Deep hypergraph clustering has shown strong potential in learning node representations by modeling high-order relationships. However, most existing methods rely on fixed propagation mechanisms that implicitly assume homophily, where connected nodes tend to be similar. This assumption often fails in real-world scenarios, especially in heterophilic settings, leading to degraded clustering performance. To bridge this gap, we propose a \textbf{Uni}fied Framework for \textbf{D}eep \textbf{H}ypergraph \textbf{C}lustering (Uni-DHC). Specifically, we introduce a learnable high-order hypergraph propagation scheme that aggregates information from multiple propagation orders and adaptively learns their importance from data. To stabilize unsupervised training and prevent structural redundancy introduced by high-order aggregation, we further impose consistency at the node level and decorrelation at the hyperedge level. From a spectral perspective, we show that conventional HGNN-style propagation corresponds to a fixed low-pass filter, while the proposed approach induces a learnable polynomial spectral filter. Extensive experiments on homophilic and heterophilic benchmarks demonstrate that Uni-DHC consistently outperforms state-of-the-art methods, with particularly strong gains in heterophilic settings.
论文检索
输入标题、作者或关键词，从 100,903 篇学术成果中精准定位
Theory · Learning Theory
This work investigates theoretically the interplay between interpolation and aggregation in regression. We establish that the $\gamma$-graph dimension characterizes learnability for a broad class of natural aggregation procedures. Furthermore, we prove that an extremely simple aggregation procedure, combining three interpolating hypotheses via the median, is optimal among all these aggregation procedures, and is strictly more powerful than proper learning. Finally, we show that some hypothesis classes are learnable only by aggregating infinitely many hypotheses or by using non-interpolating aggregation rules (which may predict outside the range of their inputs), and any finite interpolating aggregation fails to achieve even trivial performance.
Theory · Game Theory
In this paper, we settle the problem of learning optimal linear contracts from data in the offline setting, where agent types are drawn from an unknown distribution and the principal's goal is to design a contract that maximizes her expected utility. Specifically, our analysis shows that the simple Empirical Utility Maximization (EUM) algorithm yields an $\varepsilon$-approximation of the optimal linear contract with probability at least $1-\delta$, using just $O(\ln(1/\delta) / \varepsilon^2)$ samples. This result improves upon previously known bounds and matches a lower bound from (Dütting et al., 2025) up to constant factors, thereby proving its optimality. Furthermore, our result establishes the stronger guarantee of uniform convergence: the empirical utility of every linear contract is a $\varepsilon$-approximation of its true expectation with probability at least $1-\delta$, using the same optimal $O(\ln(1/\delta) / \varepsilon^2)$ sample complexity.
Multilingual safety remains significantly imbalanced, leaving non-high-resource (NHR) languages vulnerable compared to robust high-resource (HR) ones. Moreover, the neural mechanisms driving safety alignment remain unclear despite observed cross-lingual representation transfer.In this paper, we find that LLMs contain a set of cross-lingual shared safety neurons (SS-Neurons), a remarkably small yet critical neuronal subset that jointly regulates safety behavior across languages. We first identify monolingual safety neurons (MS-Neurons) and validate their causal role in safety refusal behavior through targeted activation and suppression. Our cross-lingual analyses then identify SS-Neurons as the subset of MS-Neurons shared between HR and NHR languages, serving as a bridge to transfer safety capabilities from HR to NHR domains. We observe that suppressing these neurons causes concurrent safety drops across NHR languages, whereas reinforcing them improves cross-lingual defensive consistency. Building on these insights, we propose a simple neuron-oriented training strategy that targets SS-Neurons based on language resource distribution and model architecture. Experiments demonstrate that fine-tuning this tiny neuronal subset outperforms state-of-the-art methods, significantly enhancing NHR safety while maintaining the model's general capabilities.
