Neural Architecture Search (NAS) automates the design of Vision Transformer (ViT) architectures. However, the high computational cost of training-based methods has made training-free, zero-cost proxies a key research direction. While existing proxies can estimate model potential, they fail to capture critical information transmission characteristics due to the black-box nature of neural networks. Consequently, they suffer from high computational latency and weak correlation with ground-truth performance. Although information transmission determines performance, it has not been effectively quantified or utilized. This limitation remains the core bottleneck for current zero-cost proxies. In this paper, we propose Info-NAS, a zero-cost proxy based on architectural information. This method achieves the first structured quantification of information transmission in ViT. Specifically, it evaluates architectures using three core components: global information volume, local information gradient, and global consistency. Info-NAS derives proxy scores solely from architectural parameters, requiring no forward or backward propagation. Consequently, the calculation and search processes are highly efficient. Moreover, we construct the ViT-Info-Bench dataset to facilitate correlation analysis and algorithm evaluation. Experimental results demonstrate that Info-NAS significantly reduces search overhead while achieving superior ranking accuracy. With a single evaluation requiring only 1.8 ms, Info-NAS outperforms existing methods in both efficiency and performance.
论文检索
输入标题、作者或关键词，从 990 篇学术成果中精准定位
Intracranial aneurysms are life-threatening and require accurate, timely detection. Traditional manual diagnosis by radiologists can be subjective, leading to misdiagnoses, while existing deep learning approaches struggle with small aneurysms or cases complicated by surrounding tissues. In this paper, we present the Multi-View Refinement Network (MVRNet), a framework that delivers clinically meaningful performance gains on the most challenging intracranial aneurysm cases. It directly addresses real-world diagnostic difficulties, particularly for small, obscured, or ambiguously bounded lesions that conventional methods often miss. In particular, we propose a feature enhancement technique to obtain boundary-clear CTA, an informative supplement to the bone-free CTA, to further reduce the impact of noise and enhance the robustness of IA recognition. Moreover, we develop a multi-view encoder with 2D slicing in different directions to mitigate tissue occlusion effects, coupled with a progressively refined decoder that iteratively corrects uncertain predictions, ensuring precise localization and segmentation. Experimental results indicate that MVRNet improves the F1-score by 24% and the IoU by 16% in comparison with the state-of-the-art methods. Remarkably, previous methods struggled with challenging cases, while our method still achieves satisfactory results, demonstrating a >2× improvement over prior arts on challenging test sets. Our code has been released in https://github.com/TheResearchWorks/MVRNet.
In many real-world scenarios, agents operate across heterogeneous environments where the underlying dynamics and data-generating processes vary. Standard reinforcement learning and imitation learning methods often fail in such settings as they typically assume stationarity and learn policies that overfit to environment-specific correlations. A key challenge is the presence of spurious correlations as observed states often contain both causal and non-causal features, with the latter introducing environment-specific biases that undermine generalization. To address this problem, we propose DropConnect-based Causal Imitation Learning (DCIL), a novel offline imitation learning framework designed to identify and exploit stable causal mechanisms across diverse environments. DCIL introduces a gradient alignment constraint that encourages the policy to align with causal structures shared across training environments. To further mitigate overfitting to spurious correlations, DCIL involves DropConnect-based regularization, injecting stochastic perturbations into network weights to simulate parameter uncertainty and reduce reliance on unstable features. We evaluate DCIL on synthetic benchmarks derived from OpenAI Gym control tasks, where non-causal features exhibiting spurious correlations are explicitly injected to simulate environmental heterogeneity. Experimental results show that DCIL outperforms state-of-the-art imitation learning baselines, achieving superior generalization to unseen environments. These findings highlight the importance of incorporating causal reasoning and structured regularization into policy learning for robust performance under environment shift.
Large Language Model (LLM)-based navigation systems have commonly constructed expli cit spatial representations (e.g., topological graphs, semantic raster maps) and translated them into textual descriptions as LLMs’ inputs. However, the linguistic structures of such text-based spatial representations and the choices of contextual features (e.g., topology, geometry) they contain are often treated as neutral engineering decisions rather than key factors that shape LLMs' behavior. To address this gap, we propose a dual-interventional framework that disentangles linguistic structures from different contextual cues to evaluate the linguistic inductive bias of LLMs for navigation planning. In the framework, representation intervention varies linguistic format and the degree of linguistic compression, clarifying when linguistic representations support or inhibit navigation planning; context intervention, combined with contextual feature combination and conflict probing, explicitly clarifies the preferences and weaknesses of LLMs when processing different contextual cues. Experiments across diverse spatial reasoning tasks and multiple model scales reveal a consistent pattern: topological information is a sturdy shield and the backbone of robust planning; linguistic format is a double-edged sword whose effect depends on model size, task demands, and the compression level; and semantic information is a fatal Achilles' heel---incorrect semantic cues can systematically derail the planning process. Overall, our study shows that effective text-based spatial representations in LLM-based navigation should preserve topological integrity, calibrate representational compression to model capacity, and ensure semantic correctness, rather than simply adopting a single representation.
