| Total: 22
Structured claim decomposition is often proposed as a solution for verifying complex, multi-faceted claims, yet empirical results have been inconsistent. We argue that these inconsistencies stem from two overlooked bottlenecks: evidence alignment and sub-claim error profiles. To better understand these factors, we introduce a new dataset of real-world complex claims, featuring temporally bounded evidence and human-annotated sub-claim evidence spans. We evaluate decomposition under two evidence alignment setups: Sub-claim Aligned Evidence (SAE) and Repeated Claim-level Evidence (SRE). Our results reveal that decomposition brings significant performance improvement only when evidence is granular and strictly aligned. By contrast, standard setups that rely on repeated claim-level evidence (SRE) fail to improve and often degrade performance as shown across different datasets and domains (PHEMEPlus, MMM-Fact, COVID-Fact). Furthermore, we demonstrate that in the presence of noisy sub-claim labels, the nature of the error ends up determining downstream robustness. We find that conservative "abstention" significantly reduces error propagation compared to aggressive but incorrect predictions. These findings suggest that future claim decomposition frameworks must prioritize precise evidence synthesis and calibrate the label bias of sub-claim verification models.
Identifying cancer driver genes (CDGs) requires integrating heterogeneous biological networks, each encoding distinct mechanistic insights into tumorigenesis. Existing multi-network methods typically fuse views at the feature level or enforce uniform representations, which obscures network-specific signals and limits interpretability. To address this, we propose LogicFusion, a novel differentiable framework that treats each biological network as an independent probabilistic evidence source and explicitly learns how to combine them using logical reasoning. Specifically, LogicFusion maps the output of each view into probabilistic space as independent evidence, and learns a set of logical rules in a differentiable manner. These rules adaptively select and fuse these view evidences through logical conjunction (AND) and disjunction (OR). The final prediction is then obtained via gene-specific weighting. LogicFusion enables both high-accuracy CDG identification and interpretable attribution of predictions to specific networks. Experiments on pan-cancer and cancer-specific datasets show that LogicFusion consistently outperforms state-of-the-art methods, while providing transparency in multi-view genomic reasoning through learned logical rules.
Predicting ligand binding sites on protein surfaces requires capturing complex local geometries and satisfying physical constraints. Existing voxel-based methods suffer from high computational costs and rotation sensitivity, while standard point-cloud GNNs often lack geometric completeness—failing to distinguish chiral structures or subtle topological variations. In this work, we propose UniPocket, a novel E(3)-equivariant surface graph neural network. Inspired by recent advances in efficient geometric completeness, UniPocket constructs a Manifold-Aware Surface Encoder that utilizes local surface normals as virtual reference frames to capture complete geometric invariants without expensive high-order tensor products. Furthermore, we introduce a Ligand-Gated Message Passing mechanism to condition the surface features on the chemical semantics of the target ligand, and a Physics-Aware Vector Rejection Module that enforces steric constraints via orthogonal vector decomposition. Experimental results on standard benchmarks (PDBbind, COACH420, Holo4k) demonstrate that UniPocket achieves state-of-the-art performance, validating that geometric completeness and physical inductive biases are key to precise binding site detection.
Multi-step retrosynthetic planning aims to decompose target molecules into available starting materials by iteratively invoking single-step prediction models within a search algorithm. The success of retrosynthetic planning depends on the joint guidance of single-step reasoning and global search across steps. However, most existing frameworks make step-wise decisions based only on the current molecular state, without explicitly modeling synthesizability signals that reflect long-range reachability. In this work, we propose GuideRetro, a synthesizability-aware framework for multi-step retrosynthetic planning that integrates global synthesizability knowledge into step-wise retrosynthetic prediction. GuideRetro learns transferable knowledge from large-scale reaction networks by modeling the evolution of synthetic complexity along reaction pathways. During planning, a route-aware synthesis state modeling module combines the evolving retrosynthetic route with retrieved global signals to guide reactant generation at each step. Experiments on benchmark datasets show that GuideRetro achieves state-of-the-art performance. The integration of global synthesizability knowledge and route-aware modeling improves planning accuracy and search efficiency under realistic retrosynthetic settings. The code is available at: https://github.com/L-AJ/GuideRetro.
