 2024 challenge.

Guidio Sewa, David Allouche, Simon De Givry, George Katsirelos, Pierre Montalbano, Thomas Schiex

To efficiently solve exact discrete optimization problems, branch and bound algorithms require tight bounds. In constraint programming, for optimization, soft arc consistencies typically derive much stronger bounds than those offered by domain or bound consistencies applied to a cost variable. The reason is that soft local consistencies exchange marginal cost information between variables whereas domain consistencies rely only on shrinking domains, which is less informative. However, CP solvers equipped with soft arc consistencies have so far offered limited support for efficient processing of global constraints. In this work, we show how we can efficiently enforce soft local consistency over the AllDifferent constraint, relying on algorithms for the Linear Assignment Problem (LAP). We implement this propagator in toulbar2, the state-of-the-art weighted CP solver exploiting soft local consistencies for bounding. We show that, equipped with this new propagator, toulbar2 outperforms state-of-the-art domain consistency-based CP as well as integer programming solvers for the Quadratic Assignment Problem and shows better performance for miniCOP instances of the 2024 XCSP competition with AllDifferent constraints.

Shuhan Xu, Siyuan Liang, Hongling Zheng, Aishan Liu, Xinbiao Wang, Yong Luo, Fu Lin, Leszek Rutkowski, Dacheng Tao

Visual language models (VLMs) have made significant progress in image captioning tasks, yet recent studies have found they are vulnerable to backdoor attacks. Attackers can inject undetectable perturbations into the data during inference, triggering abnormal behavior and generating malicious captions. These attacks are particularly challenging to detect and defend against due to the stealthiness and cross-modal propagation of the trigger signals. In this paper, we identify two key vulnerabilities by analyzing existing attack patterns: (1) the model exhibits abnormal attention concentration on certain regions of the input image, and (2) backdoor attacks often induce semantic drift and sentence incoherence. Based on these insights, we propose Semantic Reward Defense (SRD), a reinforcement learning framework that mitigates backdoor behavior without requiring any prior knowledge of trigger patterns. SRD learns to apply discrete perturbations to sensitive contextual regions of image inputs via a deep Q-network policy, aiming to confuse attention and disrupt the activation of malicious paths. To guide policy optimization, we design a reward signal named semantic fidelity score, which jointly assesses the semantic consistency and linguistic fluency of the generated captions, encouraging the agent to achieve a robust yet faithful output. SRD offers a trigger-agnostic, policy-interpretable defense paradigm that effectively mitigates local (TrojVLM) and global (Shadowcast) backdoor attacks, reducing ASR to 3.6% and 5.6% respectively, with less than 15% average CIDEr drop on the clean inputs.

Dianbing Xi, Guoyuan An, Jingsen Zhu, Zhijian Liu, Yuan Liu, Ruiyuan Zhang, Jiayuan Lu, Yuchi Huo, Rui Wang

We propose PFAvatar (Pose-Fusion Avatar), a new method that reconstructs high-quality 3D avatars from Outfit of the Day (OOTD) photos, which exhibit diverse poses, occlusions, and complex backgrounds. Our method consists of two stages: (1) fine-tuning a pose-aware diffusion model from few-shot OOTD examples and (2) distilling a 3D avatar represented by a neural radiance field (NeRF). In the first stage, unlike previous methods that segment images into assets (e.g. garments, accessories) for 3D assembly, which is prone to inconsistency, we avoid decomposition and directly model the full-body appearance. By integrating a pre-trained ControlNet for pose estimation and a novel Condition Prior Preservation Loss (CPPL), our method enables end-to-end learning of fine details while mitigating language drift in few-shot training. Our method completes personalization in just 5 minutes, achieving a 48x speed-up compared to previous approaches. In the second stage, we introduce a NeRF-based avatar representation optimized by canonical SMPL-X space sampling and Multi-Resolution 3D-SDS. Compared to mesh-based representations that suffer from resolution-dependent discretization and erroneous occluded geometry, our continuous radiance field can preserve high-frequency textures (e.g., hair) and handle occlusions correctly through transmittance. Experiments demonstrate that PFAvatar outperforms state-of-the-art methods in terms of reconstruction fidelity, detail preservation, and robustness to occlusions/truncations, advancing practical 3D avatar generation from real-world OOTD albums. In addition, the reconstructed 3D avatars support downstream applications such as virtual try-on, animation, and human video reenactment, further demonstrating the versatility and practical value of our approach.

