Multimodal attributed graphs (MAGs), in which nodes carry text, images, and other modalities while edges encode relations among entities, underlie e-commerce, social media, content platforms, and creative applications. Learning on MAGs has developed along two complementary lines: graph-centric methods redesign how modalities are fused, propagated, and connected within message passing, while foundation-model-centric methods pretrain transferable multimodal graph encoders or bring graph context into multimodal large language models for prediction and generation. In parallel, several benchmarks have appeared with different datasets and evaluation protocols. This survey takes an algorithm-centric and evaluation-grounded view of the field and makes three contributions. Modeling: we introduce a unified message-passing formulation and organize methods into five integration levels (feature, propagation, topology, learning, and foundation model), covering discriminative and graph-conditioned generative models; within this formulation we derive representative methods as special cases, compare their assumptions, expressiveness, and cost, and identify cross-modal sensitivity as a property that separates otherwise similar architectures. Datasets and evaluation: we review recent benchmarks, summarize their datasets and metrics, define model-independent descriptors (label homophily, average degree, clustering, and edge provenance), and map each evaluation protocol to the baselines it uses. Frontiers: we connect multimodal graph learning to AI agents, covering the multimodal graphs that agents perceive and remember and graph engineering, the practice of organizing agent workflows as explicit graphs; we then discuss open problems, concrete efforts for the community, and research directions, including when graph structure helps in the presence of strong multimodal foundation models.
Does a useful self-update remain useful after the model updates again? Third Eye separates immediate performance from the outcome of a further native update. We evaluate five 3-8B backbones on math and code: 64 fresh runs, three candidates per run, and three continuations per candidate. Selection and final scoring use disjoint items. In the balanced Qwen3-4B/Llama-3.2-3B comparison, immediate-selected utility is near zero, but continuation reduces it by 1.78 percentage points (simultaneous 95% interval [0.68, 2.88]). Candidate-averaged immediate utility is already negative: selection partly accounts for the apparently neutral first step. Continuation also lowers utility for SmolLM3-3B and Llama-3.1-8B; Qwen3-8B remains inconclusive. Target and out-of-distribution losses dominate retention changes. Matched recipe and recipient-donor controls identify neither a reliable mitigation nor a single mechanism. The results support evaluating persistent self-updates as adaptation transitions, with independent scoring and a no-update baseline, rather than interpreting immediate performance as their full value.
Large language model (LLM) agents are being explored for circuit design, but their ability to produce high-quality custom layouts has not been extensively evaluated. ICLayout-Bench is a benchmark in which agents use electronic design automation (EDA) tools to construct and optimize GDSII layouts from transistor-level circuit netlists. These layouts are evaluated using physical verification, parasitic extraction, and post-layout simulation. Layouts that pass the physical and functional checks are scored on electrical performance and area. The benchmark includes 165 tasks across 13 process design kits (PDKs), covering technology nodes from 3 nm to 180 nm. The tasks span analog, mixed-signal, and digital circuits in open-source and commercial EDA flows. The experiments evaluate 22 configurations spanning seven models on 21 public and 19 private tasks. Mean layout scores range from 4.22 to 80.26 on public tasks and from 1.43 to 67.01 on private tasks, on a 100-point scale. Higher reasoning effort does not consistently improve mean scores, and configurations with comparable scores can incur substantially different model costs.
Overlapping imaging manifestations complicate the differential diagnosis of Diffuse Cystic Lung Diseases (DCLDs), while limited annotated data constrain supervised model development. Multimodal Large Language Models (MLLMs) can integrate imaging and clinical information, but their diagnostic reasoning remains limited by incomplete volumetric perception and insufficient grounding in disease-specific evidence. We propose DCLDs-EIR, an evidence-grounded iterative reasoning framework coupling diagnostic hypothesis refinement with multimodal evidence acquisition and verification. Multiview renderings of predicted lung and cyst segmentations characterize global cyst distributions and initialize the differential diagnosis. Competing hypotheses guide axial CT inspection to identify local findings that, together with clinical context, inform retrieval from a disease-specific knowledge graph. Accumulated patient observations and retrieved knowledge are jointly assessed for diagnostic support and refutation to revise the diagnostic state. Updated hypotheses and unresolved distinctions guide subsequent inspection, forming a feedback loop between evidence acquisition and hypothesis verification. Multicenter evaluation demonstrates that DCLDs-EIR consistently improves diagnostic accuracy over baselines and enables traceable differential diagnosis through explicit links between diagnostic hypotheses, patient observations, and disease-specific knowledge.
