In spite of the fundamental role of neural networks in contemporary machine learning research, our understanding of the computational complexity of optimally training neural networks remains incomplete even when dealing with the simplest kinds of activation functions. Indeed, while there has been a number of very recent results that establish ever-tighter lower bounds for the problem under linear and ReLU activation functions, less progress has been made towards the identification of novel polynomial-time tractable network architectures.
Frozen perception foundation models encode rich geometric, semantic, and dynamic knowledge. Yet narrow conditioning interfaces may attenuate task-relevant cues, while static fusion cannot adjust expert contributions to each scene.
Knowledge distillation (KD) is a standard approach for compressing sequence-to-sequence models, but its per-sample effects are rarely examined. On the BanSum Bangla summarization benchmark, we find that standard KD improves ROUGE-L by only +0.
Deep learning frameworks like nnU-Net achieve state-of-theart brain lesion segmentation performance but remain difficult to deploy in clinical research environments due to, among other reasons, software dependencies and computational requirements. We introduce StrokeSeg2, a lightweight, modular, cross-platform C++/Qt framework designed to adapt resource-intensive 3D stroke segmentation pipelines into portable and reproducible applications.
Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into inference-time detection or training-time mitigation, but face two key limitations.
arXiv:2510. 02345v4 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) Large Language Models (LLMs) face a trilemma of load imbalance, parameter redundancy, and communication overhead.
By Peijun Zhu, Ning Yang, Baoliang Tian, Jiayu Wei, Weihao Zhang, Haijun Zhang, Pin Lv
arXiv:2607. 18293v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) teaches large language models new skills through a teacher that shares the student's backbone and supervises its own rollouts.
By Yingzi Ma, Zichen Zhu, Ming Jiang, Chaowei Xiao
arXiv:2602. 22647v2 Announce Type: replace-cross Abstract: Generative retrieval has emerged as a powerful paradigm for LLM-based recommendation.
By Zhengyang Su, Isay Katsman, Yueqi Wang, Ruining He, Lukasz Heldt, Raghunandan Keshavan, Shao-Chuan Wang, Xinyang Yi, Mingyan Gao, Onkar Dalal, Lichan Hong, Ed Chi, Ningren Han
arXiv:2607. 18921v1 Announce Type: cross Abstract: Circuit extraction identifies a small set of model components whose presence preserves a target behavior under ablation, and the resulting circuit is often read as the mechanism behind that behavior.
By Yang Sheng, Jie Fu
arXiv:2607. 18867v1 Announce Type: new Abstract: Large language models leak parametric knowledge of realized outcomes into historical financial decision tasks.
By Haozhe Jia
arXiv:2409. 07609v3 Announce Type: replace-cross Abstract: Deploying adversarially robust machine learning systems requires continuous trade-offs between robustness, cost, and latency.
By Charles Meyers, Mohammad Reza Saleh Sedghpour, Tommy L\"ofstedt, Erik Elmroth
arXiv:2605. 05482v2 Announce Type: replace Abstract: Large language models (LLMs) are rapidly being adopted across various domains.
By Denys Katerenchuk, Pablo Duboue, Keelan Evanini, David Gondek, Nithin Govindugari, Olivier Allauzen, Joshua Baptiste, David J More, Joshua Schechter
arXiv:2403. 18026v3 Announce Type: replace-cross Abstract: High-throughput imaging is often constrained by a trade-off between acquisition speed and image quality.
By Dominik Panek, Carina Rz\k{a}ca, Maksymilian Szczypior, Joanna Sorysz, Krzysztof Misztal, Zbigniew Baster, Zenon Rajfur
arXiv:2607. 18280v1 Announce Type: cross Abstract: Large language models (LLMs) are often compressed through static parameter pruning or dynamic token-level computation, yet aggressive sparsification can trigger rapid performance degradation beyond an essential sparsity boundary.
By Chao Han, Haozhe Hu, Xiaoyu Shen
arXiv:2607. 18835v1 Announce Type: cross Abstract: Antibodies are essential therapeutic molecules, and their complementarity-determining regions (CDRs) form the primary antigen-recognition interface.
By Zhuo Yang, Jiaying He, Jiaqing Xie, Daolang Wang, Xipeng Qiu, Yuxin Wang, Tianfan Fu, Beilun Wang
arXiv:2607. 18284v1 Announce Type: cross Abstract: To excel at their domain large language models are comprised of billions of parameters.
By Athanasios Ntovas, Alexandros Doumanoglou, Petros Drakoulis, Dimitris Zarpalas
arXiv:2607. 18748v1 Announce Type: cross Abstract: This paper proposes ConceptCF, a method for counterfactual generation that operates on human-interpretable concepts.
By Annemarie Jutte, Faizan Ahmed, Jeroen Linssen, Maurice van Keulen
arXiv:2607. 19108v1 Announce Type: new Abstract: Text-attributed graphs (TAGs) are an important graph data form that combine relational structure with rich node text.
By Yuze Dai, Zhihan Zhang, Yan Zhao, Ruoyu Wu, Xunkai Li, Zekai Chen, Qiangqiang Dai, Hongchao Qin, Ronghua Li
arXiv:2605. 23348v2 Announce Type: replace-cross Abstract: AI power demand is growing at an unprecedented rate while power grids are often ailing and struggle to keep up.
By Tella Rajashekhar Reddy, Atharva Deshmukh, Liangcheng Yu, Chaojie Zhang, Mike Shepperd, Rohan Gandhi, Anjaly Parayil, Srinivasan Iyengar, Ajay Manchepalli, Debopam Bhattacherjee
arXiv:2607. 19317v1 Announce Type: new Abstract: Circuit analysis can support not only model explanation but also downstream interventions such as pruning, editing, steering, and selective fine-tuning.
By Pratinav Seth, Hem Gosalia, Aditya Kasliwal, Vinay Kumar Sankarapu