Boya Shi, Thomas N Guan, Yi Xiaodong

Existing dynamic scene rendering methods often struggle to preserve sharp edges and maintain temporal consistency. To address these challenges, we introduce Edge 4D Gaussian Splatting (Edge4DGS), a real-time rendering framework that renders fine-grained geometry from sparse monocular inputs in dynamic scenes. Edge4DGS proposes a hybrid geometric representation that augments Gaussian primitives with convex hulls, enabling accurate modeling of hard surfaces and complex boundaries. To enhance spatial precision, we introduce edge consistency regularization leveraging optical flow, guiding Gaussian distributions to align with true object contours. To enforce temporal coherence, we extend the regularization from discrete time steps to continuous unit intervals, enabling accurate motion modeling and reducing flickering artifacts. A two-stage coarse-to-fine optimization further improves geometric fidelity while preserving computational efficiency. Extensive experiments on monocular and multi-view motion datasets demonstrate that Edge4DGS achieves real-time, high-resolution rendering and consistently surpasses state-of-the-art methods, reducing LPIPS by 56.25%.

Yang Ouyang, Zihan Cheng, Xiaotong Luo, Guoqi Li, Yanyun Qu

Image restoration has made great progress with the rise of deep learning, but its energy consumption limits its real-world applications. Spiking Neural Networks (SNNs) are seen as energy-efficient alternatives to Artificial Neural Networks (ANNs). Applying SNNs to image restoration (IR) remains challenging, primarily due to the limited information capacity of spike-based signals. This limitation leads to quantization errors and information loss, while IR tasks are highly sensitive to output precision and error. Thus, the restoration performance suffers significantly. To address this challenge, we propose SpikingIR, an ANN-to-SNN conversion framework for IR that reduces information loss and quantization error. SpikingIR mainly consists of two components: Convolutional Pixel Mapping (CPM) and Membrane Potential Reuse Neuron (MPRN), which are designed to alleviate quantization errors and information loss in the output and intermediate layers, respectively. Specifically, CPM maps discrete outputs into a continuous space, better aligning with pixel-level details. From the perspective of information entropy, we show that outputs of CPM contain more information than the original outputs. MPRN introduces a post-processing step with relaxed firing conditions to extract residual membrane potential, reducing information waste. Furthermore, we fine-tune the converted model to jointly optimize both accuracy and energy efficiency. Experimental results demonstrate that SpikingIR achieves performance comparable to ANN counterparts across various IR benchmarks while reducing energy consumption by up to 50%.

Xinze Liu, Dayan Wu, Hengjie Zhu, Chenming Wu, Pengwen Dai

Asymmetric image retrieval (AIR), which typically employs a compact model for the query side and a large model for the database server, has garnered significant attention in resource-constrained environments. While deep hashing methods have shown great potential in large-scale image retrieval, current attempts for the asymmetric image retrieval overlook the differences in quantization capabilities between query and gallery networks. In AIR, the conventional quantization scheme forces the outputs of small query models to approximate the discrete outputs of large models, imposing overly rigid and stringent constraints that severely limit the optimization of small query models. Furthermore, existing deep hashing methods for AIR necessitate labeled datasets from large models, which also limits their practical applicability. To this end, we reconsider the necessity of strict discretization in AIR and propose a novel asymmetric hashing method, named Deep Correlation Alignment Hashing (DCAH). Rather than explicitly quantizing continuous query features to match discrete gallery representations, we distill the correlation across both models and introduce a Correlation Alignment based Quantization (CAQ) scheme, thereby implicitly accomplishing quantization. To preserve the similarity consistency between the query and gallery models, we further employ a correlation alignment-based knowledge distillation strategy which is intrinsically compatible with the CAQ. Notably, the proposed quantization scheme can function as a plug-and-play module that seamlessly integrates with existing AIR methods. Comprehensive evaluations on three real-world benchmark datasets demonstrate the effectiveness of the proposed quantization scheme CAQ, and also show that DCAH achieves state-of-the-art performance in asymmetric image retrieval scenarios.