Theory · Deep Learning
We study the fundamental expressivity limits of transformer models by formalizing the notion of accessible sequences---those that a transformer can produce for some prompt---and characterizing how accessibility depends on prompt length and model parameters. Our analysis provides a theoretical explanation for previously observed empirical failures of transformers on simple sequence tasks---such as copying and cramming---and yields both qualitative and quantitative predictions that hold across a wide range of architectures and model sizes. We prove that (i) the maximal length of accessible sequences grows linearly with the prompt length, (ii) beyond a critical threshold the proportion of accessible sequences decays exponentially with sequence length, and (iii) the linear coefficient relating prompt length to accessible sequence length admits a theoretical upper bound. Notably, these results hold even with unbounded context and computation time. Experiments using a “cramming” procedure confirm the linear scaling, the post-threshold exponential decay, and the tightness of the theoretical upper bound on different sizes of Pythia, Llamma, and Qwen architectures.
Generative AI disrupts the practice of giving credit to work that came before. Ideally, a generative model would give credit to any work on which its output depends in a significant way. *Counterfactual credit attribution (CCA)* is a technical condition formalizing this goal---a relaxation of differential privacy---recently introduced by Livni, Moran, Nissim, and Pabbaraju (2024) who studied it in the PAC learning setting. We initiate the study of CCA generative models. Specifically, we consider autoregressive models giving credit to a deployment-time dataset (e.g., a RAG database). We uncover barriers to two natural approaches to CCA autoregressive models. First, we show that imposing CCA on the underlying next-token predictor does not guarantee that the model is CCA: CCA does not compose autoregressively (unlike DP). Second, we consider a different approach to building CCA models which we call *retrofitting*. Retrofitting takes a model that does not attribute credit, and adds credit onto it. Given black-box access to the starting model, retrofitting requires query complexity exponential in the length of the model's outputs.
General Machine Learning · Scalable Algorithms
Modern language models typically rely on two design choices: subword tokenization and autoregressive (AR) ordering. To achieve more universal modeling, the field is advancing toward byte-level modeling to bypass domain-specific vocabularies and masked diffusion models (MDM) to enable parallel non-sequential generation. Intuitively, the intersection of these paradigms represents a generative ideal: a modality-agnostic system capable of fine-grained any-order generation. However, the computational interaction between these granular representations and non-sequential objectives remains under-explored. In this work, we investigate the viability of this combination through a compute-matched scaling study. We observe a structural dichotomy: AR models on bytes effectively amortize the cost of tokenization, naturally rediscovering sub-word segmentation at scale. In contrast, byte-level MDMs suffer a non-convergent efficiency collapse. We attribute this disparity to the masking objective, which shatters the local contiguity required to resolve sub-word semantics from bytes, whereas AR's stable causal history preserves these essential local dependencies. Our findings inform the community of a critical efficiency tradeoff, suggesting that future modality-agnostic designs should address this context fragility to maintain efficient scaling.
We introduce TANGO -- a dynamical systems inspired framework for graph representation learning that governs node feature evolution through a learned energy landscape and its associated descent dynamics. At the core of our approach is a learnable Lyapunov function over node embeddings, whose gradient defines an energy non-increasing direction that guarantees stability. To enhance flexibility while preserving the benefits of energy-based dynamics, we incorporate a novel tangential component, learned via message passing, that evolves features while maintaining the energy value. This decomposition into orthogonal flows of energy gradient descent and tangential evolution yields a flexible form of graph dynamics, and enables effective signal propagation even in flat or ill-conditioned energy regions, that often appear in graph learning. Our method is designed to help alleviate oversquashing, and is compatible with different graph neural network backbones. Empirically, TANGO achieves strong performance across a diverse set of node and graph classification and regression benchmarks, demonstrating the effectiveness of jointly learned energy functions and tangential flows for graph neural networks.