Partial-label learning (PLL) addresses challenging scenarios where each instance is associated with a set of candidate labels and only one is the truth. Most existing PLL methods rely on static disambiguation heuristics, which are prone to error propagation when the ambiguity labels are high. To address this issue, we propose a novel mutual information guided reinforcement learning framework for partial label disambiguation (MR-PLL). In this framework, label disambiguation is formulated as a sequential Markov decision process, where an agent dynamically discriminates whether to retain, modify, or abstain from correcting ambiguous labels. To ensure reliable decision making, we introduce a mutual information guided gating mechanism that adaptively adjusts the confidence of soft label propagation according to the dependency between feature representations and labels. The abstention mechanism allows the model to postpone uncertain decisions, resulting in more reliable disambiguation. Furthermore, we design an information weighted reward term during the actor-critic process to gradually improve the label disambiguation ability of the policy, and provide theoretical analysis on convergence and bias reduction. Experiments on benchmark and real datasets verify the effectiveness of the proposed algorithm.
The Kidney Exchange Problem is a prominent challenge in healthcare and economics, arising in the context of organ transplantation. It has been extensively studied in artificial intelligence and optimization. In a kidney exchange, a set of donor-recipient pairs and altruistic donors are considered, with the goal of identifying a sequence of exchanges—comprising cycles or chains starting from altruistic donors—such that each donor provides a kidney to the compatible recipient in the next donor-recipient pair. These exchanges create a network of transplants aimed at maximizing the total number, t, of successful transplants. Due to constraints in medical resources, limits are often imposed on the lengths of these cycles and chains. Recently, this problem was deterministically solved in O* (14.34ᵗ) time (IJCAI 2024). In this paper, we introduce the representative set technique for the Kidney Exchange Problem, showing that the problem can be deterministically solved in O* (6.855ᵗ) time.
High dynamic range (HDR) imaging is crucial for capturing real-world lighting conditions. HDR imaging is traditionally achieved either by fusing multiple exposure frames or via inverse tone mapping from a single SDR image. However, the multi-exposure HDR method is prone to motion-induced artefacts and imposes demanding hardware requirements, limiting its practical applicability. Traditional inverse tone-mapping techniques primarily rely on pixel-wise regression methods, which ignore semantic scene contexts and thus frequently introduce halo artefacts and structural distortions. To address this limitation, this paper proposes MLLM-ITM, a novel inverse tone-mapping framework incorporating multimodal large language models (MLLMs). MLLM-ITM utilizes cross-modal features extracted from a frozen MLLM to simultaneously encode visual features and semantic understanding. These features are integrated into a downstream HDR reconstruction backbone through lightweight adapters, enabling content-aware dynamic-range expansion. Furthermore, the decoupled design between MLLM and HDR backbone avoids costly fine-tuning of MLLMs and remains model-agnostic, allowing effortless substitution with emerging multimodal architectures. Extensive experiments on public benchmarks demonstrate that the proposed MLLM-ITM achieves state-of-the-art performance compared with existing inverse tone-mapping methods, highlighting the effectiveness of cross-modal semantic priors in enhancing HDR imaging performance.
Retrosynthesis prediction is a cornerstone of drug discovery, enabling the synthesis of novel therapeutic candidates. However, current deep learning models falter when navigating the unexplored chemical space essential for innovation. In these realistic scenarios, models face a challenging mixed out-of-distribution (OOD) shift: they must handle both novel molecular scaffolds (covariate shift) and unseen reaction templates (label shift), leading to severe performance degradation. To address this, we propose AgentRetro, a framework integrating spectral domain generalization with Large Language Model (LLM) agents. It features a Spectral Domain Enhancer (SDE) that partitions chemical space via spectral clustering to capture diverse domain structures, and a Multi-Knowledge Agent (MKA) that enriches data with LLM-generated OOD reactions and textual rationales. These components are unified by a dual training strategy: meta-learning for template adaptability and adversarial learning for structural invariance. Crucially, our analysis reveals that explicitly decoupling structural invariance from mechanistic adaptability is essential for overcoming the interference between conflicting distribution shifts. Experiments show AgentRetro consistently improves state-of-the-art baselines, notably boosting EditRetro’s OOD Top-10 accuracy from 41.7% to 50.1%. The source code is available at https://github.com/jiahangshen/IJCAI26-AgentRetro.
