The paper proposes a method to train efficient multi‑task manipulation policies by distilling knowledge from single‑task Conditional Flow Matching (CFM) experts. Instead of training separate models for each task, the authors transfer the experts’ learned velocity fields into a shared policy, combining this distillation signal with the original CFM objective. Experiments on RLBench demonstrate that this approach improves multi‑task performance while keeping the model size fixed, avoiding the need for larger capacity or performance drops seen with naive concatenated training.
By Shreya Deshmukh, Imen Mahdi, Nick Heppert, Abhinav Valada
The paper introduces Newton-Schulz Attention (NS-Attn.), a parameter‑free transformation that applies a finite Newton‑Schulz polynomial step to the output of each attention head in Vision Transformers. By normalizing each head’s feature‑by‑token matrix with its Frobenius norm, applying the NS step, and restoring the norm, the method aims to reduce spectral concentration and increase effective rank before merging heads. Experiments on ViT and Swin models over CIFAR‑10 and CIFAR‑100 show consistent accuracy gains of 0.25–0.83 percentage points, though with added inference latency.
By Xiaohe Jiang (University of Exeter), Guoqiang Zhang (University of Exeter), Tianjin Huang (University of Exeter), Ronghui Mu (University of Exeter)
arXiv:2609.27988v1 Announce Type: cross
Abstract: Methods operating on Vision Transformer (ViT) feature spaces typically rely on Euclidean distance or cosine similarity. This assumes that every direc...
By Andrew Bond, Ege Erdem \"Ozl\"u, Tuna \c{C}imen, Ilkin Umut Melanlioglu, Tolga Birdal, Erkut Erdem, Aykut Erdem
arXiv:2609.27284v1 Announce Type: new
Abstract: We present Hunyuan-A13B, an open-source large language model based on a Mixture-of-Experts architecture. It contains 80 billion total parameters but ac...
By Tencent Hunyuan Team, Ao Liu, Botong Zhou, Can Xu, Chayse Zhou, ChenChen Zhang, Chengcheng Xu, Chenhao Wang, Decheng Wu, Dengpeng Wu, Dian Jiao, Dong Du, Dong Wang, Feng Zhang, Fengzong Lian, Guanghui Xu, Guanwei Zhang, Hai Wang, Haipeng Luo, Han Hu, Huilin Xu, Jiajia Wu, Jianchen Zhu, Jianfeng Yan, Jiaqi Zhu, Jihong Zhang, Jinbao Xue, Jun Xia, Junqiang Zheng, Kai Liu, Kai Zhang, Kai Zheng, Kejiao Li, Keyao Wang, Lan Jiang, Lixin Liu, Lulu Wu, Mengyuan Huang, Peijie Yu, Peiqi Wang, Qian Wang, Qianbiao Xiang, Qibin Liu, Qingfeng Sun, Richard Guo, Ruobing Xie, Saiyong Yang, Shaohua Chen, Shihui Hu, Shuai Li, Shuaipeng Li, Shuang Chen, Suncong Zheng, Tao Yang, Tian Zhang, Tinghao Yu, Weidong Han, Weijie Liu, Weijin Zhou, Weikang Wang, Wesleye Chen, Xiao Feng, Xiaoqin Ren, Xingwu Sun, Xiong Kuang, Xuemeng Huang, Xun Cao, Yanfeng Chen, Yang Du, Zhen Yang, Yangyu Tao, Yaping Deng, Yi Shen, Yigeng Hong, Yiqi Chen
arXiv:2609.26820v1 Announce Type: cross
Abstract: Physiological time series such as electrocardiograms (ECG) and electroencephalograms (EEG) exhibit complex temporal structure, substantial acquisitio...
By Naser Mansour, Sidahmed Benabderrahmane, Ameer Rahwan
arXiv:2609.27040v1 Announce Type: cross
Abstract: Multi-GPU servers have become the standard building block of modern data centers, providing aggregated capacity through high-bandwidth interconnects....
By Yi Xu, Tian Xia, Ion Stoica
arXiv:2609.27355v1 Announce Type: cross
Abstract: Unlearning ensures LLM compliance by removing the influence of private or copyrighted training data. However, since LLM models typically undergo post...
By Jialu Wang, Jianing Deng, Shuqing Luo, Yuanzhe Li, Dongwei Wang, Jingtong Hu, Huanrui Yang, Song Wang, Tianlong Chen
arXiv:2609.27378v1 Announce Type: cross
Abstract: End-to-end speech-to-speech dialogue models listen and speak simultaneously, so a continuously open acoustic channel is exposed to adversarial manipu...
By Kian Shamsaie, Iman Modarressi
arXiv:2609.27868v1 Announce Type: cross
Abstract: Octree-based 3D Gaussian Splatting organizes anchors into multi-level hierarchies for level-of-detail rendering, but features at different levels are...
By Wei Zhang, Shiqiang Gong, Shengkai Yu, Zeyu Wang, Clement Mallet, Zhitong Xiong, Qi Wang
arXiv:2609.28358v1 Announce Type: cross
Abstract: Microscaling quantization techniques are increasingly used to represent neural network parameters with 8 bits or fewer while preserving near-full pre...
By Romain Facq, Sami Ben Ali, Olivier Sentieys
arXiv:2609.27421v1 Announce Type: new
Abstract: Multi-constraint instruction following requires a model to respond to a query under many simultaneously active constraints. Even strong instruction-tun...
By Yanzhao Zheng, Yuanqiang Yu, Tianze Xu, Chao Ma, Zhentao Zhang, Jihuai Zhu, Baohua Dong, Hangcheng Zhu, Ruohui Huang
arXiv:2609.27076v1 Announce Type: new
Abstract: Open-vocabulary visual grounding enables robots to localise task-relevant entities from natural-language queries without dependence on predefined perce...
By Linus Nwankwo, Muslim Alaran, Christian Rauch, Stanley Chukwuebuka Obilikpa, Elmar Rueckert
arXiv:2609.27233v1 Announce Type: new
Abstract: Transformer language models process sequences token by token in an autoregressive manner, making growing contexts increasingly expensive. Yet many adja...
By Zixuan Lan, Jessica Yang, Yanhong Li, Karen Livescu, Jiawei Zhou
Few-step autoregressive (AR) video diffusion enables low-latency streaming generation, but existing post-training methods predominantly rely on Distribution Matching Distillation (DMD), requiring both...
Protein modification requires navigating an immense sequence space, yet wet-lab validation remains low-throughput and costly. Although computational paradigms including protein language models (PLMs),...
Deploying deep learning models on edge CPUs is bottlenecked by computational and memory constraints. Mixed-precision quantization promises to reduce inference latency while preserving accuracy. Howeve...
Segmentation-based multi-object tracking (MOT) with foundation video models such as SAM2 offers strong localization quality, yet remains fragile in crowded, real-world scenes. In detector-prompted SAM...
Driving world-action models improve planning by coupling multimodal reasoning with future prediction, but their growing inference cost increasingly conflicts with the real-time latency requirements of...
Methods operating on Vision Transformer (ViT) feature spaces typically rely on Euclidean distance or cosine similarity. This assumes that every direction is equally meaningful, but there is no reason...
Pruning large pre-trained transformer-based ASR models such as OpenAI's Whisper has seen great adoption, as pruning the decoder led to significant end-to-end transcription speedups. For instance, the...