Physiological signals such as EEG, ECG, and PPG are widely used in clinical monitoring. Recent self-supervised learning (SSL) methods offer an attractive way to leverage unlabeled recordings, yet they still fall short in practice. In particular, current SSL methods struggle across heterogeneous datasets, often distorting clinically meaningful structures or learning shortcuts from temporal and cross-channel redundancy. Consequently, existing SSL methods often deliver limited performance under linear probing, a lightweight adaptation setting that better matches real-world medical scenarios. Moreover, most Transformer-based SSL models encode a flattened spatiotemporal token sequence, incurring high computation and memory cost, and are typically developed within a single modality. To address these limitations, we present SPOTR (Spatio-temporal Pooling One-Token Reconstruction), a compress-reconstruct pretraining framework that introduces a single-token global bottleneck for physiological signals. SPOTR compresses each waveform into a single-token representation and reconstructs the signal conditioned only on this representation. Meanwhile, SPOTR introduces an efficient spatio-temporal compaction module to reduce computation and memory cost. Pretrained on 20 datasets spanning EEG, iEEG, ECG, and PPG, SPOTR consistently outperforms the strongest baseline under linear probing, improving average AUC by 18.49%, 21.71%, 17.86%, and 4.64%, respectively. Compared with a representative general-purpose time-series foundation model, SPOTR achieves around 78% lower latency and 52% lower peak GPU memory on average. The code and supplementary material can be found at https://github.com/5GYYYYY/SPOTR.
Deep learning has achieved remarkable success in automated electrocardiogram (ECG) diagnosis. However, the long-tailed distribution of real-world ECG data remains a critical challenge. Existing methods mainly operate at the signal feature level and fail to exploit semantic relationships among diagnostic labels, which limits their ability to effectively recognize rare categories. To address this issue, we propose a Semantics-Guided Representation Learning (SGRL) framework, designed to leverage semantic priors to guide feature learning and thereby correct feature bias under long-tailed distributions. Specifically, we propose a Label Semantic Prompt Adaptation (LSPA) strategy, which introduces ECG-calibrated learnable parameters into label prompts to generate adaptive label semantic embeddings under a semantic-consistency constraint, thereby overcoming the limitations of coarse-grained label prompts in characterizing fine-grained intra-class morphological variations. Subsequently, we propose Semantic-Guided Representation Decorrelation (SGRD) that fuses ECG embeddings with adaptive label semantics and suppresses inter-class semantic correlations to obtain discriminative class semantic anchors, thereby improving tail-class separability. Extensive experiments on multiple public datasets demonstrate the significant superiority of SGRL in long-tailed ECG classification tasks. Our code is available on https://github.com/gfywudi/SGRL.
The knowing--doing gap, the mismatch between ideas articulated during model reasoning and the realized creative artifact, remains a fundamental challenge in creative AI and persists in LLM-based artistic creation. This paper responds to this gap by introducing a systematic and interpretable framework for examining how user intent is articulated during model reasoning and selectively realized, or lost, during action in LLMs, using symbolic music composition as an analytical lens. We present a realizational process theory that formalizes creative generation and localizes the knowing--doing gap at the realization stage. We instantiate this theory with Music Atelier (Mutelier), an LLM-as-a-Judge framework that operationalizes idea-level realization analysis and makes the gap observable and analyzable in practice. Across diverse evaluation settings, we show that Mutelier reveals reliable, previously invisible failure modes in which intent-aligned ideas are articulated during reasoning but fail to materialize in the final artifact. By reframing artistic creation as a realizational process, this work provides a principled process-level foundation for understanding how knowing--doing gaps emerge in machine creativity.
