3797 papers
This paper proposes a trust-region interior-point stochastic sequential quadratic programming (TR-IP-SSQP) method that utilizes adaptive stochastic oracles to solve optimization problems with stochastic objectives and deterministic nonlinear constraints, proving its global almost-sure convergence to first-order stationary points and demonstrating practical performance on benchmark and logistic regression problems.
The paper proposes I2X, a framework that transforms unstructured interpretability into structured, prototype-based explanations to reveal model decision-making processes and actively improve classification accuracy through targeted sample perturbation.
This paper introduces One-A, a unified framework for step-imbalanced class-incremental learning that employs asymmetric subspace alignment and directional gating to merge task updates into a single adapter, thereby balancing stability and plasticity while maintaining constant inference costs.
This paper demonstrates that a natively spiking neuromorphic algorithm for solving partial differential equations possesses intrinsic fault tolerance, maintaining accuracy even when up to 32% of neurons and 90% of spikes are dropped, with this robustness being tunable via structural hyperparameters.
This paper introduces SiMPO, a unified framework for online diffusion reinforcement learning that generalizes policy reweighting through a two-stage measure matching approach, enabling the principled use of signed measures and negative reweighting to effectively repel policies from suboptimal actions and achieve superior performance.
This paper demonstrates that when the prior given hyperparameters in a Bayesian hierarchical model is a canonical maximum entropy distribution, the resulting dependent marginal prior also possesses a maximum entropy property, but with respect to a constraint on the marginal distribution of a function of the unknown parameters, thereby clarifying the implicit information assumptions of such models.
This paper addresses the limitation of TabPFN's autoregressive synthetic data generation, which produces spurious correlations when feature order conflicts with causal structure, by introducing DAG-aware and CPDAG-based conditioning strategies that significantly improve the fidelity, stability, and causal preservation of the generated synthetic tabular data.
This paper introduces a novel three-stage mechanistic interpretability method that extracts a compact, high-performing hematopoietic algorithm directly from the internal attention weights of the scGPT foundation model, achieving superior zero-shot classification and pseudotime ordering on independent datasets with significantly fewer parameters and training time than standard probing or retraining approaches.
The paper introduces DICE-RL, a sample-efficient reinforcement learning framework that refines pretrained generative robot policies into high-performing experts by using distribution contraction to amplify successful behaviors from online feedback, enabling mastery of complex long-horizon manipulation tasks from pixel inputs in both simulation and real-world settings.
This paper proposes a fast graph neural network-based method for estimating the condition numbers of sparse matrices with linear complexity relative to the number of non-zero elements, demonstrating significant speedups over traditional Hager-Higham and Lanczos methods.
This paper proposes and validates exponential reward-weighted SFT as a robust, fully offline post-training method for generative recommenders that eliminates reward hacking and propensity score requirements while offering theoretical guarantees and a controllable tradeoff between robustness and performance.
This paper introduces ADMM-PnP with a novel AC-DC denoiser that resolves manifold mismatch and establishes convergence guarantees for score-based generative models within the ADMM framework, thereby improving solution quality across various inverse problems.
This paper proposes a geometry-grounded framework for comparing datasets using the Generalized Singular Value Decomposition (GSVD) to derive an interpretable "angle score" that quantifies whether individual samples are better explained by one dataset, the other, or both.
The paper introduces Copula-ResLogit, a novel deep learning framework that combines ResNet architectures with copula models to detect and mitigate unobserved confounding effects in travel demand analysis, thereby revealing true causal relationships in case studies involving pedestrian stress and travel mode choices.
The paper introduces MultiwayPAM, a novel tensor clustering method designed to simultaneously estimate cluster memberships and medoids for questions, answerers, and evaluators in LLM-as-a-Judge score tensors, thereby addressing computational costs and revealing inherent evaluator biases.
This study demonstrates that quantum entanglement serves as a functional resource in competitive reinforcement learning, enabling hybrid quantum-classical agents trained on the game Pong to consistently outperform separable quantum circuits and match or exceed classical baselines by learning structurally distinct features that better model dynamic agent interactions.
This paper introduces HyMEM, a hybrid self-evolving structured memory system that combines discrete symbolic nodes with continuous embeddings in a graph format to significantly enhance the performance of open-source GUI agents, enabling them to match or surpass strong closed-source models on complex, long-horizon tasks.
GaLoRA is a parameter-efficient framework that integrates structural information into large language models for text-attributed graph node classification, achieving state-of-the-art performance with only 0.24% of the parameters required for full fine-tuning.
This paper introduces a regime-aware in-context learning framework that leverages pretrained large language models to forecast financial volatility by dynamically adapting to nonstationary market conditions through oracle-guided, regime-specific demonstrations without requiring parameter fine-tuning.
This paper introduces a search procedure to identify near-optimal learning rate schedule shapes across various workloads, revealing that while warmup and decay are robust features, commonly used schedules are suboptimal and the ideal shape is significantly influenced by hyperparameters like weight decay.