arXiv:2505.12419v3 Announce Type: replace Abstract: In this paper, we study the Karush-Kuhn-Tucker (KKT) points of the associated maximum-margin problem in homogeneous neural networks, including fully-connected and convolutional neural networks. In particular, We investigates the relationship between such KKT points across…
arXiv:2510.19990v1 Announce Type: new Abstract: Masked diffusion language models (MDLMs) are trained to in-fill positions in randomly masked sequences, in contrast to next-token prediction models. Discussions around MDLMs focus on two benefits: (1) any-order decoding and 2) multi-token decoding. However,…
arXiv:2505.22601v2 Announce Type: replace Abstract: Machine unlearning algorithms aim to remove the influence of specific training samples, ideally recovering the model that would have resulted from training on the remaining data alone. We study unlearning in the overparameterized setting, where…
arXiv:2510.20019v1 Announce Type: new Abstract: Radio Frequency Identification (RFID) tracking may be a viable solution for defense assets that must be stored in accordance with security guidelines. However, poor sensor specificity (vulnerabilities include long range detection, spoofing, and counterfeiting) can…
arXiv:2506.16349v2 Announce Type: replace Abstract: Watermarking the outputs of generative models has emerged as a promising approach for tracking their provenance. Despite significant interest in autoregressive image generation models and their potential for misuse, no prior work has attempted to…
arXiv:2510.20022v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities, enabling language agents to excel at single-turn tasks. However, their application to complex, multi-step, and long-horizon tasks remains challenging. While reinforcement learning (RL) offers a promising avenue…
arXiv:2510.04008v2 Announce Type: replace Abstract: Softmax Attention has a quadratic time complexity, which becomes prohibitive to run at long contexts, even with highly optimized GPU kernels. For example, FlashAttention (an exact, GPU-optimized implementation of Softmax Attention) cannot complete a single…
arXiv:2510.20028v1 Announce Type: new Abstract: Since its 2009 genesis block, the Bitcoin network has processed num{>1.08} billion (B) transactions representing num{>8.72}B BTC, offering rich potential for machine learning (ML); yet, its pseudonymity and obscured flow of funds inherent in its…
arXiv:2510.19705v2 Announce Type: replace Abstract: Transformer language models generate text autoregressively, making inference latency proportional to the number of tokens generated. Speculative decoding reduces this latency without sacrificing output quality, by leveraging a small draft model to propose tokens that…
arXiv:2510.20031v1 Announce Type: new Abstract: Temporal point processes are powerful generative models for event sequences that capture complex dependencies in time-series data. They are commonly specified using autoregressive models that learn the distribution of the next event from the previous…