Systematic safety evaluation of large language models must uncover diverse policy violations under tight query budgets. However, most red-teaming methods optimize attack success rate and repeatedly probe a narrow set of vulnerabilities, yielding redundant failures and leaving rarer yet critical violation categories unexplored. Under fixed budgets, such inefficient exploration delays the first discovery and limits category coverage. To address these limitations, we propose the Budget-Efficient Adaptive Cognitive Offense Navigator (BEACON), a budget-aware safety testing framework that uses Cognitive-Guided Monte Carlo Tree Search to navigate the violation search space under fixed budgets. BEACON innovatively approaches safety testing as a budget-constrained failure discovery process, aiming to identify diverse safety violations as early as possible within a fixed query budget. It also provides an efficiency-oriented evaluation perspective that measures early discovery and harm category coverage under budget constraints. Experiments on standard benchmarks and frontier LLMs show that BEACON discovers failures earlier and achieves higher coverage across policy violation categories. These results underscore the value of evaluating safety testing through discovery efficiency rather than attack success rate alone. Warning: This paper contains examples of harmful language and images, and reader discretion is recommended.
Generating protein sequences that reliably fold into target structures is a central challenge in computational biology and protein design. Progress in protein inverse folding (PIF), however, is fundamentally constrained by the scarcity of high-quality structural data, which limits the effectiveness of existing models. In this work, we propose TTS-Design, a test-time compute scaling framework that enhances protein sequence design without retraining models or relying on larger training data. For TTS-Design, its core design is a dedicated inverse folding reward model named IF-RM, which quantitatively evaluates structure–sequence compatibility and enables effective selection among multiple candidate sequences at inference time. By integrating IF-RM into existing PIF models, TTS-Design leverages additional computation during inference stage to explore and refine candidate solutions. Extensive experiments on the CATH 4.2 and CATH 4.3 demonstrate that TTS-Design consistently improves sequence recovery and structural reliability across different backbone models, without retraining or increasing model size. Case studies on real-world proteins further confirm its practical effectiveness. Overall, our results highlight test-time compute scaling as a promising and effective paradigm for advancing protein inverse folding and other scientific problems under data-limited scenarios.
Designing functional protein sequences that satisfy multiple desired properties is a core research focus of protein engineering. Prior methods struggle with inability or inefficiency when dealing with numerous, often conflicting, properties. We propose Multi-Property Protein Diffusion, (MP2D), a unified framework for multi-objective protein sequence optimization that integrates conditional discrete diffusion with constrained MCTS and global iterative refinement. MP2D formulates diffusion denoising as a constrained sequential decision-making process and employs MCTS to explore diverse denoising trajectories guided by Pareto-based rewards. A global iterative refinement strategy further enables repeated remasking and re-optimization of candidate sequences, while a dynamic Pareto constraint prevents candidate bloat and maintains balanced trade-offs across objectives. We evaluate MP2D on two challenging multi-objective protein design tasks: antimicrobial peptide and protein binder optimization, involving four to five conflicting properties. Experimental results demonstrate that MP2D consistently outperforms existing multi-objective baselines, achieving robust and balanced improvements across all objectives without retraining generative models. These results highlight MP2D as a practical and scalable solution for multi-objective functional protein design.
Deploying Video Anomaly Detection (VAD) in real-world surveillance faces a fundamental tension between the demand for high-level semantics to ensure effectiveness and the limited computational resources of edge devices. Vision–Language Models (VLMs) provide rich open-vocabulary semantics, but their latency and computational cost preclude on-device deployment. To address the challenge, we propose MemoVAD, an edge–cloud collaborative framework that selectively incorporates VLM semantics into streaming VAD. MemoVAD runs most inference on the edge with a lightweight detector and a causal Temporal Context Encoder (TCE) to model temporal dependencies. Specifically, we introduce an Uncertainty-Aware Gating (UAG) policy grounded in Subjective Logic to model perceived uncertainty and query the cloud-based VLM only for high-uncertainty and semantically novel clips. Besides, a Dynamic Semantic Memory (DSM) is designed to cache VLM-verified prototypes for efficient retrieval, enabling the edge model to progressively incorporate VLM-level semantics via a semantic adapter. Experiments on UCF-Crime and XD-Violence datasets via a real edge device show that MemoVAD substantially reduces communication overhead while surpassing state-of-the-art performance. The demo video is available at: https://memovad2026.github.io/.
