FLoKD is an adaptive knowledge‑distillation framework designed for federated fine‑tuning of low‑rank LLMs over wireless networks. It transmits intermediate LoRA activations instead of full parameters or token‑level logits, and uses transformer block importance scoring plus dataset selection to reduce communication. Experiments on WikiText‑103, PTB, and Dialog show a 50‑65% reduction in communication while maintaining competitive perplexity.
By Xinlu Zhang, Na Yan, Yang Su, Yansha Deng, Toktam Mahmoodi
arXiv:2609.13692v1 Announce Type: cross
Abstract: LLM serving reuses KV cache by exact prefix match, so when a prompt is assembled from a set of reusable pieces -- retrieved passages, tool definition...
By Rong He
arXiv:2609.15598v1 Announce Type: cross
Abstract: Generative recommendation has emerged as a promising end-to-end paradigm for personalized recommendation. However, user preferences continuously evol...
By Xinyu Lin, Zhuosong Jiang, Zixiao Suo, Siqin Wang, Hanqing Zeng, Hanchao Yu, Yinglong Xia, Jiang Zhang, Aashu Singh, Fei Liu, Wenjie Wang, Fuli Feng, Yang Song, Qifan Wang, Tat-Seng Chua
arXiv:2609.15743v1 Announce Type: new
Abstract: Automatic speech recognition (ASR) systems, trained on paired speech-text data, have been improved by leveraging language models (LMs) trained on text-...
By Hayato Futami, Tatsuya Kawahara
arXiv:2511.03728v2 Announce Type: replace
Abstract: On-device AI agents offer the potential for personalized, low-latency assistance, but their deployment is fundamentally constrained by limited memo...
By Sanidhya Vijayvargiya, Rahul Lokesh
arXiv:2609.14783v1 Announce Type: cross
Abstract: Robots need touch to manipulate objects safely and reliably, as many properties, such as softness, texture, and contact stability, are hard to infer...
By Mashood M. Mohsan, Muhayy Ud Din, Binzhao Xu, Ahmad Abubakar, Irfan Hussain
arXiv:2609.13199v1 Announce Type: new
Abstract: Knowledge distillation aims to improve the performance of lightweight student models by transferring knowledge from larger and more powerful teacher mo...
By Dawen Jiang, Zhishu Shen, Zeyu Liu, Tiehua Zhang
arXiv:2601.14945v3 Announce Type: replace-cross
Abstract: Large-scale Vision-Language-Action (VLA) models offer semantic generalization but suffer from high inference latency because they adopt a low...
By Yuteng Sun, Haoran Wang, Ruofei Bai, Zhengguo Li, Jun Li, Meng Yee Michael Chuah, Wei Yun Yau
The paper introduces Sparsity-Adaptive Sharpness-Aware Minimization (SA‑SAM), a method that adjusts the perturbation radius in sharpness-aware training to remain consistent as model sparsity increases. It also evaluates a Magnitude‑Weighted Hessian (MWH) importance metric derived from second‑order analysis. Experiments on CIFAR‑10‑C, CIFAR‑100‑C, and ImageNet‑100‑C show that SA‑SAM improves corruption robustness at 80–90% sparsity while maintaining clean accuracy, and the study reports inference throughput at deployment‑relevant sparsity levels.
By Shiryu Ueno, Yoshikazu Hayashi, Kunihito Kato
arXiv:2602.08370v2 Announce Type: replace-cross
Abstract: Realizing versatile and human-like performance in high-demand sports like badminton remains a formidable challenge for humanoid robotics. Unl...
By Yeke Chen, Shihao Dong, Xiaoyu Ji, Jingkai Sun, Zeren Luo, Liu Zhao, Jiahui Zhang, Wanyue Li, Ji Ma, Bowen Xu, Yimin Han, Xuanyi Li, Yudong Zhao, Liyun Li, Peng Lu
arXiv:2609.15228v1 Announce Type: new
Abstract: Unsupervised registration of large-scale LiDAR point clouds remains challenging due to the geometric ambiguity inherent in outdoor scenes, which degrad...
By Kezheng Xiong, Shiyun Xu, Sheng Ao, Siqi Shen, Cheng Wang, Chenglu Wen
arXiv:2609.14193v1 Announce Type: cross
Abstract: On-policy distillation (OPD) has become a standard component of frontier post-training pipelines, yet how much its training data actually contributes...
By Gengsheng Li, Mao Zheng, Mingyang Song, Jie Sun, Zeyuan Liu, Ruiqi Liu, Qiyong Zhong, Haiyun Guo, Junfeng Fang, Jinqiao Wang
arXiv:2609.13615v1 Announce Type: new
Abstract: For our submission to the WMT26 Creole Language Translation Shared Task, we focus on machine translation (MT) models for Pacific creoles: Tok Pisin, Bi...
By Rapha\"el Merx, Nick Thieberger, Ekaterina Vylomova
SpliTEE extends the split‑inference architecture of Slalom to large language models by protecting intermediate GPU computations with differential privacy rather than encryption. The authors show that masking intermediate representations is essential, as a prompt‑reconstruction attack can recover prompts with about 80% accuracy. Their global sensitivity analysis bounds the noise needed, and they demonstrate that SpliTEE on Intel TDX achieves near‑double the speed of fully CPU‑based inference and outperforms encryption‑based Slalom while maintaining higher accuracy.
By Shashie Dilhara Batan Arachchige, Robin Carpentier, Hassan Jameel Asghar, Dali Kaafar
arXiv:2609.13947v1 Announce Type: cross
Abstract: In-sensor computing reduces the cost of transmitting high-resolution image data by performing early-stage processing near the sensor. However, the lo...
By Chengwei Zhou, Abu Masum, Xuming Chen, Mehran Moghadam, Sreetama Sarkar, Arnab Sanyal, Md Abdullah-Al Kaiser, M. Hassan Najafi, Sercan Aygun, Gourav Datta
arXiv:2609.15171v1 Announce Type: new
Abstract: Airborne optical tracking of uncrewed aerial vehicle (UAV) swarms is challenging due to extremely small target scales, rapid viewpoint changes, and clu...
By Zhaochen Chu, Tao Song, Ren Jin, Mingdong Jia, Defu Lin
arXiv:2609.15671v1 Announce Type: cross
Abstract: Visual Question Answering (VQA) with Vision-Language Models (VLMs) is increasingly used in privacy-sensitive and bandwidth-constrained settings. Fede...
By Md Khalid Syfullah, Alvi Ataur Khalil
MorphoStyle is a new framework for shape‑aware motion style transfer that uses a shape‑conditioned FSQ‑VAE. It disentangles style from content through a contrastive style encoder, a text‑guided style‑routing mechanism, and a manifold‑preserving style modulator. Experiments on benchmark datasets show that MorphoStyle outperforms existing baselines in both shape control and motion style transfer.
By Xin Feng, Eleonora D'Arnese, Mohan Sridharan
arXiv:2609.15130v1 Announce Type: cross
Abstract: woma is a real-time foundation model for gastrointestinal endoscopy: a network trained without labels on about a million endoscopy frames, from which...
By Thang Tran, Lan Dang
arXiv:2609.15883v1 Announce Type: cross
Abstract: Offline reinforcement learning aims to learn a policy solely from fixed datasets, which often contain multimodal action distributions. Flow policies...
By Jaehun Shon, Jinha Choi, Jongwook Jeon, Jongmin Lee