arXiv:2509.16989v3 Announce Type: replace Abstract: Post-training quantization (PTQ) of large language models (LLMs) to extremely low bit-widths remains challenging due to the fundamental trade-off between computational efficiency and representational capacity. While existing ultra-low-bit methods rely on binary approximations or quantization-aware…
arXiv:2601.00231v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) is the default way to adapt LLMs, but widely used LoRA and QLoRA are largely geometry-agnostic: they optimize in fixed, randomly oriented low-rank subspaces with first-order descent, mostly ignoring local loss curvature.…
arXiv:2512.22428v2 Announce Type: replace Abstract: While modern multivariate forecasters such as Transformers and GNNs achieve strong benchmark performance, they often suffer from systematic errors at specific variables or horizons and, critically, lack guarantees against performance degradation in deployment. Existing post-hoc…
arXiv:2601.00276v1 Announce Type: new Abstract: We present a theory of feature learning in wide L2-regularized networks showing that supervised learning is inherently compressive. We derive a kernel ODE that predicts a “water-filling” spectral evolution and prove that for any stable…
arXiv:2206.01592v2 Announce Type: replace-cross Abstract: We consider the problem of conditional density estimation, which is a major topic of interest in the fields of statistical and machine learning. Our method, called Marginal Contrastive Discrimination, MCD, reformulates the conditional density function…
arXiv:2601.00309v1 Announce Type: new Abstract: In robotics and multi-agent systems, fleets of autonomous agents often operate in subtly different environments while pursuing a common high-level objective. Directly pooling their data to learn a shared reward function is typically impractical due…
arXiv:2409.19926v4 Announce Type: replace-cross Abstract: The entropic risk measure is widely used in high-stakes decision-making across economics, management science, finance, and safety-critical control systems because it captures tail risks associated with uncertain losses. However, when data are limited, the empirical…
As these events become more common at midlatitudes, a phenomenon called an atmospheric inversion will determine how long they last.
arXiv:2502.05795v3 Announce Type: replace Abstract: In this paper, we introduce the Curse of Depth, a concept that highlights, explains, and addresses the recent observation in modern Large Language Models (LLMs) where nearly half of the layers are less effective than…
arXiv:2505.14975v3 Announce Type: replace Abstract: Offline goal-conditioned reinforcement learning (GCRL) is a promising approach for pretraining generalist policies on large datasets of reward-free trajectories, akin to the self-supervised objectives used to train foundation models for computer vision and natural language…
