The scaling exponent in neural scaling laws is not fixed but systematically depends on the optimizer used, with preconditioned optimizers generally yielding steeper scaling.

This study empirically benchmarks classical and quantum machine learning models for image recognition, finding that while quantum models offer superior accuracy and resource efficiency at high dimensi…

The paper introduces Score Broadcast and Decorrelation (SBD), a general theoretical framework that unifies broadcast-based credit assignment across various differentiable loss functions by leveraging…

This paper introduces survey sampling techniques to estimate or minimize empirical pairwise loss functions, showing that targeting informative pairs significantly reduces computational cost while main…

This paper analyzes the poor performance of Meta-learning for Training-data Selection (MTS) and proposes that increasing the batch size and incorporating informative features can significantly improve…

The paper introduces TSVD, a novel framework that efficiently pre-trains LLMs by enforcing both low rank and strict weight orthonormality, achieving performance comparable to full-parameter models wit…

This paper identifies prediction bias, a failure mode of entropy minimization in test-time adaptation, and proposes Distribution Shift Bias Reduction (DSBR) to stabilize adaptation and prevent model c…

The paper introduces an Item Response Theory (IRT)-based indicator that effectively identifies likely mislabeled items in existing LLM benchmarks, revealing systematic errors in labeling and model spe…

VideoMLA introduces a novel Multi-Head Latent Attention (MLA) mechanism that replaces per-head KV caches with a shared low-rank content latent, significantly reducing memory and improving throughput f…

The paper proposes evaluating certified training methods by comparing their Pareto fronts across the natural-certified accuracy trade-off, revealing superior performance and previously unappreciated c…

The paper identifies a fundamental mismatch between standard pairwise ranking metrics (like AP and FPR-95) and the true assignment objective in multi-view object association, proposing a Sinkhorn-base…

The paper introduces CalArena, a large-scale, standardized benchmark covering nearly 2000 experiments to comprehensively evaluate post-hoc calibration methods, finding that smooth calibration function…

The paper investigates applying Riemannian optimization techniques to low-rank matrix parameters for deep learning, but finds that the proposed methods do not conclusively outperform the AdamW baselin…

This paper introduces CFMME, a comprehensive Chinese financial multimodal benchmark, and evaluates current Large Vision-Language Models (LVLMs), finding that while state-of-the-art models perform mode…

The paper argues that the standard FID metric is unreliable because its performance depends significantly on the geometric structure and density of the reference dataset, not just the sample quality.

The paper introduces LL-Bench, a comprehensive benchmark for evaluating large-scale generative models on low-level vision tasks, and proposes LL-Score, an MLLM-based evaluator that better aligns quali…

This paper develops a unified spectral analysis framework to explain how knowledge transfer (KT) works across different machine learning regimes, such as Knowledge Distillation and Weak-to-Strong gene…