Matthijs Van Keirsbilck

Fayçal Aït Aoudia, Jakob Hoydis, Sebastian Cammerer et al.

We propose a neural network (NN)-based algorithm for device detection and time of arrival (ToA) and carrier frequency offset (CFO) estimation for the narrowband physical random-access channel (NPRACH) of narrowband internet of things (NB-IoT). The introduced NN architecture leverages residual convolutional networks as well as knowledge of the preamble structure of the 5G New Radio (5G NR) specifications. Benchmarking on a 3rd Generation Partnership Project (3GPP) urban microcell (UMi) channel model with random drops of users against a state-of-the-art baseline shows that the proposed method enables up to 8 dB gains in false negative rate (FNR) as well as significant gains in false positive rate (FPR) and ToA and CFO estimation accuracy. Moreover, our simulations indicate that the proposed algorithm enables gains over a wide range of channel conditions, CFOs, and transmission probabilities. The introduced synchronization method operates at the base station (BS) and, therefore, introduces no additional complexity on the user devices. It could lead to an extension of battery lifetime by reducing the preamble length or the transmit power. Our code is available at: https://github.com/NVlabs/nprach_synch/.

Xin Dong, Yonggan Fu, Shizhe Diao et al.

We propose Hymba, a family of small language models featuring a hybrid-head parallel architecture that integrates transformer attention mechanisms with state space models (SSMs) for enhanced efficiency. Attention heads provide high-resolution recall, while SSM heads enable efficient context summarization. Additionally, we introduce learnable meta tokens that are prepended to prompts, storing critical information and alleviating the "forced-to-attend" burden associated with attention mechanisms. This model is further optimized by incorporating cross-layer key-value (KV) sharing and partial sliding window attention, resulting in a compact cache size. During development, we conducted a controlled study comparing various architectures under identical settings and observed significant advantages of our proposed architecture. Notably, Hymba achieves state-of-the-art results for small LMs: Our Hymba-1.5B-Base model surpasses all sub-2B public models in performance and even outperforms Llama-3.2-3B with 1.32% higher average accuracy, an 11.67x cache size reduction, and 3.49x throughput.

Yonggan Fu, Xin Dong, Shizhe Diao et al.

Efficient deployment of small language models (SLMs) is essential for numerous real-world applications with stringent latency constraints. While previous work on SLM design has primarily focused on reducing the number of parameters to achieve parameter-optimal SLMs, parameter efficiency does not necessarily translate into proportional real-device speed-ups. This work aims to identify the key determinants of SLMs' real-device latency and offer generalizable principles and methodologies for SLM design and training when real-device latency is the primary consideration. Specifically, we identify two central architectural factors: depth-width ratios and operator choices. The former is crucial for small-batch-size latency, while the latter affects both latency and large-batch-size throughput. In light of this, we first study latency-optimal depth-width ratios, with the key finding that although deep-thin models generally achieve better accuracy under the same parameter budget, they may not lie on the accuracy-latency trade-off frontier. Next, we explore emerging efficient attention alternatives to evaluate their potential as candidate building operators. Using the identified promising operators, we construct an evolutionary search framework to automatically discover latency-optimal combinations of these operators within hybrid SLMs, thereby advancing the accuracy-latency frontier. In addition to architectural improvements, we further enhance SLM training using a weight normalization technique that enables more effective weight updates and improves final convergence. Combining these methods, we introduce a new family of hybrid SLMs, called Nemotron-Flash, which significantly advances the accuracy-efficiency frontier of state-of-the-art SLMs, e.g., achieving over +5.5% average accuracy, 1.3x/1.9x lower latency, and 18.7x/45.6x higher throughput compared to Qwen3-1.7B/0.6B, respectively.