Analyzing attention weights has become a standard approach for interpreting the information flow of Large Language Models (LLMs). However, this approach has significant limitations as it neglects the geometric properties of the value vectors being aggregated. To address this gap, we introduce \emph{Contribution Weights}, a projection-based metric that quantifies a token's influence by accounting for it's attention weight, value magnitude, and directional alignment with the layer output. We demonstrate that contribution weights provide a more faithful measure of token importance, consistently outperforming attention-based metrics in identifying semantically critical tokens across different models, tasks, and datasets. Further, our metric enables novel mechanistic analysis of \emph{attention sinks}. While previous work has characterized sinks as passive repositories for excess attention, we reveal they serve an active functional role, suppressing information through a convex relationship between sink rate and output norm, stabilizing representations by opposing the semantic drift of low-confidence tokens.
Hyperbolic geometry has recently emerged as a powerful representation space for multimodal learning, as it naturally captures hierarchical semantic structure across modalities. Despite this progress, how such representations behave under continual learning poses fundamentally different challenges that remain underexplored. This work provides a geometric perspective on this problem and establishes a theoretical foundation for representation preservation in hyperbolic space, showing that preventing forgetting requires cross-modal invariance under a shared hyperbolic isometry. Guided by these insights, a principled continual learning framework is derived that preserves essential geometric structure while allowing effective adaptation to new tasks. Experiments on continual multimodal benchmarks corroborate the effectiveness of the proposed approach.
Deep Learning · Algorithms
Quantization has significantly improved the compute and memory efficiency of Large Language Model (LLM) training. However, existing approaches still rely on accumulating their updates in high-precision: concretely, gradient updates must be applied to a high-precision weight buffer, known as $\textit{master weights}$. This buffer introduces substantial memory overhead, particularly for Sparse Mixture of Experts (SMoE) models, where model parameters and optimizer states dominate memory usage. To address this, we introduce the Error-Compensating Optimizer (ECO), which eliminates master weights by applying updates directly to quantized parameters. ECO quantizes weights after each step and carefully injects the resulting quantization error into the optimizer momentum, forming an error-feedback loop with no additional memory. We prove that, under standard assumptions and a decaying learning rate, ECO converges to a constant-radius neighborhood of the optimum, while naive master-weight removal can incur an error that is inversely proportional to the learning rate. We show empirical results for pretraining small Transformers (30--800M), a Gemma-3 1B model, and a 2.1B parameter Sparse MoE model with FP8 quantization, and fine-tuning DeepSeek-MoE-16B in INT4 precision. Throughout, ECO matches baselines with master weights up to near-lossless accuracy, significantly shifting the static memory vs validation loss Pareto frontier.
Mixture-of-Experts (MoE) effectively scales model capacity while preserving computational efficiency through sparse expert activation. However, training high-quality MoEs from scratch is prohibitively expensive. A promising alternative is to convert pretrained dense models into sparse MoEs. Existing dense-to-MoE methods fall into two categories: \textbf{dynamic structural pruning} that converts dense models into MoE architectures with moderate sparsity to balance performance and inference efficiency, and \textbf{downcycling} approaches that use pretrained dense models to initialize highly sparse MoE architectures. However, existing methods break the intrinsic activation patterns within dense models, leading to suboptimal expert construction. In this work, we argue that the Gated Linear Unit (GLU) mechanism provides a natural blueprint for dense-to-MoE conversion. We show that the fine-grained neural-wise activation patterns of GLU reveal a coarse-grained structure, uncovering an inherent MoE architecture composed of consistently activated universal neurons and dynamically activated specialized neurons. Leveraging this discovery, we introduce ExpertWeaver, a training-free framework that partitions neurons according to their activation patterns and constructs shared experts and specialized routed experts with layer-adaptive configurations. Our experiments demonstrate that ExpertWeaver significantly outperforms existing methods, both as a training-free dynamic structural pruning technique and as a downcycling strategy for superior MoE initialization.