Spike cameras encode dynamic scenes into high-temporal-resolution binary spike streams for efficient high-speed vision. Although spiking neural networks (SNNs) can process such signals with sparse and accumulate-only computation, existing SNN-based reconstruction methods are typically shallow and still lag behind ANN-based models in reconstruction fidelity. This paper proposes MADSNet, a Multi-scale Axial-attentive Dense Spiking Network for spike camera image reconstruction. MADSNet adopts a hierarchical spiking encoder--decoder, where a multi-scale spike stem extracts early features, axial spike attention captures long-range dependencies, a dense spiking bottleneck enhances feature reuse, and a spike-to-continuous decoder reconstructs continuous intensity images from spike-domain representations. Experiments on gray-scale and color spike reconstruction show that MADSNet outperforms SSIR by 4.3 dB PSNR and Spk2ImgNet by 1.94 dB on SREDS. Compared with Spk2ImgNet, it achieves about 15$\times$ lower latency and uses only about 1/40 of the estimated energy, demonstrating that carefully designed SNN architectures can improve reconstruction quality while preserving computational efficiency.
Distilling flow matching models for one-step generation generally follows two paradigms. Trajectory alignment supervises the student with the teacher's probability flow ODE, but its performance degrades under very small sampling budgets. Distribution matching directly optimizes the generated distribution, but estimating its reverse Kullback-Leibler gradient typically requires a separate network to track the evolving student score. We propose trajectory-regularized distribution distillation (TRD), which combines distribution-level and trajectory-level supervision through a momentum-mixture policy predicted in a single student forward pass. This policy serves simultaneously as a one-step generator, an estimator of the student's marginal velocity that removes the need for a second trainable network in distribution matching, and a closed-form time-dependent velocity field supervised along the teacher ODE trajectory. Experiments on SANA-1.6B and Stable Diffusion 3.5 show that TRD outperforms representative consistency and distribution matching baselines in generation quality and training efficiency for both one-step and few-step generation, with a trade-off in sample diversity.
Surgical action-center localization requires both an accurate reference point and a decision about whether to report it. When frames with and without a reportable center are mixed, the benefit of improved localization depends on which correct candidates survive selection. We present a selective localization pipeline combining heatmap and coordinate supervision with a logistic-regression scorer. The scorer learns to identify predictions with a reportable center and a localization error within a specified tolerance. The internal evaluation uses 5,000 frames from 50 surgical sources, five source-grouped folds and two random seeds. Matched locator and scoring comparisons track correct candidates and their rejection. At an 80% acceptance quota per source and a tolerance of 0.10 times the image diagonal, our method retains 46.08 correct outputs per 100 inputs. The baseline locator with the same scoring approach retains 44.20. The gain is 1.88 (descriptive 95% source-paired bootstrap interval, 0.94 to 2.79). Under entropy-based selection, increased rejection of correct predictions offsets the higher supply of correct predictions on average. For the coordinate-supervised locator, supervised scoring reduces these rejections from 6.15 to 2.99 per 100 inputs. Evaluating retained correct outputs reveals whether a selection rule preserves or erodes an improvement in localization.
