arXiv:2507.01679v2 Announce Type: replace Abstract: Existing post-training techniques for large language models are broadly categorized into Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT). Each paradigm presents a distinct trade-off: SFT excels at mimicking demonstration data but can lead to problematic…
arXiv:2509.20591v1 Announce Type: new Abstract: The Fast Multipole Method (FMM) is an efficient numerical algorithm for computation of long-ranged forces in $N$-body problems within gravitational and electrostatic fields. This method utilizes multipole expansions of the Green’s function inherent to the…
arXiv:2508.16949v3 Announce Type: replace Abstract: Recent advances in Large Language Models (LLMs) have underscored the potential of Reinforcement Learning (RL) to facilitate the emergence of reasoning capabilities. Despite the encouraging results, a fundamental dilemma persists as RL improvement relies on…
arXiv:2509.20595v1 Announce Type: new Abstract: Quality of Experience (QoE) modeling is crucial for optimizing video streaming services to capture the complex relationships between different features and user experience. We propose a novel approach to QoE modeling in video streaming applications…
arXiv:2509.17034v2 Announce Type: replace Abstract: Out-of-distribution (OOD) detection is crucial for deploying robust machine learning models. However, when training data follows a long-tailed distribution, the model’s ability to accurately detect OOD samples is significantly compromised, due to the confusion between…
arXiv:2509.20599v1 Announce Type: new Abstract: Backpropagation through (neural) SDE solvers is traditionally approached in two ways: discretise-then-optimise, which offers accurate gradients but incurs prohibitive memory costs due to storing the full computational graph (even when mitigated by checkpointing); and optimise-then-discretise,…
arXiv:2408.01730v2 Announce Type: replace-cross Abstract: We introduce a real-time identification method for discrete-time state-dependent switching systems in both the input–output and state-space domains. In particular, we design a system of adaptive algorithms running in two timescales; a stochastic approximation algorithm…
arXiv:2509.20605v1 Announce Type: new Abstract: Function encoders are a recent technique that learn neural network basis functions to form compact, adaptive representations of Hilbert spaces of functions. We show that function encoders provide a principled connection to feature learning and…
arXiv:2505.11679v2 Announce Type: replace-cross Abstract: Ambiguity in natural language is a significant obstacle for achieving accurate text to structured data mapping through large language models (LLMs), which affects the performance of tasks such as mapping text to agentic tool calling…
arXiv:2509.20609v1 Announce Type: new Abstract: Mutual information (MI) is one of the most general ways to measure relationships between random variables, but estimating this quantity for complex systems is challenging. Denoising diffusion models have recently set a new bar for…
