Paper Archive

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 9/4/2026 huggingface

Layer dropout (a.k.a. stochastic depth) has been shown to enable faster training, higher accuracy, and robustness to zero-shot layer pruning in both language and vision transformers. However, as models and datasets have scaled, dropout - particularly layer dropout - has largely disappeared from larg...

[object Object], [object Object], [object Object], [object Object] 9/4/2026 huggingface

Large Reasoning Models (LRMs) achieve superior problem-solving through extended Chain-of-Thought (CoT) generation, but the resulting key-value (KV) cache grows linearly with sequence length and creates severe memory bottlenecks, often exceeding GPU capacity for long reasoning traces. Existing KV cac...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 9/4/2026 huggingface

Skill libraries improve the sample efficiency of agentic reinforcement learning (RL) by enabling large language model (LLM) agents to reuse procedural knowledge. Yet existing paradigms exhibit structural shortcomings: they either decouple skill evolution from policy optimization or instantiate meta-...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 9/4/2026 huggingface

Optimizing multiple conversion objectives is a core challenge in industrial recommendation, often limited by signal erosion in rigid architectures. Existing Multi-Task Learning (MTL) methods typically enforce uniform dependency strengths across a static conversion funnel, overlooking how task correl...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 9/4/2026 huggingface

As spaceborne computing systems increasingly rely on neural network (NN) accelerators, the opacity of commercial, black-box architectures severely restricts the development of verifiable radiation mitigation strategies. Open-source, register-transfer level (RTL)-accessible accelerators resolve this ...

Quoc H. Nguyen, Ali Lafzi, Abhijeet Phatak, Siddharth Pratap Singh, Rohit Upadhyay, Yogananda Domlur Seetharama, Chittaranjan Tripathy 9/4/2026 arxiv

Retail search systems serve diverse geographic regions with distinct query patterns, vocabularies, and product preferences, creating significant data heterogeneity that challenges both privacy-preserving training and model personalization. Federated learning offers a natural solution for privacy, bu...

Linzhan Mou, Jiahui Lei, Zhiyang Dou, Chenyue Cai, Chaoyue Song, Adam Finkelstein, Szymon Rusinkiewicz 9/4/2026 arxiv

Recent advances in automatic rigging now deliver animation-ready 3D assets at scale, yet generating the motion to drive them remains a bottleneck. Existing learned animators are topology-constrained: they rely on category-specific templates or require per-skeleton fine-tuning and reference motions a...

Yuxiao Li, Keke Hu, Santiago Mazuelas, Yuan Shen 9/4/2026 arxiv

Wireless signals with position-related labels are pivotal for both performance evaluation and model training in the realm of wireless sensing. However, acquiring real-world datasets is often challenged by significant measurement and labeling costs. Traditional methods for synthesizing labeled wirele...

Samer Abualhanud, Max Mehltretter 9/4/2026 arxiv

Reliable 3D understanding of the surrounding environment is a core requirement for autonomous driving. Multi-view surround camera rigs provide broad scene coverage, but the spatially adjacent images typically overlap only minimally. Consequently, the depth of most pixels must be inferred from monocu...

Julien Colin, Nuria Oliver, Thomas Serre 9/4/2026 arxiv

More than a decade in, explainable AI (XAI) for computer vision has assembled a mature toolbox: attribution, feature visualization, concept-based, and circuit-based methods. Yet almost all of the field's effort has gone into building and comparing these methods, and little into the question they wer...