4642 papers
The paper introduces GNN, a plug-and-play technique that leverages two sets of prototypes to enrich global context and denoise local neighborhoods, thereby significantly boosting the performance of Message Passing Graph Neural Networks across diverse node recommendation and classification tasks.
This paper argues that advancements in logical reasoning for large language models inadvertently create a mechanistic pathway to dangerous situational awareness and strategic deception, necessitating new safety frameworks like the RAISE model to mitigate these emergent risks.
This paper presents a fully data-driven signal separator using a modified SoundStream tokenizer and a transformer trained with cross-entropy loss, which achieves significant improvements in separating radio-frequency signals from non-Gaussian interference compared to conventional methods.
This paper investigates emotion as a latent factor influencing LLM attention and reasoning, introducing the AURA-QA dataset and an emotional regularization framework that demonstrably improves reading comprehension performance across both emotionally varying and standard benchmarks.
MM-Zero is the first RL-based framework to enable Vision Language Models to self-evolve from zero data by employing a multi-role system (Proposer, Coder, and Solver) trained with Group Relative Policy Optimization to generate visual concepts, render them via code, and solve multimodal reasoning tasks without any seed images.
This paper proposes \texttt{RQRE-OVI}, an optimistic value iteration algorithm that computes the unique and smooth Risk-Sensitive Quantal Response Equilibrium (RQRE) in general-sum Markov games with linear function approximation, offering a principled trade-off between performance and robustness that outperforms traditional Nash equilibrium approaches in both theoretical guarantees and empirical stability.
This paper introduces Test-Time Control (TTC), a hardware-efficient neural layer that embeds finite-horizon optimal control planning directly into pretrained LLMs via a symplectic LQR solver, significantly boosting mathematical reasoning performance without requiring test-time training.
This paper proposes a unified, target-gradient-free generative sampling framework that enforces time-reversibility constraints via Maximum Mean Discrepancy minimization between forward and backward Markov trajectories, enabling efficient sampling from complex continuous, discrete, and hybrid distributions using only energy evaluations.
This paper proposes a training-only framework combining a length-aware attention prior (RPA) and a gain-aware controller (Guardian) to enhance reasoning efficiency and reduce validation loss in Transformers without increasing test-time computational costs or latency.
This paper introduces efficient, representation-based transductive generalization bounds for graph node classification using optimal transport and Wasserstein distances, which not only correlate strongly with empirical performance but also explain the non-monotonic relationship between GNN depth and generalization error through the analysis of distributional transformations.
This paper introduces DendroNN, a novel dendrocentric neural network that leverages non-differentiable sequence detection and a rewiring phase to efficiently classify event-based spatiotemporal data, achieving competitive accuracy with up to 4x higher energy efficiency than state-of-the-art neuromorphic hardware through a dedicated asynchronous digital architecture.
This paper advances the theoretical understanding of Gaussian process Thompson sampling (GP-TS) in Bayesian optimization by establishing a regret lower bound, deriving improved upper bounds for cumulative regret and the second moment of regret, and providing expected lenient regret bounds that address gaps in existing analyses compared to GP-UCB.
This paper proposes a proxy-guided framework using variational autoencoders and causal modeling to identify and correct systematic measurement errors in aggregate outcome variables by leveraging proxy variables that depend on true outcomes but are independent of bias mechanisms.
This paper establishes a non-asymptotic Gaussian comparison theorem based on Gordon's theorem to rigorously validate dynamic mean-field expressions and derive refined iterative approximations for the training dynamics of machine learning models, such as perceptrons, under Gaussian mixture data.
The paper proposes CLoE, a consistency-driven framework that enhances missing-modality medical image segmentation by enforcing decision-level agreement among modality experts on both global and clinically critical foreground regions, thereby improving robustness and generalization compared to state-of-the-art methods.
The paper introduces Reward-Zero, a general-purpose implicit reward mechanism that leverages language embeddings to transform natural-language task descriptions into dense, semantically grounded progress signals, thereby accelerating training, stabilizing learning, and improving generalization for reinforcement learning agents without requiring task-specific reward engineering.
This paper introduces TA-GGAD, a testing-time adaptive graph foundation model that addresses the cross-domain generalization challenge in anomaly detection by identifying and modeling the "Anomaly Disassortativity" issue, thereby achieving state-of-the-art performance across diverse real-world graphs with a single training phase.
This paper presents a data-driven framework that combines a multilayer perceptron trained on experimental data augmented by a conditional generative adversarial network with an interactive 3D web interface to predict and visualize surface roughness in material extrusion additive manufacturing, enabling optimized process planning and part orientation.
This paper introduces a differentially private, zero-order optimization framework that extends dataset condensation to non-differentiable clinical models, enabling the creation of compact, privacy-preserving synthetic datasets that facilitate the democratization of clinical data sharing without compromising model utility.
The paper proposes CAHC, an end-to-end contrastive learning framework for attributed hypergraph clustering that integrates node-level and hyperedge-level objectives with joint embedding and cluster assignment optimization to outperform existing two-stage methods.