Molecular representation learning aims to learn vector embeddings that capture molecular structure and geometry, thereby enabling property prediction and downstream scientific applications. In many AI for science tasks, labeled data are expensive to obtain and therefore limited in availability. Under the few-shot setting, models trained with scarce supervision often learn brittle structure–property relationships, resulting in substantially higher prediction errors and reduced generalization to unseen molecules. To address this limitation, we propose PCEvo, a path-consistent representation method that learns from virtual paths through dynamic structural evolution. PCEvo enumerates multiple chemically feasible edit paths between retrieved similar molecular pairs under topological dependency constraints. It transforms the labels of the two molecules into stepwise supervision along each virtual evolutionary path. It introduces a path-consistency objective that enforces prediction invariance across alternative paths connecting the same two molecules. Comprehensive experiments on the QM9 and MoleculeNet datasets demonstrate that PCEvo substantially improves the few-shot generalization performance of baseline methods. The code is available at https://github.com/DrugD/PCEvo.
Federated learning (FL) enables collaborative model training without centralizing raw data, but privacy regulations such as the right to be forgotten require FL systems to remove the influence of previously used training data upon request. Retraining a federated model from scratch is prohibitively expensive, motivating federated unlearning (FU). However, existing FU methods suffer from high unlearning overhead, utility degradation caused by entangled knowledge, and unintended relearning during post-unlearning recovery. In this paper, we propose FedCARE, a unified and low overhead FU framework that enables conflict-aware unlearning and relearning-resistant recovery. FedCARE leverages gradient ascent for efficient forgetting when target data are locally available and employs data free model inversion to construct class level proxies of shared knowledge. Based on these insights, FedCARE integrates a pseudo-sample generator, conflict-aware projected gradient ascent for utility preserving unlearning, and a recovery strategy that suppresses rollback toward the pre-unlearning model. FedCARE supports client, instance, and class level unlearning with modest overhead. Extensive experiments on multiple datasets and model architectures under both IID and non-IID settings show that FedCARE achieves effective forgetting, improved utility retention, and reduced relearning risk compared to state of the art FU baselines. The source code can be found at https://github.com/thechosenchu/FedCARE.
Designing enzymes with substrate-binding pockets is a critical challenge in protein engineering, as catalytic activity depends on the precise interaction between pockets and substrates. Currently, generative models dominate functional protein design but cannot model pocket-substrate interactions, which limits enzyme generation with precise catalytic environments. To address this issue, we propose EnzyPGM, a unified framework that jointly generates enzymes and substrate-binding pockets conditioned on functional priors and substrates, with a particular focus on learning accurate pocket–substrate interactions. At its core, EnzyPGM includes two main modules: a Residue-atom Bi-scale Attention (RBA) that jointly models intra-residue dependencies and fine-grained interactions between pocket residues and substrate atoms, and a Residue Function Fusion (RFF) that incorporates enzyme function priors into residue representations. Also, we curate EnzyPock, an enzyme–pocket dataset comprising 84,336 enzyme–substrate pairs across 1,036 four-level enzyme families. Extensive experiments demonstrate that EnzyPGM achieves state-of-the-art performance on EnzyPock. Notably, EnzyPGM reduces the average binding energy by 0.47 kcal/mol over EnzyGen, showing its superior performance on substrate-specific enzyme design. The code is available at https://github.com/John-Lin98/EnzyPGM.
