6803 papers
This paper introduces an analysis-driven framework that generates a publicly available, 19-hour procedural engine sound dataset with sample-accurate RPM and torque annotations by extracting harmonic structures from real recordings to drive a parametric synthesizer, thereby addressing the scarcity of clean, standardized audio data for automotive sound design and machine learning applications.
This paper introduces StructAttack, a black-box jailbreak framework that exploits the semantic slot-filling vulnerability of Large Vision-Language Models by embedding benign-looking visual structures to covertly assemble and generate harmful content.
The paper proposes Difficulty-Scaled Segment-Wise GRPO (DSS-GRPO), a reinforcement learning method that decomposes training signals into separate "think" and "answer" segments with difficulty-aware scaling to compress reasoning traces without compromising answer quality.
MetaSort is a novel algorithm that integrates an adaptive level crossing compression technique with meta-transfer learning-based feature representation to simultaneously achieve high-fidelity neural spike compression and robust few-shot classification, demonstrating strong potential for ultra-low-power on-chip implementation.
The paper introduces TT-Sparse, a differentiable neural framework utilizing truth tables and a novel soft TopK operator to learn sparse, high-performance rule-based models that enable exact extraction of globally interpretable Boolean formulas while outperforming existing state-of-the-art methods in both accuracy and complexity.
This paper introduces MAS-H2, a hierarchical multi-agent system for Kubernetes that bridges the gap between business policies and resource provisioning through strategic, planning, and execution agents, demonstrating significant reductions in CPU stress and peak load while enabling zero-downtime infrastructure migrations compared to native autoscalers.
This paper proposes a novel visual representation framework that encodes signals as functions parametrized by low-rank adaptations on frozen diffusion models, enabling compact storage via single-vector hashing and bridging visual compression with generation through inference-time scaling and control.
The paper proposes Staged Multi-Agent Training (SMAT), a four-stage curriculum that progressively trains a human-exoskeleton system to achieve stable co-adaptation, resulting in a control policy that significantly reduces hip muscle activation and delivers consistent, positive mechanical power across diverse users without requiring subject-specific retraining.
This paper introduces a novel silicon photonics-based accelerator that significantly enhances the energy efficiency and throughput of diffusion models, addressing the high computational costs and energy consumption associated with their iterative denoising processes on conventional electronic platforms.
This paper presents a reinforcement learning framework for training exoskeleton controllers to reduce biological joint moments and establishes a quantitative validation pipeline that demonstrates strong simulation-to-data consistency in torque predictions, particularly at the hip, while identifying specific challenges in timing and power injection for sim-to-real transfer.
The paper introduces HELIX, a Hierarchical Evolutionary Reinforcement Learning framework that combines in-context learning with iterative policy refinement to achieve state-of-the-art results in open-ended scientific problem solving, outperforming existing methods and GPT-4o on tasks like circle packing and machine learning benchmarks.
This paper proposes a high-fidelity synthetic data generation pipeline using NVIDIA Omniverse to address data scarcity and privacy constraints in airport logistics, demonstrating that mixed training with synthetic data and only 40% of real annotations achieves performance comparable to full real-data baselines while reducing annotation effort by 25–35%.
This paper proposes FedCEF, a novel federated learning algorithm that combines a decoupled proximal update scheme with error feedback and control variates to achieve communication-efficient, sublinear convergence for non-convex composite optimization on heterogeneous data under extreme compression.
This critical review synthesizes classical and machine learning approaches for solving partial differential equations by contrasting their deductive and inductive epistemologies, identifying three genuine complementarities, and establishing principles for hybrid methods that rigorously address error budgets and structural guarantees across emerging computational frontiers.
This paper proposes a unified theoretical framework that quantifies the relationships between different evaluation metrics using Bayes-Optimal Set and Regret Transfer to bridge the gap between offline validation and online performance by addressing the structural asymmetry in metric mismatch.
This dissertation addresses the memory bottleneck in modern computing by advocating a shift from data-agnostic to data-informed microarchitectural designs, proposing four machine learning-driven and data-aware mechanisms that significantly enhance performance and energy efficiency.
This paper presents Megatron Core, a scalable and production-ready open-source framework that addresses the coupled memory, communication, and computation challenges of Mixture-of-Experts (MoE) training through integrated system-level optimizations, enabling high-performance training of models ranging from billions to trillions of parameters on large-scale GPU clusters.
This paper proposes a primal-dual natural actor-critic algorithm using multi-layer neural network critics and Neural Tangent Kernel theory to establish the first global convergence and cumulative constraint violation guarantees for infinite-horizon Constrained MDPs with general policy parameterizations, overcoming the limitations of previous tabular or linear-critic approaches.
This paper demonstrates that over-decaying step-size schedules in greedy sparse learning algorithms induce structural stagnation and prevent convergence in realizable regression problems, even in low-dimensional settings with controlled feature coherence.
This paper introduces Deep Incentive Design (DID), a novel framework that employs game-agnostic differentiable equilibrium blocks (DEBs) to enable the automated, neural-network-based design of multi-agent interactions across diverse economic and computer science tasks, effectively solving complex incentive problems by handling a wide range of game scales and contexts.