97 citations · 267 across the 10 of their papers we have counts for
11 papers
KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks
Lorenz K. Muller, Philippe Bich, Chiara Boretti +3
Test-time scaling is a powerful approach to obtain better reasoning in large language models, but it becomes memory-bottlenecked during long-horizon decoding, as the KV-cache grows…
SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights
Lorenz K. Müller, Philippe Bich, Jiawei Zhuang +3
Post-training quantization has emerged as the most widely used strategy for deploying large language models at low precision. Still, current methods show perplexity degradation at…
SSSD: Simply-Scalable Speculative Decoding
Michele Marzollo, Jiawei Zhuang, Niklas Roemer +3
Speculative Decoding has emerged as a popular technique for accelerating inference in Large Language Models. However, most existing approaches yield only modest improvements in pro…
RL-based Stateful Neural Adaptive Sampling and Denoising for Real-Time Path Tracing
Antoine Scardigli, Lukas Cavigelli, Lorenz K. Müller
Monte-Carlo path tracing is a powerful technique for realistic image synthesis but suffers from high levels of noise at low sample counts, limiting its use in real-time application…
Overparametrization of HyperNetworks at Fixed FLOP-Count Enables Fast Neural Image Enhancement
Lorenz K. Muller
Deep convolutional neural networks can enhance images taken with small mobile camera sensors and excel at tasks like demoisaicing, denoising and super-resolution. However, for prac…
A neuromorphic systems approach to in-memory computing with non-ideal memristive devices: From mitigation to exploitation
Melika Payvand, Manu V Nair, Lorenz K. Muller +1
Memristive devices represent a promising technology for building neuromorphic electronic systems. In addition to their compactness and non-volatility features, they are characteriz…
A differential memristive synapse circuit for on-line learning in neuromorphic computing systems
Manu V Nair, Lorenz K. Muller, Giacomo Indiveri
Spike-based learning with memristive devices in neuromorphic computing architectures typically uses learning circuits that require overlapping pulses from pre- and post-synaptic no…
Neural Sampling by Irregular Gating Inhibition of Spiking Neurons and Attractor Networks
Lorenz K. Muller, Giacomo Indiveri
A long tradition in theoretical neuroscience casts sensory processing in the brain as the process of inferring the maximally consistent interpretations of imperfect sensory input.…
An event-based architecture for solving constraint satisfaction problems
Hesham Mostafa, Lorenz K. Müller, Giacomo Indiveri
Constraint satisfaction problems (CSPs) are typically solved using conventional von Neumann computing architectures. However, these architectures do not reflect the distributed nat…
Rounding Methods for Neural Networks with Low Resolution Synaptic Weights
Lorenz K. Muller, Giacomo Indiveri
Neural network algorithms simulated on standard computing platforms typically make use of high resolution weights, with floating-point notation. However, for dedicated hardware imp…
Rhythmic inhibition allows neural networks to search for maximally consistent states
Hesham Mostafa, Lorenz K. Muller, Giacomo Indiveri
Gamma-band rhythmic inhibition is a ubiquitous phenomenon in neural circuits yet its computational role still remains elusive. We show that a model of Gamma-band rhythmic inhibitio…