10410 papers
This paper introduces fedCI and fedCI-IOD, a novel framework for privacy-preserving federated causal discovery that enables conditional independence testing and latent confounding analysis across heterogeneous, distributed datasets with non-identical variables and mixed data types.
This study demonstrates that simple lung cropping preprocessing effectively mitigates racial shortcut learning in chest X-ray diagnosis models by suppressing spurious racial cues while preserving diagnostic accuracy, thereby avoiding the typical fairness-accuracy trade-off.
This paper proposes Alt-FL, a novel federated learning framework that employs a round-based interleaving strategy of Differential Privacy, Homomorphic Encryption, and synthetic data to effectively balance privacy protection, learning quality, and system efficiency under varying resource constraints.
This paper introduces GeoDVF, a geometry-adaptive deep variational framework that jointly optimizes neural network-parameterized order parameters and trainable domain sizes to eliminate artificial stress and robustly discover stable and metastable ordered phases in the Landau-Brazovskii model from random initializations.
This paper proposes a trainable bitwise soft quantization layer that compresses neural network input features using sigmoid-approximated step functions, achieving significant data transmission reductions (5x to 16x) with minimal accuracy loss for efficient IoT applications.
This paper proposes a mechanism design framework for AI regulation that forces providers to bet on their model's compliance, proving that such mechanisms can achieve perfect market outcomes if and only if the set of non-compliant distributions forms a credal set, thereby bridging mechanism design and imprecise probability to create enforceable regulations.
This paper introduces the Sequential Thresholding of Coefficient of Variation (STCV), a novel sparse regression algorithm that replaces magnitude-based thresholding with a dimensionless statistical metric to ensure robust and accurate identification of governing equations in non-linear dynamics, even when data is normalized and noisy.
This paper introduces Stable-LoRA, a weight-shrinkage optimization strategy that resolves the feature learning instability caused by non-zero initialization in Low-Rank Adaptation (LoRA) while preserving its benefits and achieving superior performance across diverse tasks without additional memory costs.
This paper proposes a vocabulary trimming strategy for speculative decoding that formulates draft model vocabulary selection as a constrained optimization problem to balance token coverage and latency, achieving significant throughput improvements and latency reductions by tailoring the vocabulary to domain-specific workloads.
This paper introduces IAENet, a novel Transformer-based multi-label learning framework that leverages a new Multi-label Adverse Events dataset (MuAE), an improved TAFiLM module for robust data fusion, and a Label-Constrained Reweighting Loss to effectively predict multiple intraoperative adverse events with significantly higher accuracy than existing baselines.
The paper introduces KARL, a system that leverages multi-task reinforcement learning and an agentic synthesis pipeline to train enterprise search agents achieving state-of-the-art, Pareto-optimal performance across diverse, hard-to-verify search tasks while surpassing leading closed models with sufficient compute.
This paper proposes a novel, computationally efficient framework for learning optimal individualized decision rules that incorporate demographic parity and conditional demographic parity constraints to mitigate discriminatory effects, supported by theoretical convergence guarantees and empirical validation.
By employing an interventional approach that modifies Transformer architecture, this paper demonstrates that enforcing spherical topology and uniform attention routing eliminates the delayed generalization phenomenon known as grokking in modular addition tasks, provided these architectural priors align with the task's intrinsic symmetries.
This paper introduces ASR-TRA, a novel test-time reinforcement learning framework that leverages audio-text semantic rewards and causal intervention to overcome confirmation bias in existing adaptation methods, thereby significantly improving ASR robustness and accuracy in noisy and accented environments without ground-truth labels.
SlideSparse is the first system to enable Sparse Tensor Core acceleration for accuracy-preserving structured sparsity on commodity GPUs by employing a sliding window decomposition and activation lifting technique, achieving near-theoretical speedups for LLMs without hardware modifications.
This paper introduces Recursive Inference Machines (RIMs), a neural reasoning framework that unifies neural backbones with classical recursive inference mechanisms to enhance the performance of models like Tiny Recursive Models on complex reasoning benchmarks such as ARC-AGI and Sudoku Extreme, as well as tabular data classification tasks.
This paper proposes a privacy-preserving, two-stage federated learning framework that clusters distributed wind turbines based on long-term behavioral statistics using Double Roulette Selection and recursive Auto-split refinement to train localized LSTM models, achieving competitive short-term forecasting accuracy that outperforms geographic partitioning while maintaining data locality.
This paper proposes a robust auditing framework for automatic speech recognition systems that moves beyond traditional Word Error Rate by introducing the Sample Difficulty Index and semantic metrics to quantify and mitigate the "diversity tax" disproportionately affecting marginalized speakers.
This paper introduces "Whisperer," a sample-efficient visual prompting framework that bootstraps frozen OCR models by using a four-stage behavioral cloning curriculum to learn diffusion-based preprocessors that enhance degraded text inputs, achieving an 8% absolute reduction in Character Error Rate without modifying the downstream model's weights.
This paper demonstrates that distribution shift is the primary cause of performance degradation in deeper layers of Vision Transformers and reveals that optimal out-of-distribution probing requires selecting between feedforward network activations and normalized self-attention outputs depending on the severity of the shift.