74 citations · 448 across the 40 of their papers we have counts for
15 papers · 1 filter
Sample Where You Struggle: Sharpening Base Model Reasoning via Entropy-Guided Power Sampling
Hong Guo, Nianhui Guo, Christoph Meinel +1
Sampling from the sequence-level power distribution elicits RL-level reasoning from base language models without any parameter updates, but the standard Metropolis--Hastings…
VADE: Variance-Aware Dynamic Sampling via Online Sample-Level Difficulty Estimation for Multimodal RL
Zengjie Hu, Jiantao Qiu, Tianyi Bai +5
Group-based policy optimization methods like GRPO and GSPO have become standard for training multimodal models, leveraging group-wise rollouts and relative advantage estimation. Ho…
WavefrontDiffusion: Dynamic Decoding Schedule for Improved Reasoning
Haojin Yang, Rui Hu, Zequn Sun +3
Diffusion Language Models (DLMs) have shown strong potential for text generation and are becoming a competitive alternative to autoregressive models. The denoising strategy plays a…
Feature Distribution Shift Mitigation with Contrastive Pretraining for Intrusion Detection
Weixing Wang, Haojin Yang, Christoph Meinel +3
In recent years, there has been a growing interest in using Machine Learning (ML), especially Deep Learning (DL) to solve Network Intrusion Detection (NID) problems. However, the f…
Supervised Knowledge May Hurt Novel Class Discovery Performance
Ziyun Li, Jona Otholt, Ben Dai +3
Novel class discovery (NCD) aims to infer novel categories in an unlabeled dataset by leveraging prior knowledge of a labeled set comprising disjoint but related classes. Given tha…
BoolNet: Minimizing The Energy Consumption of Binary Neural Networks
Nianhui Guo, Joseph Bethge, Haojin Yang +4
Recent works on Binary Neural Networks (BNNs) have made promising progress in narrowing the accuracy gap of BNNs to their 32-bit counterparts. However, the accuracy gains are often…
Not All Knowledge Is Created Equal: Mutual Distillation of Confident Knowledge
Ziyun Li, Xinshao Wang, Di Hu +4
Mutual knowledge distillation (MKD) improves a model by distilling knowledge from another model. However, \textit{not all knowledge is certain and correct}, especially under advers…
Evaluating Post-Training Compression in GANs using Locality-Sensitive Hashing
Gonçalo Mordido, Haojin Yang, Christoph Meinel
The analysis of the compression effects in generative adversarial networks (GANs) after training, i.e. without any fine-tuning, remains an unstudied, albeit important, topic with t…
microbatchGAN: Stimulating Diversity with Multi-Adversarial Discrimination
Gonçalo Mordido, Haojin Yang, Christoph Meinel
We propose to tackle the mode collapse problem in generative adversarial networks (GANs) by using multiple discriminators and assigning a different portion of each minibatch, calle…
MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?
Joseph Bethge, Christian Bartz, Haojin Yang +2
Binary Neural Networks (BNNs) are neural networks which use binary weights and activations instead of the typical 32-bit floating point values. They have reduced model sizes and al…
Back to Simplicity: How to Train Accurate BNNs from Scratch?
Joseph Bethge, Haojin Yang, Marvin Bornstein +1
Binary Neural Networks (BNNs) show promising progress in reducing computational and memory costs but suffer from substantial accuracy degradation compared to their real-valued coun…
Training Competitive Binary Neural Networks from Scratch
Joseph Bethge, Marvin Bornstein, Adrian Loy +2
Convolutional neural networks have achieved astonishing results in different application areas. Various methods that allow us to use these models on mobile and embedded devices hav…
Learning to Train a Binary Neural Network
Joseph Bethge, Haojin Yang, Christian Bartz +1
Convolutional neural networks have achieved astonishing results in different application areas. Various methods which allow us to use these models on mobile and embedded devices ha…
Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators
Gonçalo Mordido, Haojin Yang, Christoph Meinel
We propose to incorporate adversarial dropout in generative multi-adversarial networks, by omitting or dropping out, the feedback of each discriminator in the framework with some p…
BMXNet: An Open-Source Binary Neural Network Implementation Based on MXNet
Haojin Yang, Martin Fritzsche, Christian Bartz +1
Binary Neural Networks (BNNs) can drastically reduce memory size and accesses by applying bit-wise operations instead of standard arithmetic operations. Therefore it could signific…