Computation Tree Logic (CTL) is a fundamental formalism for specifying and reasoning about the behavior of non-terminating systems. Due to the lack of uniform interpolation (UI) property, CTL is usually limited in modular reasoning and system abstraction. This paper studies uniform interpolation in CTL fragments with restricted temporal operators from the point of knowledge forgetting, aiming to identify the minimal logic extensions of these fragments that preserve UI property (referred to as their uniform interpolation closure). Our results demonstrate that: (1) CTL(X), the fragment of CTL allowing only the “neXt” operator, enjoys the UI property; (2) the UI closure of the fragment CTL(F<, X) is the bisimulation-invariant fragment of quantified CTL in prenex-normal-form, where F< is the operator “next Future”; (3) CTL(F<) fails to possess Craig interpolation, and every extension of CTL(F<) that possesses the Craig interpolation property is necessarily an extension of CTL(U) which contains only the “Until” operator. These findings provide a precise characterization of the expressive power required to achieve modularity in CTL.
Recently, diffusion models have been applied to reformulate the regressive portrait matting task as a gradual denoising-driven generative process, alleviating the inherent limitations of discriminative models via iterative error correction. However, due to the lack of high-quality ground-truth mattes, existing generative methods for portrait matting still suffer from severe detail degradation, especially in structurally delicate hair strands and pixels with ambiguous colors and context. To address these challenges, we propose OrienDiffusion, a diffusion-based framework tailored for fine-grained portrait matting. Specifically, we construct a Hair Orientation Field to conditionally guide the denoising process, constraining the generation toward authentic structural consistency in hair regions. Furthermore, instead of relying on overly encoded deep features or ambiguous original color cues as existing methods do, we develop a Pixel Color-anchored Local Structure Embedding approach, which models alpha matte transitions as local structural variations, achieving accurate alpha estimation in pixels with ambiguous colors or context. Extensive experiments on multiple portrait matting datasets demonstrate that OrienDiffusion achieves state-of-the-art performance in these matting challenging regions. Code is available at https://github.com/xtz0001/OrienDiffusion.
Gait recognition has achieved remarkable success in constrained environments, yet its performance often degrades significantly in cross-domain and cross-vertical-view scenarios. This is primarily due to the fact that domain-specific silhouette geometry causes models to overfit to extrinsic geometric characteristics rather than learning generalizable motion patterns. To address this issue, we present ViSA-Gait, which utilizes Vision Foundation Models (VFMs) as a “Semantic Compass” for stable universal human body knowledge guidance, enabling a lightweight backbone to robustly capture fine-grained gait dynamics. Specifically, we introduce a token-based distillation mechanism where a Spatial Token Learner (STL) and a Temporal Token Learner (TTL) filter dense VFM features into motion-consistent descriptors. These descriptors are then adaptively injected into a lightweight 3D-CNN backbone via a Gated Cross-Attention (GCA) mechanism, functioning as “Semantic Anchors” that regularize the feature space and guide the model to focus on intrinsic body motion. Extensive experiments demonstrate that ViSA-Gait achieves SOTA performance on cross-domain and cross-vertical-view benchmarks while remaining competitive within-domain, offering a new perspective on bridging the gap between geometry-based analysis and universal semantic understanding.
Multimodal clustering (MMC) focuses on learning consistent representations through fusing discriminative features from each modality in an unsupervised fashion. Recently, information bottleneck-based MMC methods transform the representation learning into a non-redundant multimodal feature puzzle process. However, they depend on manually setting the trade-off parameter β to compress task-irrelevant features while preserving task-relevant features, which severely impairs final clustering results. In addition, manually setting β overlooks both the information quality balance and the information quantity balance, hindering the learning of compact and meaningful representations for discovering cluster patterns. In this work, we propose a novel βqq-guided information bottleneck (βqq IB) for addressing the aforementioned problems. The core of βqq IB is a self-balance mechanism that consists of a βquality component and a βquantity component. The βquality component aims to achieve an information quality balance by modeling the relation between task characteristics and data sample scale. Meanwhile, the βquantity component intends to realize information quantity balance through modeling the dynamic changes of data scale within the deep variational architect. Experiments on six benchmark datasets demonstrate the superiority of βqq IB method. To the best of our knowledge, this is the first work to investigate self-balance learning in IB-based multimodal clustering.