Immune Checkpoint Inhibitors (ICIs) represent a cornerstone of modern cancer immunotherapy. However, their clinical application is frequently accompanied by immune-related Adverse Events (irAEs) of diverse severity. Predicting Gene-Disease Associations (GDAs) is crucial for identifying the related genes that cause irAEs but remains experimentally expensive in the context of cancer immunotherapy. While existing graph neural network-based methods provide solutions to this problem, they often overlook disease-disease and disease-gene associations that may exist but have not yet been identified, leading to contaminated representations. To address these limitations, we propose Gene-Disease Associations based on Optimal Transport (GDAs-OT), a novel framework for GDA prediction. GDAs-OT constructs gene-gene, disease-disease and gene-disease relationships as graphs. Optimal transport was utilized to identify potential disease-disease associations to expand the disease-disease graph structure, and select high-confidence negative pairs in the gene-disease graph. By mapping nodes into a refined embedding space, the processed gene-disease graph guides node representation learning, providing robust node representations. Comprehensive experiments demonstrate that GDAs-OT outperforms state-of-the-art methods across most evaluation metrics. In addition, GDAs-OT successfully identifies potential risk genes for irAEs, providing a computational foundation for understanding the mechanisms of immunotherapy toxicity. Code is available at https://github.com/RuhaoLiu/GDAs-OT.
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
Predicting responses to genetic perturbation is pivotal for elucidating gene regulatory machinery. However, existing methods often rely on statistical perspectives to model differential expression, overlooking the constraints of the underlying molecular interactome, which renders predictions susceptible to spurious correlations. Based on the fact that a genetic perturbation is a molecular stimulus acting through functional connectivity to reconfigure cellular expression profiles, we propose PertDCR, a framework for context-aware Perturbation response prediction via Distance-Constrained Refinement. Specifically, PertDCR addresses the heterogeneity of perturbation effects by contextualizing the perturbation source with relevant gene programs inferred from the protein-protein interaction network as well as cell representation. To activate biologically valid responses, PertDCR predicts the distance between the perturbation source and highly responsive genes within the PPI network, and dynamically modulates the response intensity based on distance, thereby facilitating accurate perturbation prediction. Extensive experiments demonstrate that PertDCR achieves state-of-the-art performance across diverse unseen genetic perturbations, and the predictions are consistent with underlying biological mechanisms.
Accurately predicting the popularity of information cascades facilitates the development of social media network applications. During the cascade propagation process, user-generated comments continually evolve, thereby substantially affecting overall information popularity. However, existing methods primarily focus on learning structural–temporal cascade dynamics while neglecting the modeling of user-generated comment evolution, leading to suboptimal predictions. In this paper, we propose a novel framework, CasUGC, that aligns Cascade dynamics with User-Generated Comment evolution for popularity prediction. Specifically, we develop a dual-granularity alignment strategy that bridges the representation gap between comment semantics and structural–temporal dynamics at both the user and cascade levels. Building on this alignment, we further design a dynamic cascade feature generation module to produce temporally enhanced cascade embeddings. To further address the inherent uncertainties in both alignment and prediction, we introduce two diffusion-based components: a cascade-level diffusion network that learns a latent distribution mapping between semantic and structural–temporal representations, and a second diffusion process that captures the stochasticity of propagation dynamics for robust prediction. Extensive experiments conducted on four real-world social media datasets demonstrate the superiority of CasUGC over state-of-the-art methods.