Open-vocabulary object detection (OVD) expects the model trained on base classes to recognize both base and novel classes at inference. Typical methods rely on CLIP-style vision-language embeddings, yet the learned space is often biased toward base categories, with limited effective capacity preserved for novel concepts. Such a base-dominated representation can compress novel semantics, leading to semantic collapse and mis-calibrated confidence at inference. To address this issue, we present PR-OVD, a partition-and-refine framework that explicitly reserves capacity for novel categories and strengthens category separation, while being seamlessly integrated into different detector architectures. Specifically, PR-OVD first performs coarse partitioning to build global divisions for base, novel, and an explicit background partition in both visual and textual modalities, preventing object-irrelevant embeddings from leaking into category-specific representations. It then applies category-level refinement within each partition to sharpen decision boundaries and alleviate the lack of fine-grained region-level pretraining in CLIP. To further provide reliable visual anchors for novel categories, we design a cognitively inspired Structure Prompt (SP) that encodes both egocentric attributes and allocentric context, facilitating stable partition-and-refine learning. Extensive experiments on two OVD benchmarks show that PR-OVD delivers an average 6.5\% proportional improvement on novel categories over the state-of-the-art methods. Notably, PR-OVD also benefits other open-vocabulary tasks, including segmentation and classification, further confirming its effectiveness and generality.
Generalized category discovery (GCD) aims to discover novel categories from unlabeled data by leveraging limited labeled samples from old classes. Existing methods that rely solely on visual cues often neglect the multimodal nature of human perception, prompting recent approaches to incorporate textual information such as category tags and attributes. However, these approaches typically entangle global tags and local attributes within a shared global image representation, rendering attributes unreliable and potentially providing misleading cues that can drive the model toward incorrect predictions. To this end, we propose AptM-GCD, a novel multimodal framework that exploits apt textual guidance through attribute evidence learning and multimodal prompt reasoning. Specifically, we design an Attribute-Evidence Learning (AEL) mechanism that treats attributes as localized visual evidence rather than global category descriptors. By interacting attribute embeddings with patch-level visual tokens, AEL identifies reliable attribute-related regions and extracts discriminative local evidence, thereby reducing the impact of noisy or irrelevant attribute cues. Building upon the extracted evidence, we further develop a Multimodal Prompt Learning (MPL) mechanism to bridge local attribute semantics and global visual understanding. MPL converts fine-grained textual evidence into visual prompts and injects them into a multimodal prompt transformer, enabling attribute information to enhance category discrimination through contextual reasoning without enforcing direct global alignment between modalities. Extensive experiments on six datasets demonstrate that AptM-GCD consistently achieves SoTA performance across both fine-grained and generic benchmarks. Moreover, the proposed framework exhibits strong generalization ability, delivering consistent gains under unimodal and class-imbalanced GCD settings.
Time-series forecasting has recently seen a paradigm shift with the introduction of foundation-style models that adapt large pretrained language architectures to sequential data. However, effectively exposing fundamental temporal structures, such as trend, scale, and temporal dependence, to these models remains an open challenge, particularly when the available observations are limited. In this paper, we conduct an exploratory empirical study across different generations of forecasting architectures and propose StatPrompt-LLM, a lightweight statistical refinement of Time-LLM. StatPrompt-LLM augments the existing Time-LLM prompting mechanism with dataset-level statistical information and introduces a zero-initialised autoregressive bypass as a complementary linear forecasting pathway. We evaluate our framework on electricity and meteorological time-series benchmarks, including ETTh1, ETTh2, and Weather, under full-prefix and reduced-prefix configurations. Under the 10% reduced-prefix configuration, StatPrompt-LLM achieved lower in-sample prediction errors than Time-LLM, with unweighted average relative reductions across datasets of 40.2% in MSE and 21.4% in MAE. Full-prefix results were more dataset-dependent. Ablation analyses revealed relatively modest and dataset-dependent changes when selected additional statistical descriptor groups were masked within the combined architecture. Computational profiling indicated additional model parameters and runtime overhead relative to Time-LLM.