Recent writing assistants are increasingly shifting from passive, prompt-driven interaction to proactive, suggestion-based completion, which integrates localized continuations into the writing flow and reduces coordination burden. However, existing evaluations simply focus on output quality, failing to capture how users accept, edit, or repair suggestions in real-time interaction, and thus obscuring the true usability of proactive co-writing systems. To address this gap, we adopt a sequential, behavior-centered view of interactive writing and formalize co-writing as a Human-in-the-Loop Markov Decision Process, modeling writing as an interaction shaped by user acceptance and editing decisions. Based on this formulation, we introduce the Co-Writing Fidelity Suite, an interaction-aware metric suite that captures both user–assistant alignment and cognitive editing effort, including Hierarchical Acceptance Rate and Knowledge-aware Editing Distance. We conduct a large-scale simulation study across 16 writing domains, using 1,688 controlled continuation queries sampled from different writing stages. Our analysis reveals systematic effects of interaction structure on acceptance behavior and editing cost. A follow-up user study with 30 participants confirms that these behavioral patterns align with real user experience. Together, our findings demonstrate that interaction-aware evaluation provides insights beyond output-only metrics and informs the design of more effective proactive writing assistants.
Knowledge Compilation transforms propositional formulas into tractable structures like decision-DNNF to support efficient reasoning. However, these representations often suffer from exponential size, and standard minimization via SAT sweeping is computationally prohibitive for large instances. In this paper, we propose a scalable minimization framework for decision-DNNF that eliminates the need for SAT solvers. We introduce a semantic hashing technique leveraging polynomial-time model counting to rapidly filter redundancies, followed by a polynomial-time verification strategy based on CNF projection. Our experimental evaluation demonstrates that this approach efficiently compresses decision-DNNF circuits while avoiding the bottleneck of NP-hard equivalence checks.
Immune Checkpoint Inhibitors (ICIs) have become a major therapeutic strategy in cancer treatment. However, widespread ICIs use can cause mild-to-severe immune-related Adverse Events (irAEs). Identifying factors associated with irAEs is beneficial for assessing the risk of irAEs occurrence during ICIs treatment. Nevertheless, the lack of sufficient irAEs-related clinical tabular data has slowed progress in this field. Thus, we proposed Tabular data-driven semi-Supervised Learning (Tab-semiSL), a novel Semi-Supervised Learning (SSL) method specifically designed for tabular data. Tab-semiSL can be divided into the pre-training phase and SSL phase. Specifically, in the pre-training, we used the collected dataset of 4,817 cancer patients without the irAEs label to train an auto-encoder. In the SSL phase, the predictor was fine-tuned using the collected dataset of 237 irAEs labeled cancer patients who treated with ICIs. We assigned class-specific thresholds and used samples as pseudo-labels only when their maximum confidence exceeded the threshold, with the thresholds dynamically adjusted during training to improve reliability. We tested Tab-semiSL against three traditional machine learning approaches and five semi-supervised or self-supervised methods using two public datasets plus the collected clinical data, achieving outperformed results across most metrics. SHapley Additive exPlanations (SHAP) analysis revealed ten key factors linked to irAEs. Code and Supplementary Material are available at https://github.com/RuhaoLiu/Tab-semiSL
Forecasting precise future motion of surrounding agents is essential for reliable autonomous vehicles. However, as the demand for longer prediction horizons increases, existing endpoint-completion or iterative-refine methods increasingly struggle with weak guidance and compounding errors. To tackle the long-horizon prediction challenge, we propose Pivot-Centric Trajectory Prediction (PCTP). By introducing "pivots" and focusing on predicting pivot points along extended trajectories, we divide the long-term prediction task into short-term sub-tasks at various scales. Specifically, PCTP decouples the long-term trajectory predicting process into two processes: pivot prediction and pivot-based trajectory refinement. The pivot prediction process aims to utilize global map context and agent-to-agent interactions to identify these "pivot points", while the pivot-based trajectory refinement process focuses on local map details and refines the short-term trajectory based on predicted "pivot points". Compared with existing methods, PCTP provides more intermediate guidance while reducing compounding errors. Moreover, PCTP is a flexible approach that can be integrated into most state-of-the-art trajectory prediction models. Experimental results show that PCTP improves the prediction accuracy of leading models on both Argoverse I and Argoverse II datasets with minimal impact on model size. Specifically, PCTP combined with QCNet outperforms all published ensemble-free methods on the Argoverse II leaderboard at submission.
