Academic

Academic · 1 min

Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention Looping

arXiv:2603.23998v1 Announce Type: new Abstract: Existing approaches to increasing the effective depth of Transformers predominantly rely on parameter reuse, extending computation through recursive execution. Under …

Yao Chen, Yilong Chen, Yinqi Yang, Junyuan Shang, Zhenyu Zhang, Zefeng Zhang, Shuaiyi Nie, Shuohuan Wang, Yu Sun, Hua Wu, HaiFeng Wang, Tingwen Liu

6 views Mar 26

Academic · 1 min

Thinking with Tables: Enhancing Multi-Modal Tabular Understanding via Neuro-Symbolic Reasoning

arXiv:2603.24004v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable reasoning capabilities across modalities such as images and text. However, tabular data, …

Kun-Yang Yu, Zhi Zhou, Shi-Yu Tian, Xiao-Wen Yang, Zi-Yi Jia, Ming Yang, Zi-Jian Cheng, Lan-Zhe Guo, Yu-Feng Li

8 views Mar 26

Academic · 1 min

Beyond Accuracy: Introducing a Symbolic-Mechanistic Approach to Interpretable Evaluation

arXiv:2603.23517v1 Announce Type: new Abstract: Accuracy-based evaluation cannot reliably distinguish genuine generalization from shortcuts like memorization, leakage, or brittle heuristics, especially in small-data regimes. In …

Reza Habibi, Darian Lee, Magy Seif El-Nasr

35 views Mar 26

Academic · 1 min

Implicit Turn-Wise Policy Optimization for Proactive User-LLM Interaction

arXiv:2603.23550v1 Announce Type: new Abstract: Multi-turn human-AI collaboration is fundamental to deploying interactive services such as adaptive tutoring, conversational recommendation, and professional consultation. However, optimizing …

Haoyu Wang, Yuxin Chen, Liang Luo, Buyun Zhang, Ellie Dingqiao Wen, Pan Li

17 views Mar 26

Academic · 1 min

Upper Entropy for 2-Monotone Lower Probabilities

arXiv:2603.23558v1 Announce Type: new Abstract: Uncertainty quantification is a key aspect in many tasks such as model selection/regularization, or quantifying prediction uncertainties to perform active …

Tuan-Anh Vu, S\'ebastien Destercke, Fr\'ed\'eric Pichon

11 views Mar 26

Academic · 1 min

Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG

arXiv:2603.23562v1 Announce Type: new Abstract: Synthetic data augmentation helps language models learn new knowledge in data-constrained domains. However, naively scaling existing synthetic data methods by …

Seungju Han, Konwoo Kim, Chanwoo Park, Benjamin Newman, Suhas Kotha, Jaehun Jung, James Zou, Yejin Choi

7 views Mar 26

Academic · 1 min

Safe Reinforcement Learning with Preference-based Constraint Inference

arXiv:2603.23565v1 Announce Type: new Abstract: Safe reinforcement learning (RL) is a standard paradigm for safety-critical decision making. However, real-world safety constraints can be complex, subjective, …

Chenglin Li, Guangchun Ruan, Hua Geng

7 views Mar 26

Academic · 1 min

AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization

arXiv:2603.23566v1 Announce Type: new Abstract: AscendC (Ascend C) operator optimization on Huawei Ascend neural processing units (NPUs) faces a two-fold knowledge bottleneck: unlike the CUDA …

Jiehao Wu, Zixiao Huang, Wenhao Li, Chuyun Shen, Junjie Sheng, Xiangfeng Wang

6 views Mar 26

Academic · 1 min

Causal Reconstruction of Sentiment Signals from Sparse News Data

arXiv:2603.23568v1 Announce Type: new Abstract: Sentiment signals derived from sparse news are commonly used in financial analysis and technology monitoring, yet transforming raw article-level observations …

Stefania Stan, Marzio Lunghi, Vito Vargetto, Claudio Ricci, Rolands Repetto, Brayden Leo, Shao-Hong Gan

14 views Mar 26

Academic · 1 min

StateLinFormer: Stateful Training Enhancing Long-term Memory in Navigation

arXiv:2603.23571v1 Announce Type: new Abstract: Effective navigation intelligence relies on long-term memory to support both immediate generalization and sustained adaptation. However, existing approaches face a …

Zhiyuan Chen, Yuxuan Zhong, Fan Wang, Bo Yu, Pengtao Shao, Shaoshan Liu, Ning Ding

7 views Mar 26

Academic · 1 min

Dual-Criterion Curriculum Learning: Application to Temporal Data

arXiv:2603.23573v1 Announce Type: new Abstract: Curriculum Learning (CL) is a meta-learning paradigm that trains a model by feeding the data instances incrementally according to a …

Gaspard Abel, Eloi Campagne, Mohamed Benloughmari, Argyris Kalogeratos

6 views Mar 26

Academic · 1 min

PoiCGAN: A Targeted Poisoning Based on Feature-Label Joint Perturbation in Federated Learning

arXiv:2603.23574v1 Announce Type: new Abstract: Federated Learning (FL), as a popular distributed learning paradigm, has shown outstanding performance in improving computational efficiency and protecting data …

Tao Liu, Jiguang Lv, Dapeng Man, Weiye Xi, Yaole Li, Feiyu Zhao, Kuiming Wang, Yingchao Bian, Chen Xu, Wu Yang

8 views Mar 26

Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention Looping

Thinking with Tables: Enhancing Multi-Modal Tabular Understanding via Neuro-Symbolic Reasoning

Beyond Accuracy: Introducing a Symbolic-Mechanistic Approach to Interpretable Evaluation

Implicit Turn-Wise Policy Optimization for Proactive User-LLM Interaction

Upper Entropy for 2-Monotone Lower Probabilities

Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG

Safe Reinforcement Learning with Preference-based Constraint Inference

AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization

Causal Reconstruction of Sentiment Signals from Sparse News Data

StateLinFormer: Stateful Training Enhancing Long-term Memory in Navigation

Dual-Criterion Curriculum Learning: Application to Temporal Data

PoiCGAN: A Targeted Poisoning Based on Feature-Label Joint Perturbation in Federated Learning

JCG, PC

HSOLLC Co., Ltd.