Large Language Models (LLMs) show strong potential for social media content moderation, but their trustworthiness beyond overall accuracy remains underexplored. We introduce TrustMod-SM, a benchmark of roughly 29,000 instances across eight datasets, to evaluate LLM moderators on five dimensions: trustfulness, fairness, safety, robustness, and context integrity. Evaluating 16 open-weight models (0.5B-284B parameters, spanning text-only and vision-language architectures) and one closed frontier model, we find persistent trustworthiness gaps. Higher detection accuracy often coincides with greater demographic disparity, and models frequently comply with concealment or exaggeration prompts, assign high confidence to wrong predictions, rarely escalate ambiguous cases, and struggle to separate hate speech from counter-speech or reclaimed language (especially below 8B parameters). Scaling does not uniformly resolve these issues, and no single model excels across all five dimensions.
A paleographer applies a script type classifier to unseen manuscripts. We measure how much testing on other pages of training manuscripts inflates accuracy. On VML-HP-ext (715 pages, 171 Hebrew manuscripts, 14 script classes) we compare page-level and manuscript-level splits. Page-level accuracy drops from 97% to 54% (59% at manuscript level), and is 39% on the official blind test set. The gap of 40 to 47 percentage points (pp) at patch, page and manuscript level is statistically significant and reproduces with ResNet18; on binarized patches (ink and background only) it is 34 to 42 pp, also significant. On unseen manuscripts the model is overconfident: mean confidence 70% against 54% correct pages; patch-level expected calibration error (ECE, mean gap between confidence and accuracy) rises from 0.065 to 0.444. Binarization leaves patch-level overconfidence but cuts it markedly at page level. Confidence still helps triage: in the more confident half of pages 67% are correct, 41% in the rest. Training on expert soft labels showed no evidence of an accuracy difference, though a small page-level loss cannot be ruled out. The predicted distributions are closer to the expert's assessment. ECE is lower at patch level (0.21 to 0.31) and in most runs at page level, but not significantly at manuscript level. Label smoothing (blurring the label, no expert input) also lowers ECE but comes no closer to the expert. Temperature scaling (post-training confidence correction) helps significantly only at patch level. On 97 pages of 16 manuscripts with mixed expert assessment, soft labels cut divergence from the expert by 22 to 30% (significant in four of five runs); the point estimate of accuracy is 16.5 to 23.7 pp below hard labels, but with 16 manuscripts the loss can neither be confirmed nor ruled out. We propose recommendations for the evaluation protocol; code will be released with the paper
Large language models (LLMs) can generate SQL and SQL--Python workflows for investment research, but ensuring point-in-time (PIT) validity remains challenging. Agents must enforce disclosure cutoffs and select the appropriate historical states and record versions throughout data retrieval and financial analysis. We introduce \textsc{BuySideFlow}, a benchmark of 408 practitioner-derived Chinese-language tasks spanning equities, funds, fixed income, and macroeconomics over a fixed snapshot from a licensed production financial database. We provide executable references and a taxonomy of temporal errors, pairing result checks with expert audits of executed workflows. We evaluate nine agent configurations on all tasks, with result accuracy ranging from 16.2\% to 36.8\%. An audit of 900 runs on 100 shared tasks confirms PIT violations in 193 of the 380 runs that pass result checks (50.8\%), showing that output agreement alone does not establish temporal validity.
While federated reinforcement learning (RL) has traditionally guaranteed high efficiency in homogeneous environments, collaboration is often hindered when agents possess distinct goals. In this paper, we flip this paradigm, framing reward heterogeneity not as a hurdle to consensus, but as a structural asset that catalyzes exploration. We first propose Personalized Federated Upper Confidence Bound Value Iteration (PF-UCBVI), which achieves optimal linear speedup by decoupling shared dynamics from personalized objectives. To eliminate the risks of explicit exploration, we then introduce Personalized Federated Exploration-Free Value Iteration (PF-EFVI), a purely greedy algorithm that leverages reward diversity to ensure state-action coverage. We prove that PF-EFVI attains logarithmic regret without explicit exploration bonuses under sufficient reward diversity. Our results reveal that agent disagreement shifts the exploration burden from temporal complexity to spatial diversity, enabling efficient collective learning without explicit exploration.