Gonçalo Mordido, Matthijs Van Keirsbilck, Alexander Keller

We demonstrate that 1x1-convolutions in 1D time-channel separable convolutions may be replaced by constant, sparse random ternary matrices with weights in $\{-1,0,+1\}$. Such layers do not perform any multiplications and do not require training. Moreover, the matrices may be generated on the chip during computation and therefore do not require any memory access. With the same parameter budget, we can afford deeper and more expressive models, improving the Pareto frontiers of existing models on several tasks. For command recognition on Google Speech Commands v1, we improve the state-of-the-art accuracy from $97.21\%$ to $97.41\%$ at the same network size. Alternatively, we can lower the cost of existing models. For speech recognition on Librispeech, we half the number of weights to be trained while only sacrificing about $1\%$ of the floating-point baseline's word error rate.

Alexander Keller, Matthijs Van keirsbilck

Artificial neural networks can be represented by paths. Generated as random walks on a dense network graph, we find that the resulting sparse networks allow for deterministic initialization and even weights with fixed sign. Such networks can be trained sparse from scratch, avoiding the expensive procedure of training a dense network and compressing it afterwards. Although sparse, weights are accessed as contiguous blocks of memory. In addition, enumerating the paths using deterministic low discrepancy sequences, for example the Sobol' sequence, amounts to connecting the layers of neural units by progressive permutations, which naturally avoids bank conflicts in parallel computer hardware. We demonstrate that the artificial neural networks generated by low discrepancy sequences can achieve an accuracy within reach of their dense counterparts at a much lower computational complexity.

Matthijs Van Keirsbilck, Alexander Keller, Xiaodong Yang

Recurrent neural networks (RNNs) are omnipresent in sequence modeling tasks. Practical models usually consist of several layers of hundreds or thousands of neurons which are fully connected. This places a heavy computational and memory burden on hardware, restricting adoption in practical low-cost and low-power devices. Compared to fully convolutional models, the costly sequential operation of RNNs severely hinders performance on parallel hardware. This paper challenges the convention of full connectivity in RNNs. We study structurally sparse RNNs, showing that they are well suited for acceleration on parallel hardware, with a greatly reduced cost of the recurrent operations as well as orders of magnitude less recurrent weights. Extensive experiments on challenging tasks ranging from language modeling and speech recognition to video action recognition reveal that structurally sparse RNNs achieve competitive performance as compared to fully-connected networks. This allows for using large sparse RNNs for a wide range of real-world tasks that previously were too costly with fully connected networks.

Gonçalo Mordido, Matthijs Van Keirsbilck, Alexander Keller

Low bit-width integer weights and activations are very important for efficient inference, especially with respect to lower power consumption. We propose Monte Carlo methods to quantize the weights and activations of pre-trained neural networks without any re-training. By performing importance sampling we obtain quantized low bit-width integer values from full-precision weights and activations. The precision, sparsity, and complexity are easily configurable by the amount of sampling performed. Our approach, called Monte Carlo Quantization (MCQ), is linear in both time and space, with the resulting quantized, sparse networks showing minimal accuracy loss when compared to the original full-precision networks. Our method either outperforms or achieves competitive results on multiple benchmarks compared to previous quantization methods that do require additional training.

Matthijs Van keirsbilck, Bert Moons, Marian Verhelst

Today's Automatic Speech Recognition systems only rely on acoustic signals and often don't perform well under noisy conditions. Performing multi-modal speech recognition - processing acoustic speech signals and lip-reading video simultaneously - significantly enhances the performance of such systems, especially in noisy environments. This work presents the design of such an audio-visual system for Automated Speech Recognition, taking memory and computation requirements into account. First, a Long-Short-Term-Memory neural network for acoustic speech recognition is designed. Second, Convolutional Neural Networks are used to model lip-reading features. These are combined with an LSTM network to model temporal dependencies and perform automatic lip-reading on video. Finally, acoustic-speech and visual lip-reading networks are combined to process acoustic and visual features simultaneously. An attention mechanism ensures performance of the model in noisy environments. This system is evaluated on the TCD-TIMIT 'lipspeaker' dataset for audio-visual phoneme recognition with clean audio and with additive white noise at an SNR of 0dB. It achieves 75.70% and 58.55% phoneme accuracy respectively, over 14 percentage points better than the state-of-the-art for all noise levels.