Deep Learning · Large Language Models
Language Models (LMs) have shown remarkable potential as role-playing chatbots, delivering consistent, stylized interactions when given a specification of a character or user persona. However, applying these capabilities to real-world applications (*e.g*., ecosystems with numerous NPCs interacting simultaneously) exposes a critical inefficiency due to the excessive computational cost. In this paper, we question the necessity of dedicating a full, generalist model to a single persona, hypothesizing that a specific character identity relies on only a fraction of the model’s total capacity. We observe that naïvely pruning LMs often severely degrades the role-playing performance for a specific persona; it does not distinguish between redundant knowledge and essential character traits. We propose **Persona-Pruner**, a framework that sculpts a lightweight role-playing model by isolating persona-specific sub-networks from a single description. Our experiments consistently show that Persona-Pruner preserves role-playing performance substantially more effectively than existing state-of-the-art LLM pruning techniques, reducing the performance drop from the dense model by up to 93.8% over the strongest baseline on RoleBench in LLM-as-a-judge score, while still maintaining general LLM capabilities.
Test-time reinforcement learning generates multiple candidate answers via repeated rollouts and performs online updates using pseudo-labels constructed by majority voting. To reduce overhead and improve exploration, prior work introduces tree-structured rollouts, which share reasoning prefixes and branch at key nodes to improve sampling efficiency. However, this paradigm still faces two challenges: (1) high-entropy branching can trigger rollout collapse, where the branching budget concentrates on a few trajectories with consecutive high-entropy segments, rapidly reducing the number of effective branches; (2) early pseudo-labels are noisy and biased, which can induce self-reinforcing overfitting, causing the policy to sharpen prematurely and suppress exploration. To address these issues, we propose Entropy–Confidence Hybrid Group Relative Policy Optimization (ECHO). During rollout, ECHO jointly leverages local entropy and group-level confidence to adaptively control branch width, and further introduces online confidence-based pruning to terminate persistently low-confidence branches, avoiding high-entropy traps and mitigating collapse. During policy updates, ECHO employs confidence-adaptive clipping and an entropy–confidence hybrid advantage shaping approach to enhance training robustness and mitigate early-stage bias. Experiments demonstrate that ECHO achieves consistent gains on multiple mathematical and visual reasoning benchmarks, and generalizes more effectively under a limited rollout budget.
Spiking Neural Networks (SNNs) offer low-power, brain-inspired computation, but Transformer-based SNNs face deployment challenges on neuromorphic hardware due to complex operations and high communication overhead. We propose hardware-efficient attention mechanisms, \textbf{Simplified Spiking Attention (SSA)} and \textbf{Ultra-Simplified Spiking Attention (USSA)}, which replace matrix multiplications with Hadamard products and remove multi-head attention, scaling, and patching. We theoretically show that double masking is redundant and early-spiking gating preserves richer temporal information than late-spiking. On the CIFAR‑10, CIFAR‑100, and DVS‑Gesture datasets, SSA achieves accuracies of 96.38\%, 79.45\%, and 97.56\%, respectively, outperforming baseline Transformer‑SNNs by up to +1.73\%, while reducing computational complexity from $\mathcal{O}(N^2D)$ to $\mathcal{O}(ND)$ and communication complexity from $\mathcal{O}(N^2)$ to $\mathcal{O}(ND)$. USSA further compresses communication complexity to $\mathcal{O}(N)$ with only marginal accuracy loss.
Applications · Time Series
Context-aided forecasting (CAF) holds promise for integrating domain knowledge and forward-looking information, enabling AI systems to surpass traditional statistical methods. However, recent empirical studies reveal a puzzling gap: multimodal models often fail to outperform their unimodal counterparts. We hypothesize that this underperformance stems from poor context quality in existing datasets, as verification is challenging. To address these limitations, we introduce a semi-synthetic data augmentation method that generates contexts both descriptive of temporal dynamics and verifiably complementary to numerical histories. This approach enables massive-scale dataset creation, resulting in CAF-7M, a corpus of 7 million context-augmented time series windows, including a rigorously verified test set. We demonstrate that semi-synthetic pre-training transfers effectively to real-world evaluation, and show clear evidence of context utilization. Our results suggest that dataset quality, rather than architectural limitations, has been the primary bottleneck in context-aided forecasting.
