10184 papers
The paper proposes Stratum, a unified system infrastructure that decouples pipeline execution from agent reasoning to efficiently scale agentic ML pipeline search by integrating with existing Python libraries and utilizing an optimized Rust-based runtime, achieving up to 16.6x speedup.
This paper establishes a theoretical foundation for the superior parallelizability of linear RNNs by demonstrating that they correspond to log-depth arithmetic circuits (-complete), whereas nonlinear RNNs are fundamentally limited by their ability to solve - and -complete problems, thereby explaining why linear variants can be efficiently parallelized like transformers while traditional nonlinear RNNs cannot.
This paper proposes a DMD-augmented Unpaired Neural Schrödinger Bridge framework that enhances Ultra-Low Field (64 mT) MRI image quality by leveraging diffusion-guided distribution matching and anatomical structure preservation to achieve superior realism and structural fidelity in translating unpaired 64 mT scans to 3 T quality.
LoRA-MME is a parameter-efficient multi-model ensemble that combines LoRA-tuned UniXcoder, CodeBERT, GraphCodeBERT, and CodeBERTa encoders to achieve strong code comment classification performance, though its high computational cost ultimately limited its final competition score.
This study demonstrates that introducing "Semantic Anchoring," a text-alignment mechanism, effectively resolves intrinsic embedding collapse and domain-locking in cross-species pathology models by using language as a stable coordinate system to re-align visual features, thereby significantly improving cancer detection performance across same-cancer, cross-cancer, and cross-species scenarios.
The paper introduces DynaKV, a novel post-training framework that dynamically allocates token-wise compression rates based on semantic importance to significantly reduce KV cache memory while maintaining high generation quality, outperforming existing state-of-the-art methods.
This paper proposes FreST Loss, a model-agnostic training objective that leverages the Joint Fourier Transform to align predictions with ground truth in the joint spatio-temporal frequency domain, thereby effectively decorrelating complex dependencies and outperforming state-of-the-art baselines on real-world datasets.
Through a large-scale study of Qwen-VL and LLaVA-1.5, this paper demonstrates that vision-language models exhibit significant context-dependent affordance drift, where both lexical and semantic outputs vary substantially based on agentic personas, suggesting a need for dynamic, query-dependent ontological projection in robotics rather than static world modeling.
This study introduces Equilibrium-Informed Neural Networks (EINNs), a novel deep learning approach that reverses the traditional parameter-search process by inferring system parameters from candidate equilibrium states to efficiently detect critical bifurcation thresholds and tipping points in complex nonlinear dynamical systems.
FedEMA-Distill is a robust and communication-efficient federated learning framework that leverages server-side exponential moving average smoothing and ensemble knowledge distillation from compressed client logits to achieve superior accuracy, faster convergence, and Byzantine resilience under non-IID data conditions without requiring client-side software modifications.
This paper presents an empirical study demonstrating that network topology, congestion dynamics, and GPU locality often cause unpredictable scaling failures in distributed GPU training, urging system builders to adopt specific diagnostic principles to address these overlooked fabric-level bottlenecks.
This paper leverages a multi-generational cellular network dataset from OpenCelliD to analyze deployment patterns and utilization metrics, offering a strategic framework for Mobile Network Operators to optimize infrastructure, identify cost-saving opportunities, and guide targeted LTE upgrades in underserved regions.
The paper introduces Delta-Crosscoder, a robust method that combines BatchTopK sparsity with a delta-based loss to effectively identify and mitigate localized behavioral changes in narrowly fine-tuned models, outperforming existing SAE-based baselines across diverse model architectures and tasks.
This paper proposes reducing KV cache memory usage in transformers by employing low-dimensional keys for attention selection while maintaining full-dimensional values for semantic transfer, a strategy validated across multiple models and datasets to achieve up to 75% cache savings with minimal performance degradation.
This paper introduces a system for multi-agent LLM inference on edge devices that persists 4-bit quantized KV caches to disk, enabling direct cache restoration to eliminate redundant prefill computations and achieve up to 136x faster time-to-first-token while fitting four times more agent contexts into limited RAM.
The paper introduces Flowers, a novel neural architecture for solving partial differential equations that replaces traditional attention, convolution, and Fourier mechanisms with multihead warps to achieve adaptive global interactions at linear computational cost, demonstrating superior performance on 2D and 3D flow and wave benchmarks compared to existing foundation models.
The paper introduces SOLID, a mask-conditioned diffusion framework that learns spatiotemporal dynamics directly from sparse observations without requiring dense ground truth, achieving superior probabilistic forecasting and calibrated uncertainty through a novel dual-masking objective.
This paper proposes an auction-based framework for allocating shared reconfigurable intelligent surfaces (RISs) in multi-cell networks, where deep reinforcement learning agents optimize bidding strategies to dynamically balance spectral efficiency and cost constraints.
This paper proposes ZorBA, a zeroth-order federated fine-tuning framework for large language models that reduces VRAM usage and communication overhead through heterogeneous block activation and shared random seeds, while optimizing convergence via a novel lexicographic algorithm.
This paper proposes ASFL, an adaptive split federated learning framework that jointly optimizes model splitting and resource allocation via an online block coordinate descent algorithm to significantly reduce training delay and energy consumption while accelerating convergence in wireless networks.