Xiaoxing Hu, Ziyang Gong, Yupei Wang, Yuru Jia, Fei Lin, Dexiang Gao, Ke An, Jianhong Han, Zhuoran Sun, Gen Luo 等

Vision Foundation Models (VFMs), while powerful, often struggle in Remote Sensing (RS) segmentation tasks when combined with existing Parameter-Efficient Fine-Tuning (PEFT) methods. We observe that this limitation primarily arises from their inability to effectively handle the pervasive artifacts in RS imagery. To address this, we introduce Earth-Adapter, the first PEFT method specifically designed for RS artifact mitigation. Earth-Adapter introduces a novel Frequency-Guided Mixture of Adapters (MoA) approach, structured around a ''divide and conquer" strategy. It first utilizes Discrete Fourier Transformation (DFT) to "divide" features into distinct frequency components, thereby effectively isolating artifact-related information from semantic signals. Subsequently, to ''conquer" these artifact, MoA independently optimizes features within different subspaces and dynamically assigns weights via a router to aggregate the refined representations. This enables adaptive refinement of the VFM’s representation space to mitigate the impact of artifacts. This simple yet highly effective PEFT method demonstrably mitigates artifacts and significantly enhances VFMs performance on RS segmentation tasks. Extensive experiments demonstrate Earth-Adapter's effectiveness on in-domain semantic segmentation (SS), as well as Domain Adaptive (DA) and Domain Generalized (DG) semantic segmentation tasks. Compared with the baseline Rein, Earth-Adapter significantly improves mIoU by 1.2% in SS, 9.0% in DA, and 3.1% in DG benchmarks. Our code and weights will be released soon.

Zihan Gao, Lingling Li, Xu Liu, Fang Liu, Licheng Jiao, Puhua Chen, Wenping Ma, Shuyuan Yang

Semantic understanding of large-scale aerial scenes represents a critical challenge in 3D computer vision, hindered by the prohibitive cost of dense annotation. This paper introduces EvoPropGS, a novel approach for the semantic segmentation of 3D Gaussian Splatting models that requires only minimal supervision. Our core insight is to leverage the inherent structural repetitions within aerial environments to propagate semantic information from a sparse set of annotations across the entire 3D scene. Our approach constructs a prompt library by pairing SAM-generated mask candidates with DINOv2 feature embeddings from annotated views. For unannotated regions, we generate pseudo-labels by matching region proposals with these featured prompts via cosine similarity. We then formulate optimal prompt selection as a discrete optimization problem solved via evolutionary search, guided by our novel fitness function that evaluates both 3D consistency and 2D semantic coherence. Extensive experiments demonstrate that EvoPropGS achieves accurate segmentation with only 2 percent annotated pixels.

Zhuo Chen, Zhongqun Zhang, Yihua Cheng, Aleš Leonardis, Hyung Jin Chang

Contact-based grasp generation plays a crucial role in various applications. Recent methods typically focus on the geometric structure of objects, producing grasps with diverse hand poses and plausible contact points. However, these approaches often overlook the physical attributes of the grasp, specifically the contact force, leading to reduced stability of the grasp. In this paper, we focus on stable grasp generation using explicit contact force predictions. First, we define a force-aware contact representation by transforming the normal force value into discrete levels and encoding it using a one-hot vector. Next, we introduce force-aware stability constraints. We define the stability problem as an acceleration minimization task and explicitly relate stability with contact geometry by formulating the underlying physical constraints. Finally, we present a pose optimizer that systematically integrates our contact representation and stability constraints to enable stable grasp generation. We show that these constraints can help identify key contact points for stability which provide effective initialization and guidance for optimization towards a stable grasp. Experiments are carried out on two public benchmarks, showing that our method brings about 20% improvement in stability metrics and adapts well to novel objects.