Large language models (LLMs) dominate both everyday and specialized applications, but their high computational demand, energy consumption, and privacy risks are increasingly critiqued. Small language models (SLMs) mitigate these drawbacks and are gaining momentum in scenarios where full LLM capabilities are not required, such as agents, industrial systems, or edge devices. Nevertheless, a systematic comparison of model capabilities, energy usage, and scaling behavior has not been conducted yet. We evaluate 70+ SLMs from 2023–2025 on five task-specific benchmarks and compare them with two popular LLMs, revealing key trade-offs between energy, performance, and model selection. Our findings challenge common assumptions: First, smaller models are not automatically more efficient, and energy increases do not guarantee performance gains. Second, newer SLMs show clear improvements in performance–energy trade-offs, though the progress begins to plateau. Last, the efficiency landscape forms a clear Pareto frontier: initial energy increases yield substantial gains, but the last percentage points of performance need orders of magnitude more energy. These results highlight diminishing returns of scaling and emphasize the need for informed, task-aware model selection rather than size-driven choices.
Predicting drug–target affinity (DTA) is central to drug discovery, yet most deep learning models rely on a single static protein structure, neglecting the conformational heterogeneity that underlies many binding mechanisms. We propose MultiGeo, a DTA prediction framework that explicitly leverages multiple protein conformations rather than a single snapshot. For each target, MultiGeo starts from an ensemble of structure predictions and uses confidence scores to adaptively select a small set of high-quality, diverse conformers. A hierarchical structural encoder then extracts multi-scale geometric features from these conformers, which are aggregated by a GRU to obtain an ensemble-level representation. To avoid indiscriminately mixing noisy or redundant views, we introduce a disagreement-aware gating mechanism that adaptively fuses this ensemble representation with the dominant structure only when the additional conformers provide complementary information. Finally, ligand–target interactions are modeled via a block-wise cross-attention module that captures multi-perspective dependencies between ligand and protein features. Extensive experiments on multiple DTA benchmarks demonstrate that MultiGeo consistently outperforms state-of-the-art baselines, showing that explicitly encoding conformational diversity yields more accurate and robust affinity prediction.
Creative story generation has achieved notable progress with large language models. Current methods construct narratives through hierarchical planning or incremental expansion. These approaches produce structurally complete stories but offer limited support for organic narrative development. Many fiction writers offer a complementary view of the creative process. They often describe their work as gradually uncovering a story embedded in the world they have built. This perspective motivates our approach. We propose that a world model can grow to contain latent narratives as it develops. When characters hold incomplete knowledge and situations remain unresolved, the world structure itself accumulates seeds for story development. Based on this insight we present FossilWriter, a framework that learns hypergraph world models for creative story generation. FossilWriter represents the story world as a shared hypergraph and introduces a narrative layer that marks elements with developmental potential. An excavation module detects and scores latent narratives on this structure. A scene controller selects locations and characters to develop promising narrative threads. The hypergraph grows during writing and serves as the single source of truth to ensure long-range consistency. Experiments on three benchmarks show that FossilWriter achieves an 81.4% win rate on plot coherence and 84.7% on world consistency. Human assessment shows a 32.5% reduction in long-range factual conflicts compared with strong baselines.
Reconstructing PDE-governed fields from sparse and irregular measurements is challenging due to their ill-posed nature. Deterministic surrogates are trained on dense fields that struggle with limited measurements and uncertainty quantification. Generative models, by learning distributions over spatiotemporal fields, can better handle sparsity and uncertainty. However, existing generative approaches enforce data consistency and PDE constraints simultaneously via sampling-time gradient guidance, resulting in slow and unstable inference. To this end, we propose PerFlow, a Physics-embedded rectified Flow for efficient sparse reconstruction and uncertainty quantification of spatiotemporal dynamics. PerFlow decouples observation conditioning from physics enforcement, performing guidance-free conditioning by feeding observations into rectified-flow dynamics while embedding hard physics via a constraint-preserving projection (e.g., incompressibility or conservation). Theoretically, we establish invariance guarantees to ensure that trajectories remain on the physics-consistent manifold throughout sampling. Experiments on various PDE systems demonstrate competitive reconstruction accuracy with sound physics consistency, while enabling efficient conditional sampling (e.g., 50 steps) and up to 320x faster inference than 2000-step guided diffusion baselines.