Deep Learning · Large Language Models
Reasoning-capable large language models (LLMs) have recently been adopted as automated judges, but their benefits and costs in LLM-as-a-Judge settings remain unclear. Through controlled comparisons between reasoning and non-reasoning judges, we show that explicit reasoning substantially improves judgment accuracy on tasks requiring structured verification (e.g., math and coding), while offering limited or even negative gains on simpler evaluations and incurring significantly higher computational cost. These findings motivate that reasoning should be used selectively rather than universally, with awareness of possible distribution shift. We propose a Robust Adaptive Cost-Efficient Router (RACER), which dynamically selects between reasoning and non-reasoning judges under a fixed budget by formulating routing as a constrained distributionally robust optimization problem. RACER explicitly accounts for distribution shift via a KL-divergence uncertainty set, admits an efficient primal–dual algorithm, and enjoys theoretical guarantees including uniqueness of the optimal policy and linear convergence. Extensive experiments show that RACER achieves superior accuracy–cost trade-offs under distribution shift.
Deep Learning · Generative Models and Autoencoders
Controllable generation with discrete diffusion models is often hindered by high computational overhead or the need for retraining. In this paper, we present Gradient-Informed Logit Correction (GILC), a plug-and-play framework that efficiently estimates guidance signals by repurposing the pretrained denoising network as a variational proxy. To circumvent the gradient instability inherent in high-dimensional discrete spaces, we introduce a Jacobian-free mechanism that directly corrects the clean prediction logits, facilitating stable and effective guidance. Our method accommodates both differentiable and non-differentiable reward functions. Extensive experiments across DNA, protein sequence, and molecular generation tasks demonstrate that GILC achieves state-of-the-art performance without additional training, frequently outperforming fine-tuning approaches.
Three-dimensional (3D) shape classification plays a central role in computer vision and computer-aided design (CAD), underpinning applications in intelligent manufacturing, automated inspection, and digital engineering. Despite recent progress with 3D CNNs and graph-based approaches, existing methods often overlook the geometric-topological regularities and symmetry principles intrinsic to CAD boundary representations (B-reps). To address this challenge, we introduce EquiCAD, a symmetry-aware learning framework that integrates equivariant representations with graph-based reasoning. By leveraging group-theoretic decomposition of curve and surface descriptors, EquiCAD enforces consistent $SO(3)/O(3)$-equivariance while preserving rich geometric details. The model further exploits hierarchical message passing to capture interactions between local features and global structure. Experimental results across multiple datasets, including SolidLetters, Parts, the Machining Feature benchmark, and our newly constructed Features dataset, demonstrate substantial improvements over prior state-of-the-art approaches, particularly on industrially relevant shapes with fine-grained attributes. These findings highlight the value of symmetry-aware modeling for robust and generalizable 3D shape analysis.
Applications · Chemistry, Physics, and Earth Sciences
Retrosynthesis prediction aims to infer the reactant molecule based on a given product molecule, which is a fundamental task in chemical synthesis. However, existing models rely on static pattern-matching paradigm, which limits their ability to perform effective logic decision-making, leading to a black-box process. Building on this, we propose Retro-Expert, an interpretable retrosynthesis framework that performs collaborative reasoning by combining the complementary reasoning strengths of Large Language Models and specialized models via reinforcement learning. It outputs natural language explanations grounded in chemical logic through three components: (1) specialized models analyze the product to construct high-quality chemical decision space, (2) LLM-driven critical reasoning to generate predictions and corresponding interpretable reasoning path, and (3) reinforcement learning optimizing interpretable decision policy. Experiments show that Retro-Expert not only surpasses both LLM-based and specialized models across different metrics but also provides expert-aligned explanations that bridge the gap between AI predictions and actionable chemical insights.