arXiv:2601.15331v1 Announce Type: new Abstract: The deployment of large language models (LLMs) has raised security concerns due to their susceptibility to producing harmful or policy-violating outputs when exposed to adversarial prompts. While alignment and guardrails mitigate common misuse, they remain vulnerable to automated jailbreaking methods such as GCG, PEZ, and GBDA, which generate adversarial suffixes via training and gradient-based search. Although effective, these methods particularly GCG are computationally expensive, limiting their practicality for organisations with constrained resources. This […]

Ver mais

We study federated learning (FL) over wireless fading channels where multiple devices simultaneously send their model updates. We propose an efficient emph{age-aware edge-blind over-the-air FL} approach that does not require channel state information (CSI) at the devices. Instead, the parameter server (PS) uses multiple antennas and applies maximum-ratio combining (MRC) based on its estimated sum of the channel gains to detect the parameter updates. A key challenge is that the number of orthogonal subcarriers is limited; thus, transmitting […]

Ver mais

arXiv:2601.23252v1 Announce Type: cross Abstract: Model comparison and calibrated uncertainty quantification often require integrating over parameters, but scalable inference can be challenging for complex, multimodal targets. Nested Sampling is a robust alternative to standard MCMC, yet its typically sequential structure and hard constraints make efficient accelerator implementations difficult. This paper introduces Nested Slice Sampling (NSS), a GPU-friendly, vectorized formulation of Nested Sampling that uses Hit-and-Run Slice Sampling for constrained updates. A tuning analysis yields a simple near-optimal rule […]

Ver mais

arXiv:2603.05576v1 Announce Type: new Abstract: Generalizing skill policies to novel conditions remains a key challenge in robot learning. Imitation learning methods, while data-efficient, are largely confined to the training region and consistently fail on input data outside it, leading to unpredictable policy failures. Alternatively, transfer learning approaches offer methods for trajectory generation robust to both changes in environment or tasks, but they remain data-hungry and lack accuracy in zero-shot generalization. We address these challenges by framing the problem […]

Ver mais

I’ve been working on an educational implementation repo for speculative decoding: https://github.com/shreyansh26/Speculative-Decoding The goal is not to wrap existing libraries, but to implement several speculative decoding methods from scratch behind a shared decoding/evaluation contract so that the differences between proposer designs are easier to study. Implemented methods so far: EAGLE-3 Medusa-1 standard draft model speculation PARD / parallel draft models n-gram prompt lookup suffix decoding The repo has both training and inference paths where applicable. For learned proposers, […]

Ver mais

arXiv:2603.20219v1 Announce Type: new Abstract: Autoregressive language models trained with next-token prediction generate text by sampling one discrete token at a time. Although very scalable, this objective forces the model to commit at every step, preventing it from exploring or reflecting upon multiple plausible continuations. Furthermore, the compute allocation across tokens is uniform; every token is formed based on a single forward-pass, potentially limiting the model’s expressiveness in cases where difficult tokens require inherently more compute. Towards addressing […]

Ver mais

Reinforcement Learning (RL) enhances LLM reasoning, yet a paradox emerges as models scale: strong base models saturate standard benchmarks (e.g., MATH), yielding correct but homogeneous solutions. In such environments, the lack of failure cases causes the advantage signal in group-relative algorithms (e.g., GRPO) to vanish, driving policies into mode collapse. To address this, we propose Constrained Uniform Top-K Sampling (CUTS), a parameter-free decoding strategy enforcing structure-preserving exploration. Unlike standard sampling that follows model biases, CUTS flattens the local […]

Ver mais

As engineers, we’re taught to design for reliability. We do design calculations, run simulations, build and test prototypes, and even then we recognize that these are imperfect, so we include safety factors. When it comes to the Industrial Internet of Things (IIoT) though, we rarely give the same level of scrutiny to the components that we rely on. What if we treated our IIoT database the same way we treated the physical things we produce? We build and […]

Ver mais