74 citations · 448 across the 40 of their papers we have counts for
43 papers
WorldCast: Exploring Intelligent Visual Generation in World State Prediction
Wenhao Yan, Haodong Li, Xiaotong Li +9
Humans interpret multimodal observations of the world and forecast how it will evolve. Recent multimodal generative systems have demonstrated similar capabilities: they can integra…
APEX4: Efficient Pure W4A4 LLM Inference via Intra-SM Compute Rebalancing
Hong Guo, Nianhui Guo, Weixing Wang +3
W4A4 quantization promises full utilization of INT4 Tensor Cores, yet group dequantization overhead on CUDA Cores has driven existing systems to mixed-precision fallbacks. We prese…
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…
Harmonizing Dense and Sparse Signals in Multi-turn RL: Dual-Horizon Credit Assignment for Industrial Sales Agents
Haojin Yang, Ai Jian, Xinyue Huang +5
Optimizing large language models for industrial sales requires balancing long-term commercial objectives (e.g., conversion rate) with immediate linguistic constraints such as fluen…
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…
Image Tokens Matter: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing
Weixing Wang, Zifeng Ding, Jindong Gu +4
Large Vision-Language Models (LVLMs) with discrete image tokenizers unify multimodal representations by encoding visual inputs into a finite set of tokens. Despite their effectiven…
Data Pruning Can Do More: A Comprehensive Data Pruning Approach for Object Re-identification
Zi Yang, Haojin Yang, Soumajit Majumder +2
Previous studies have demonstrated that not each sample in a dataset is of equal importance during training. Data pruning aims to remove less important or informative samples while…
SeCoKD: Aligning Large Language Models for In-Context Learning with Fewer Shots
Weixing Wang, Haojin Yang, Christoph Meinel
Previous studies have shown that demonstrations can significantly help Large Language Models (LLMs ) perform better on the given tasks. However, this so-called In-Context Learning…
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…
Generalized Categories Discovery for Long-tailed Recognition
Ziyun Li, Christoph Meinel, Haojin Yang
Generalized Class Discovery (GCD) plays a pivotal role in discerning both known and unknown categories from unlabeled datasets by harnessing the insights derived from a labeled set…
ImbaGCD: Imbalanced Generalized Category Discovery
Ziyun Li, Ben Dai, Furkan Simsek +2
Generalized class discovery (GCD) aims to infer known and unknown categories in an unlabeled dataset leveraging prior knowledge of a labeled set comprising known classes. Existing…
Scaled Prompt-Tuning for Few-Shot Natural Language Generation
Ting Hu, Christoph Meinel, Haojin Yang
The increasingly Large Language Models (LLMs) demonstrate stronger language understanding and generation capabilities, while the memory demand and computation cost of fine-tuning L…
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…
DocLangID: Improving Few-Shot Training to Identify the Language of Historical Documents
Furkan Simsek, Brian Pfitzmann, Hendrik Raetz +3
Language identification describes the task of recognizing the language of written text in documents. This information is crucial because it can be used to support the analysis of a…
Join the High Accuracy Club on ImageNet with A Binary Neural Network Ticket
Nianhui Guo, Joseph Bethge, Christoph Meinel +1
Binary neural networks are the extreme case of network quantization, which has long been thought of as a potential edge machine learning solution. However, the significant accuracy…
Empirical Evaluation of Post-Training Quantization Methods for Language Tasks
Ting Hu, Christoph Meinel, Haojin Yang
Transformer-based architectures like BERT have achieved great success in a wide range of Natural Language tasks. Despite their decent performance, the models still have numerous pa…
A Closer Look at Novel Class Discovery from the Labeled Set
Ziyun Li, Jona Otholt, Ben Dai +3
Novel class discovery (NCD) aims to infer novel categories in an unlabeled dataset leveraging prior knowledge of a labeled set comprising disjoint but related classes. Existing res…
Synthesis in Style: Semantic Segmentation of Historical Documents using Synthetic Data
Christian Bartz, Hendrik Raetz, Jona Otholt +2
One of the most pressing problems in the automated analysis of historical documents is the availability of annotated training data. The problem is that labeling samples is a time-c…
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…
AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecks
Haojin Yang, Zhen Shen, Yucheng Zhao
Deep convolutional neural networks (CNN) have achieved astonishing results in a large variety of applications. However, using these models on mobile or embedded devices is difficul…
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…
One Model to Reconstruct Them All: A Novel Way to Use the Stochastic Noise in StyleGAN
Christian Bartz, Joseph Bethge, Haojin Yang +1
Generative Adversarial Networks (GANs) have achieved state-of-the-art performance for several image generation and manipulation tasks. Different works have improved the limited und…