3797 papers
This paper introduces \texttt{InFusionLayer}, a novel, open-source Python ensemble tool inspired by Combinatorial Fusion Analysis (CFA) that integrates rank-score characteristic functions and cognitive diversity to enhance multiclassification performance across PyTorch, TensorFlow, and Scikit-learn workflows.
This paper addresses the failure of byte-sequence-based masked modeling in encrypted traffic classification by identifying a mismatch in inductive bias and proposing FlowSem-MAE, a protocol-native tabular masked autoencoder that leverages field-specific semantics and temporal patterns to significantly outperform existing methods with substantially less labeled data.
OmniGuide is a universal framework that enhances the performance of generalist Vision-Language-Action (VLA) policies on complex tasks by integrating diverse guidance sources—such as 3D foundation models and human pose estimators—into a unified differentiable energy field that guides action sampling through task-specific attractors and repellers.
This paper proposes CAADRL, a cluster-aware deep reinforcement learning framework that leverages hierarchical encoding and a dynamic dual-decoder to efficiently solve Pickup and Delivery Problems by explicitly modeling multi-scale cluster structures, achieving state-of-the-art performance with significantly lower inference latency than collaborative-search baselines.
This paper resolves a 20-year-old conjecture by proving that the volume-averaged Ricci scalar of binary Bayesian networks is universally quantized to positive half-integers for tree and complete-graph structures via a Beta function cancellation mechanism, while demonstrating that this quantization fails in general due to loop counterexamples and contrasting the positive curvature of discrete networks with the negative curvature of Gaussian DAGs.
This paper proposes using Neural Cellular Automata to generate controllable, synthetic non-linguistic data for pre-pre-training large language models, demonstrating that this approach significantly improves downstream performance and convergence speed while outperforming training on much larger natural language datasets.
This paper introduces HTMuon, a heavy-tailed spectral correction method that improves upon the Muon optimizer by preserving parameter interdependencies while inducing heavier-tailed weight spectra, resulting in consistent performance gains in LLM pretraining and image classification alongside theoretical convergence guarantees.
This paper introduces Search Agent Policy Optimization (SAPO), a method that resolves catastrophic training instability in Tool-based Agentic Reinforcement Learning by applying a conditional token-level KL constraint to prevent Importance Sampling Distribution Drift, achieving significant performance gains with only a single line of code modification to standard GRPO.
This paper pioneers the application of sparse autoencoders to the Chronos-T5 time series foundation model, revealing a depth-dependent causal hierarchy where mid-encoder features responsible for change detection are more critical to forecasting accuracy than the semantically rich but less causally influential features in the final encoder layer.
This paper demonstrates that neural networks learning a conditional task with K-fold ambiguity first converge to a marginal solution characterized by a log K loss plateau, which persists until an internally assembled selector-routing head triggers a sharp, collective transition to the full conditional solution, a process governed by dataset size and stabilized by gradient noise.
This paper introduces Stochastic Port-Hamiltonian Neural Networks (SPH-NNs), a framework that parameterizes Hamiltonian systems with neural networks to enforce physical passivity and skew-symmetry constraints, thereby achieving universal approximation of stochastic dynamics with guaranteed energy stability and superior long-term performance compared to standard baselines.
This paper provides a quantitative large-deviations theory for the "catapult phase" in stochastic gradient descent training of shallow networks under NTK scaling, establishing an explicit criterion based on a function that determines whether large NTK-flattening spikes occur with high probability or decay rapidly depending on the learning rate, data, and kernel.
The paper introduces "Amnesia," a lightweight adversarial attack that manipulates the internal activation states of open-weight Large Language Models to bypass existing safety mechanisms and induce harmful or antisocial behaviors without requiring any fine-tuning.
This paper proposes a multi-stage residual learning framework for quantum machine learning models to mitigate the inherent bias against learning high-frequency or non-dominant frequency components, demonstrating significant improvements in spectral expressivity and test performance across diverse synthetic benchmarks.
This paper introduces Multi-Level Concept Splitting (MLCS) and Deep-HiCEMs to overcome the limitations of shallow hierarchies in concept-based models by automatically discovering multi-level concept structures from coarse annotations and enabling effective interventions at various levels of abstraction.
KernelSkill is a multi-agent framework that enhances GPU kernel optimization by replacing opaque LLM heuristics with a knowledge-driven, dual-level memory architecture of expert skills, achieving state-of-the-art speedups and a 100% success rate on KernelBench.
The paper introduces ES-dLLM, a training-free inference acceleration framework for Diffusion Large Language Models that significantly boosts throughput by dynamically skipping tokens in early layers based on intermediate representation variations and confidence scores, achieving up to a 16.8 speedup while maintaining generation quality.
This survey introduces "Weight Space Learning" as a unified framework that treats neural network weights as a structured, learnable domain, categorizing existing research into understanding, representation, and generation to enable advanced applications like model retrieval, continual learning, and data-free reconstruction.
This paper introduces Equivariant Asynchronous Diffusion (EAD), a novel model that combines the strengths of auto-regressive and synchronous approaches through an adaptive denoising schedule to effectively capture molecular hierarchy and achieve state-of-the-art 3D molecular conformation generation.
This paper introduces TS_Adam, a lightweight variant of the Adam optimizer that removes second-order bias correction to enhance responsiveness to distributional drift in non-stationary time series forecasting, achieving significant performance improvements across various tasks without requiring additional hyperparameters.