Federated fine-tuning with low-rank adaptation (LoRA) reduces communication and computational overhead by training and exchanging compact trainable LoRA factors. Clients may use different LoRA ranks to meet adapter communication budgets and accommodate different local adaptation needs. The server must process these differences during aggregation and construct adapters at each client's rank for local training. We distinguish pre-aggregation alignment, which handles factor dimensions and scaling conventions before aggregation and rank-specific LoRA adapter extraction, which constructs client-sized pairs from the aggregated global model. Two common approaches to rank-specific extraction are direct rank truncation and Singular Value Decomposition (SVD) of the dense update. Direct prefix truncation keeps the leading columns of one aggregated factor and the corresponding rows of the other. It is cheap but can increase reconstruction error. The dense SVD approach first forms the product of aggregated LoRA factors. It then decomposes this matrix and retains the leading singular components to construct adapters at the target rank. This gives the optimal rank-constrained approximation in Frobenius norm but incurs significant computational overhead. To address this trade-off, we propose RBLA+ as an extension of RBLA. It uses established compact QR/core-SVD decomposition to minimize Frobenius error for the extracted LoRA update without forming the dense update. It also accounts for client and server scaling conventions during upload and broadcast. Across vision and language tasks, RBLA+ improves accuracy over RBLA in multiple heterogeneous settings. In CPU benchmarks with synthetic adapters, RBLA+ has lower extraction time than the dense partial-SVD baseline. RBLA+ preserves each client's prescribed adapter size and per-round communication payload.
Privacy-aware person re-identification (Re-ID) from top-view cameras replaces frontal appearance with anthropometric shape, while depth sensing further reduces color-based identity cues. The ICPR 2026 TVRID competition evaluates this setting using 86 identities captured by four synchronized Intel RealSense D455 cameras with RGB and Depth streams across flat, ascent, descent, and oblique viewpoints. Performance is measured using mAP and CMC@1 across within-camera in/out, ascent-descent, and flat-oblique scenarios. The competition had 147 registered participants and 33 final submissions. Three teams from IIT Patna participated: 'abhinavkumar03' and 'sjkdgfhl_' ranked 5th and 7th among 31 ranked participants, and 'vivek katuri' reached 77.67% CMC@1 / 85.20% mAP on the RGB track. This paper presents the methods of the two top-10 teams. Methodology 1 (abhinavkumar03) achieves 93.51% mAP and 90.42% CMC@1 on Depth, ranking 4th of 28, while Methodology 2 (sjkdgfhl_) reaches 99.63%/99.35% on RGB and 86.26%/80.34% on Depth. Both substantially outperform the 57.19% track-average Depth mAP, with Methodology 1 yielding a 7.3-point gain over Methodology 2. These results demonstrate the importance of depth representation and supervision for privacy-preserving Re-ID.
Monitoring a visible channel can change how learned agents communicate without removing why communication is useful. We test this distinction in an end-to-end game where a sender and receiver learn a discrete protocol and route policy without communication supervision. In two independent 20-seed batches, 20/20 and 19/20 protocols form. Online partial coverage increases shadow-route share over no monitoring by .701 [.574,.826] and .575 [.412,.737], while task accuracy remains .905/.913 and signed frozen message contribution remains .592/.563. Complete coverage removes most selective migration without removing communication. Frozen interventions, including a fresh pre-outcome confirmation, show that route is semantic: joint message--route shuffling changes .668 of receiver predictions and route alone retains .388 accuracy versus .25 chance. A corrected explicit-silence cost makes 18/20 policies fully silent and lowers mean sending to .050, but its strict complete-suppression gate fails because two seeds retain communication. Failed semantic-evasion and operational gates further bound the result. The evidence supports adaptive reallocation of a joint message--route code under partial monitoring, not open-world route discovery, emergent encryption, or a universal defense.
