This paper proposes a preconditioning layer for stable weight conditioning in LLM training.

This paper proposes Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit propagation entirely.

This paper presents the benefits of visual pretraining for foundation model intelligence, outperforming text-only pretraining on multiple backbones and benchmarks.

This paper investigates the application of Parameter-Efficient Fine-Tuning (PEFT) methods, specifically adapters and LoRA, to large pretrained models for instance segmentation, demonstrating that thes…

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 proposes pretraining a Perceiver-style in-context learner on synthetic data to solve Multiple Instance Learning (MIL) tasks efficiently in the low-label regime.

This paper demonstrates that in-domain pretraining of BERT significantly improves the detection of DNS exfiltration, particularly in maintaining a low false positive rate.

The paper introduces TabPrep, a feature engineering pipeline that systematically improves performance across various tabular machine learning models by addressing structural data patterns ignored by c…

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…

The authors present ZONOS2 8B, a TTS model with improved naturalness, prosody, and voice cloning fidelity, achieved through scaling, data expansion, and simplification.

The paper introduces a novel, non-deep neural network architecture that achieves the performance of LLMs by finding the global optimum of the loss function in a single, closed-form iteration, eliminat…

This book provides a compact, derivation-oriented mathematical primer that connects major families of generative AI models, showing their underlying structural relationships.

The paper proposes a novel layer and point-wise projection mapping combined with LoRA injection to efficiently distill knowledge from a large teacher model to a small student model, significantly impr…

The paper introduces PRAXIS, a novel algorithm that efficiently approximates the computation of 'Rashomon sets' for decision trees, significantly reducing memory and runtime complexity.

This paper studies the behavior of mixture-of-experts (MoE) models under distribution shift and proposes an adversarial reweighting method to improve their calibration.

PRIMA is a framework that significantly improves 3D quadruped mesh recovery by integrating biological knowledge and a test-time adaptation strategy, achieving state-of-the-art results on diverse and c…

The paper argues that large language models (LLMs) are a special case of world models and proposes a continuous spectrum between token prediction and latent-space architectures.