Predicting the response of anticancer drugs for specific cancer cell lines remains an important challenge in cancer treatment, largely due to the diversity among cell lines. Existing machine learning methods usually perform well on cell lines seen during training, but their performance often drops when applied to new cell lines. Many approaches rely heavily on cell-line specific features, which limits their ability to generalize. At the same time, methods that focus mainly on generalization often fail to capture differences in drug response across distinct cellular environments. Some studies improve prediction accuracy by introducing additional and more detailed cell line features. However, these features are difficult to collect and are frequently missing, especially for newly studied cell lines. To address these issues, we propose a generalizable bias-disentangled framework for drug response prediction. Our method separates drug-related patterns that are shared across cell lines from representations that reflect cell-line specific environments. We further isolate real but non-generalizable biases that arise from noise or unobserved factors. This design helps preserve accurate predictions for specific cell lines while improving performance on unseen ones. In addition, the bias-related branch supports counterfactual consistency learning when some modalities are missing, allowing the model to handle incomplete data. Experimental results show that GBD-DRP achieves state-of-the-art performance, and additional tests on unseen cell lines and missing-modality settings indicate good generalization in practice.
Large language models (LLMs) are increasingly used as general planners in embodied intelligence, enabling high level coordination and low level task planning for both single robot and multi-robot collaboration. This increasing reliance on embodied LLM planners also raises critical security concerns, since misaligned or manipulated instructions can be translated into physical actions. Prior work has studied such threats in single robot settings, while security risks in LLM controlled multi-robot collaboration, especially those propagated through inter robot communication, remain largely unexplored. To bridge this gap, we propose a novel attack paradigm for multi-robot system in which the adversary interacts with only a single entry robot. The compromised robot then propagates malicious intent through peer communication, leading to coordinated unsafe actions across the system. Our evaluation, covering high risk dimensions of dereliction of duty, privacy compromise, and public safety hazards, reveals a persistent safety alignment gap in multi-robot planners. We quantify this process with three metrics, obedience, infectiousness, and stealthiness. Experiments demonstrate both persistent attacker control and rapid propagation: obedience reaches 1.00 in the strongest cases, and infectiousness rises to 0.90. Notably, the attack is highly efficient, requiring as few as 3.0 rounds to compromise all the robots while maintaining a stealthiness score of 0.81. Such risks are amplified when robots must resolve trade offs in critical situations, such as emergencies or conflicts of rights, because the coordination mechanism can unintentionally allow adversarial instructions to override safety requirements. The code is available at https://github.com/TheFatInsect/InfectBot.
Partial Dependence Plots (PDPs) visualize how changes in a single feature affect the average model prediction. They are widely used in practice to interpret decision tree ensembles and other machine learning models. Joint-PDPs extend this idea to pairs of features, revealing their combined effect. Partial Dependence Interaction Values (PDIVs) measure feature interactions. The Any-Order-PDIVs task computes these interactions for every feature subset across all rows of the dataset. We introduce WOODELF++, a unified and efficient approach for computing all these useful explainability tools on decision tree ensembles, building on WOODELF, an algorithm for efficient SHAP computation. By deriving suitable metrics over pseudo-Boolean functions, WOODELF++ can compute PDPs (exact and approximate), Joint-PDPs, and Any-Order-PDIVs in a unified framework. Our method delivers substantial complexity improvements over the state of the art, including an exponential gain for Any-Order-PDIVs. Additionally, we introduce and efficiently compute Full PDPs, which leverage the model’s split thresholds to faithfully capture its behavior across all possible feature values. WOODELF++ is implemented in pure Python and supports GPU acceleration. On a dataset with 400,000 rows, WOODELF++ computes PDP and Joint-PDP up to 6x faster than the state of the art and up to five orders of magnitude faster than scikit-learn. For Any-Order-PDIVs, the gap is even larger: WOODELF++ computes all interaction values in 5 minutes, while the state of the art is estimated to require over 1,000,000 years.
Graph-level anomaly detection (GLAD) is crucial for ensuring the reliability of graph-driven applications by identifying abnormal graphs that deviate from the majority. Considering the privacy concerns in distributed scenarios, federated graph-level anomaly detection (FedGLAD) has emerged as a promising solution to enable collaborative detection without sharing raw data. However, existing methods suffer from poor generalization due to the reliance on unrealistic synthetic anomalies and insufficient personalization capabilities under data heterogeneity. To address these challenges, we propose a novel Federated graph-level anomaly detection approach with Cluster-adaptIve GAted Reconstruction (FedCIGAR). Specifically, we design a reconstruction-based paradigm trained on normal graphs to avoid synthetic data. Furthermore, we introduce a client-side node contribution gating mechanism and a server-side sliding window-based clustering strategy to tackle data heterogeneity. Extensive experiments demonstrate that FedCIGAR achieves superior performance and robustness compared to state-of-the-art methods.