Recent advances in large models have accelerated AI for Science toward agentic science, where AI agents autonomously conduct scientific discovery. Realising this vision requires closing the loop between computational reasoning and physical experimentation, positioning self-driving laboratories (SDLs) as critical enablers. However, existing SDLs exhibit a fundamental paradox: foundation model integration has increased linguistic sophistication while severing physical grounding. By treating models as disembodied planners that output symbolic workflows for separate robotic systems, current architectures inherently block the development of embodied experimental intuition. We argue that overcoming this paradox requires embedding \emph{learnability} along three interdependent axes: cognitive learnability (learning what to investigate), experimental learnability (learning where to search), and embodied learnability (learning how to act). Building on this view, we introduce the Embodied Science Agent (ESA), which unifies digital intelligence with physical embodiment through three synergistic components: a Digital Agent that provides cognitive and experimental learnability via memory-based reasoning and Bayesian optimisation, an Embodied Agent that provides embodied learnability via generalisable instrument control, and an Embodied Unified Interface for seamless coordination. We validated ESA in autonomous wastewater treatment experiments, navigating over 200 million possible conditions. Through 15 continuous rounds, ESA raised the final solution transmittance from 82\% to 99.7\%, corresponding to a 98.5\% reduction in residual dye concentration and near-complete decolourisation, while its learned visuomotor policies generalised across varying instrument placements, a promising step toward next-generation SDLs for autonomous scientific discovery.
DeepSeek Sparse Attention (DSA) reduces the computational cost of attention through token-level selection. However, its indexer still scores the entire causal prefix for each query, making indexing a dominant source of latency in long-context inference. Notably, the indexer alone can account for more than 50% of total prefill GPU time at long context lengths. To address this bottleneck, we propose ADIndex, an Adaptive and Distillation-driven Indexing method for token-level sparse attention. ADIndex integrates three key components: (i) a layer-wise calibration strategy that adaptively accommodates cross-query retrieval overlap, motivated by our observation of pronounced inter-layer heterogeneity; (ii) a group-level distillation scheme that leverages this heterogeneity to efficiently train adaptive layer-wise group indexers, capturing salient retrieval signals from individual queries; and (iii) a low-latency inference strategy that reduces repeated full-prefix scans through token bank sharing within query groups while retaining query-specific refinement. Experiments on DeepSeek-V3.2 and GLM-5.1 demonstrate that ADIndex preserves near-lossless task performance on LongBench, LongBench v2, and RULER while delivering substantial efficiency gains over standard DSA, including prefill and decoding kernel speedups of up to 6.22x and 3.40x, respectively, at a context length of 256K across the layer-wise reuse configurations, as well as an end-to-end serving speedup of 1.54x at a context length of 128K.
Time-series classifiers deployed in risk-sensitive domains must be (1) accurate, (2) interpretable, and (3) able to abstain when evidence is weak. Existing methods do not deliver all 3 at once, and the obstacle is structural, rather than logistical. Meaningful temporal patterns cannot be defined without knowing segment boundaries, yet meaningful boundaries cannot be placed without knowing which patterns to expect. Existing approaches break this circularity by using fixed windows or expert-annotated vocabularies, thereby sacrificing at least one of the 3 properties. We introduce ConceptTime, which closes the loop through a single self-supervised signal. A frozen probabilistic forecaster predicts a distribution over the next observation at every timestep of the sequence. We call the mismatch between its prediction and the realized signal the predictive surprise. This signal both locates segment boundaries and characterizes each resulting segment through the forecaster. Segments are thus grounded by how they behaved relative to expectation, not by what they look like. These summaries cluster into a vocabulary of dynamical regimes that we call concepts. A lightweight head classifies from the concept sequence, and the distance to the nearest concept yields reliability by design. Across 17 public benchmarks, ConceptTime is competitive with state-of-the-art black-box accuracy, beats every interpretable baseline, and retains near-98% accuracy on Epilepsy with 1% of labels. It further remains competitive with softmax, prototype-distance, and SHAP/TimeX/TimeX++ on OOD detection and deletion faithfulness, without a single annotation, language model call, or domain expert. Code is available at: https://github.com/Sachithx/ConceptTime.git.