arXiv:2604.14626v2 Announce Type: replace-cross
Abstract: Mixture-of-Experts (MoE) models have become the dominant architecture for large-scale language models, yet on-premises serving remains fundamentally memory-bound as batching turns sparse per-to…
arXiv:2604.21741v1 Announce Type: new
Abstract: Post-training is essential for turning pretrained generalist robot policies into reliable task-specific controllers, but existing human-in-the-loop pipelines remain tied to physical execution: each corre…
arXiv:2604.21006v1 Announce Type: new
Abstract: We introduce Deep FinResearch Bench, a practical and comprehensive evaluation framework for deep research (DR) agents in financial investment research. The benchmark assesses three dimensions of report q…
arXiv:2508.10177v3 Announce Type: replace
Abstract: Recent Large Language Model (LLM)-based AutoML systems demonstrate impressive capabilities but face significant limitations such as constrained exploration strategies and a severe execution bottlenec…
arXiv:2604.21029v1 Announce Type: cross
Abstract: The recent emergence of planar transport systems necessitates re-evaluation of Flexible Manufacturing Systems (FMS) to address the simultaneous scheduling of internal logistics and production operation…
arXiv:2601.11044v4 Announce Type: replace
Abstract: Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain focused on single ag…
arXiv:2604.08016v2 Announce Type: replace
Abstract: Regardless of its foundational role in human discovery and sense-making, abductive reasoning–the inference of the most plausible explanation for an observation–has been relatively underexplored in …
arXiv:2507.01829v2 Announce Type: replace-cross
Abstract: Multi-timescale sequence modeling relies on capturing both local fast dynamics and global slow context; yet, maintaining these capabilities under the strict memory constraints common to edge de…
arXiv:2511.11439v2 Announce Type: replace-cross
Abstract: Binary security has increasingly relied on deep learning to reason about malware behavior and program semantics. However, the performance often degrades as threat landscapes evolve and code rep…
arXiv:2604.21251v1 Announce Type: cross
Abstract: Large language models (LLMs) trained on unfiltered corpora inherently risk retaining sensitive information, necessitating selective knowledge unlearning for regulatory compliance and ethical safety. Ho…