arXiv:2603.03517v1 Announce Type: new Abstract: General-purpose large language models (LLMs) that rely on in-context learning do not reliably deliver the scientific understanding and performance required for drug discovery tasks. Simply increasing model size or introducing reasoning tokens does not yield…
arXiv:2506.18703v3 Announce Type: replace-cross Abstract: Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition. When using appropriate modeling units, e.g., byte-pair encoding, these systems are in principle open vocabulary systems. In practice, however, they often fail to recognize words…
arXiv:2603.03523v1 Announce Type: new Abstract: We study reinforcement learning in infinite-horizon discounted Markov decision processes with continuous state spaces, where data are generated online from a single trajectory under a Markovian behavior policy. To avoid maintaining an infinite-dimensional, function-valued estimate,…
arXiv:2510.09782v2 Announce Type: replace-cross Abstract: We study how large language models (LLMs) “think” through their representation space. We propose a novel geometric framework that models an LLM’s reasoning as flows — embedding trajectories evolving where logic goes. We disentangle logical…
arXiv:2603.03524v1 Announce Type: new Abstract: As strong general reasoners, large language models (LLMs) encounter diverse domains and tasks, where the ability to adapt and self-improve at test time is valuable. We introduce MASS, a meta-learning framework that enables LLMs to…
arXiv:2602.12851v2 Announce Type: replace-cross Abstract: Deploying expressive learning models directly on programmable dataplanes promises line-rate, low-latency traffic analysis but remains hindered by strict hardware constraints and the need for predictable, auditable behavior. Chimera introduces a principled framework that maps attention-oriented…
arXiv:2603.03527v1 Announce Type: new Abstract: Vision-Language Models (VLMs) with their multimodal capabilities have demonstrated remarkable success in almost all domains, including education, transportation, healthcare, energy, finance, law, and retail. Nevertheless, the utilization of VLMs in healthcare applications raises crucial concerns…
arXiv:2603.04177v1 Announce Type: cross Abstract: Large language model (LLM) coding agents can generate working code, but their solutions often accumulate complexity, duplication, and architectural debt. Human developers address such issues through refactoring: behavior-preserving program transformations that improve structure and maintainability.…
arXiv:2603.03529v1 Announce Type: new Abstract: We introduce mlx-snn, the first spiking neural network (SNN) library built natively on Apple’s MLX framework. As SNN research grows rapidly, all major libraries — snnTorch, Norse, SpikingJelly, Lava — target PyTorch or custom backends,…
arXiv:2603.04317v1 Announce Type: cross Abstract: Recent work interprets the linear recoverability of geographic and temporal variables from large language model (LLM) hidden states as evidence for world-like internal representations. We test a simpler possibility: that much of the relevant structure…
