Related papers: A Novel Token-Based Replay Technique to Speed Up C…
This study investigates the performance of the DeepSeek R1 language model on 30 challenging mathematical problems derived from the MATH dataset, problems that previously proved unsolvable by other models under time constraints. Unlike prior…
Scientific workflows have been predominantly used for complex and large scale data analysis and scientific computation/automation and the need for robust workflow scheduling techniques has grown considerably. But, most of the existing…
Long traces and large event logs that originate from sensors and prediction models are becoming more common in our data-rich world. In such circumstances, conformance checking, a key task in process mining, can become computationally…
Since traditional tokenizers are isolated from a downstream task and model, they cannot output an appropriate tokenization depending on the task and model, although recent studies imply that the appropriate tokenization improves the…
Diffusion Language Models (DLMs) decode multiple tokens in parallel, but aggressive multi-token decoding amplifies cross-token dependency errors and can sharply degrade generation quality. We propose BackPlay, a frozen-backbone…
Despite growing interest in process analysis and mining for data-aware specifications, alignment-based conformance checking for declarative process models has focused on pure control-flow specifications, or mild data-aware extensions…
Recent large language models have shown promising capabilities in long-form reasoning, following structured chains of thought before arriving at a final answer. However, we observe that these reasoning paths tend to include substantial…
Nowadays, GPU accelerators are commonly used to speed up general-purpose computing tasks on a variety of hardware. However, due to the diversity of GPU architectures and processed data, optimization of codes for a particular type of…
Transformers achieve state-of-the-art performance for natural language processing tasks by pre-training on large-scale text corpora. They are extremely compute-intensive and have very high sample complexity. Memory replay is a mechanism…
The subject of this paper is to study conformance checking for timed models, that is, process models that consider both the sequence of events in a process as well as the timestamps at which each event is recorded. Time-aware process mining…
Selecting the right compiler optimisations has a severe impact on programs' performance. Still, the available optimisations keep increasing, and their effect depends on the specific program, making the task human intractable. Researchers…
Advanced compiler technology is crucial for enabling machine learning applications to run on novel hardware, but traditional compilers fail to deliver performance, popular auto-tuners have long search times and expert-optimized libraries…
Process mining is a family of techniques that aim at analyzing business process execution data recorded in event logs. Conformance checking is a branch of this discipline embracing approaches for verifying whether the behavior of a process,…
Diffusion models excel in high-fidelity image generation but face scalability limits due to transformers' quadratic attention complexity. Plug-and-play token reduction methods like ToMeSD and ToFu reduce FLOPs by merging redundant tokens in…
Token-based transformer world models have shown strong performance in visual reinforcement learning, but often suffer from temporal inconsistency in long-horizon rollouts, including object duplication, disappearance, and transmutation. A…
Benchmarking functionalities in current commercial process mining tools allow organizations to contextualize their process performance through high-level performance indicators, such as completion rate or throughput time. However, they do…
Tokenization plays a critical role in language modeling, yet existing approaches such as Byte-Pair Encoding (BPE) or WordPiece operate purely on frequency statistics, ignoring the underlying semantic structure of text. This leads to…
We present fastrerandomize, an R package for fast, scalable rerandomization in experimental design. Rerandomization improves precision by discarding treatment assignments that fail a prespecified covariate-balance criterion, but existing…
Previous research on code intelligence usually trains a deep learning model on a fixed dataset in an offline manner. However, in real-world scenarios, new code repositories emerge incessantly, and the carried new knowledge is beneficial for…
Autoregressive decoding in language models is inherently slow, generating only one token per forward pass. We propose Parallel Token Prediction (PTP), a general-purpose framework for predicting multiple tokens in a single model call. PTP…