arXiv:2509.21743v1 Announce Type: new Abstract: Large reasoning models improve accuracy by producing long reasoning traces, but this inflates latency and cost, motivating inference-time efficiency. We propose Retrieval-of-Thought (RoT), which reuses prior reasoning as composable “thought” steps to guide new problems.…
arXiv:2404.11973v2 Announce Type: replace Abstract: This critical review provides an in-depth analysis of Large Language Models (LLMs), encompassing their foundational principles, diverse applications, and advanced training methodologies. We critically examine the evolution from Recurrent Neural Networks (RNNs) to Transformer models,…
arXiv:2509.21765v1 Announce Type: new Abstract: Recent neural solvers have demonstrated promising performance in learning to solve routing problems. However, existing studies are primarily based on one-off training on one or a set of predefined problem distributions and scales, i.e., tasks.…
arXiv:2406.01086v2 Announce Type: replace-cross Abstract: Large annotated datasets are crucial for the success of deep neural networks, but labeling data can be prohibitively expensive in domains such as medical imaging. This work tackles the subset selection problem: selecting a small…
arXiv:2509.21766v1 Announce Type: new Abstract: Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical real-world tasks, such as large-scale software development, commercial investment, and scientific discovery,…
arXiv:2504.00220v2 Announce Type: replace-cross Abstract: This paper presents a novel theoretical framework for understanding how diffusion models can learn disentangled representations. Within this framework, we establish identifiability conditions for general disentangled latent variable models, analyze training dynamics, and derive sample…
arXiv:2509.21782v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly positioned as AI collaborators for building complex web-related applications like GUI agents and front-end code generation. However, existing benchmarks largely emphasize visual perception or UI code generation, showing…
arXiv:2505.17117v5 Announce Type: replace-cross Abstract: Humans organize knowledge into compact categories that balance compression with semantic meaning preservation. Large Language Models (LLMs) demonstrate striking linguistic abilities, yet whether they achieve this same balance remains unclear. We apply the Information Bottleneck…
arXiv:2509.21799v1 Announce Type: new Abstract: Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction. Despite rapid advancements, current approaches are hindered by several critical challenges: data bottleneck in end-to-end training, high…
arXiv:2507.03262v2 Announce Type: replace-cross Abstract: Recent multimodal large language models (MLLMs) increasingly integrate multiple vision encoders to improve performance on various benchmarks, assuming that diverse pretraining objectives yield complementary visual signals. However, we show this assumption often fails in practice.…
