Tootfinder

Mellum: Production-Grade in-IDE Contextual Code Completion with Multi-File Project Understanding
Nikita Pavlichenko, Iurii Nazarov, Ivan Dolgov, Ekaterina Garanina, Dmitry Ustalov, Ivan Bondyrev, Kseniia Lysaniuk, Evgeniia Vu, Kirill Chekmenev, Joseph Shtok, Yaroslav Golubev, Anton Semenkin, Uladzislau Sazanovich
https://arxiv.org/abs/2510…

Mellum: Production-Grade in-IDE Contextual Code Completion with Multi-File Project Understanding
We present the Mellum models family, open-weight code completion models designed for interactive use in JetBrains IDEs. Mellums have 4B parameters, adopt a Llama-style architecture, and are pre-trained on ~4T tokens of permissively licensed, multi-language code. Our studies show that (i) careful data curation and staged training significantly improve the model's quality, (ii) editor-critical capabilities such as context packing are necessary for high-quality suggestions, and (iii) a compact, ta…

An Encoder-Decoder Network for Beamforming over Sparse Large-Scale MIMO Channels
Yubo Zhang, Jeremy Johnston, Xiaodong Wang
https://arxiv.org/abs/2510.02355 https://

An Encoder-Decoder Network for Beamforming over Sparse Large-Scale MIMO Channels
We develop an end-to-end deep learning framework for downlink beamforming in large-scale sparse MIMO channels. The core is a deep EDN architecture with three modules: (i) an encoder NN, deployed at each user end, that compresses estimated downlink channels into low-dimensional latent vectors. The latent vector from each user is compressed and then fed back to the BS. (ii) a beamformer decoder NN at the BS that maps recovered latent vectors to beamformers, and (iii) a channel decoder NN at the B…

Thinking While Listening: Simple Test Time Scaling For Audio Classification
Prateek Verma, Mert Pilanci
https://arxiv.org/abs/2509.19676 https://arxiv.org/…

Thinking While Listening: Simple Test Time Scaling For Audio Classification
We propose a framework that enables neural models to "think while listening" to everyday sounds, thereby enhancing audio classification performance. Motivated by recent advances in the reasoning capabilities of large language models, we address two central questions: (i) how can thinking be incorporated into existing audio classification pipelines to enable reasoning in the category space and improve performance, and (ii) can a new architecture be designed from the ground up to support both thi…

Chinese ModernBERT with Whole-Word Masking
Zeyu Zhao, Ningtao Wang, Xing Fu, Yu Cheng
https://arxiv.org/abs/2510.12285 https://arxiv.org/pdf/2510.12285

Chinese ModernBERT with Whole-Word Masking
Encoder-only Transformers have advanced along three axes -- architecture, data, and systems -- yielding Pareto gains in accuracy, speed, and memory efficiency. Yet these improvements have not fully transferred to Chinese, where tokenization and morphology differ markedly from English. We introduce Chinese ModernBERT, a from-scratch Chinese encoder that couples: (i) a hardware-aware 32k BPE vocabulary tailored to frequent Chinese affixes/compounds, lowering the embedding budget; (ii) whole-word …

TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edge
Zhirui Huang, Rui Ma, Shijie Cao, Ran Shu, Ian Wang, Ting Cao, Chixiao Chen, Yongqiang Xiong
https://arxiv.org/abs/2509.13765

TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edge
Ternary quantization has emerged as a powerful technique for reducing both computational and memory footprint of large language models (LLM), enabling efficient real-time inference deployment without significantly compromising model accuracy. Conventional LLM inference platforms (e.g GPUs) cannot capitalize on its benefits, as they (i) lack native support for ternary arithmetic and memory specialization and (ii) remain severely under-utilized in low-batch, real-time scenarios. In this work, we …

Constrained Sensing and Reliable State Estimation with Shallow Recurrent Decoders on a TRIGA Mark II Reactor
Stefano Riva, Carolina Introini, Jos\`e Nathan Kutz, Antonio Cammi
https://arxiv.org/abs/2510.12368

Constrained Sensing and Reliable State Estimation with Shallow Recurrent Decoders on a TRIGA Mark II Reactor
Shallow Recurrent Decoder networks are a novel data-driven methodology able to provide accurate state estimation in engineering systems, such as nuclear reactors. This deep learning architecture is a robust technique designed to map the temporal trajectories of a few sparse measures to the full state space, including unobservable fields, which is agnostic to sensor positions and able to handle noisy data through an ensemble strategy, leveraging the short training times and without the need for …

Instant prediction of relaxation in moir\'{e} superlattices using neural networks
Aleksei V. Belonovskii, Elizaveta I. Girshova, Erkki L\"ahderanta, Mikhail Kaliteevski
https://arxiv.org/abs/2509.13147

Instant prediction of relaxation in moiré superlattices using neural networks
The relaxation of moiré superlattices in twisted bilayers of transition metal dichalcogenides (TMDs) has been modeled using a set of neural-network-based approaches. We implemented and compared several architectures, including (i) an interpolator combined with an autoencoder, (ii) an interpolator combined with a decoder, (iii) a direct generator mapping input parameters to displacement fields, and (iv) a physics-informed neural network (PINN). Among these, the direct generator architecture dem…