Related papers: Boost Test-Time Performance with Closed-Loop Infer…
In-context learning (ICL) refers to the process of adding a small number of localized examples from a training set of labelled data to an LLM's prompt with an objective to effectively control the generative process seeking to improve the…
To improve deep-learning performance in low-resource settings, many researchers have redesigned model architectures or applied additional data (e.g., external resources, unlabeled samples). However, there have been relatively few…
While Deep Learning (DL) technologies are a promising tool to solve networking problems that map to classification tasks, their computational complexity is still too high with respect to real-time traffic measurements requirements. To…
Test-time compute scaling is a primary axis for improving LLM reasoning. Existing methods primarily scale depth by extending a single reasoning trace. Scaling breadth by sampling multiple candidates in parallel is straightforward, but…
Diffusion distillation models effectively accelerate reverse sampling by compressing the process into fewer steps. However, these models still exhibit a performance gap compared to their pre-trained diffusion model counterparts, exacerbated…
Instruction tuning increasingly relies on LLM-based prompt refinement, where prompts in the training corpus are selectively rewritten by an external refiner to improve clarity and instruction alignment. This motivates an instance-level…
Consider a multi-class labelling problem, where the labels can take values in $[k]$, and a predictor predicts a distribution over the labels. In this work, we study the following foundational question: Are there notions of multi-class…
Large Language Models (LLMs) often rely on test-time scaling via parallel decoding (for example, 512 samples) to boost reasoning accuracy, but this incurs substantial compute. We introduce CoRefine, a confidence-guided self-refinement…
We propose a novel sample selection method for image classification in the presence of noisy labels. Existing methods typically consider small-loss samples as correctly labeled. However, some correctly labeled samples are inherently…
Large Language Models (LLMs) have recently gained the In-Context Learning (ICL) ability with the models scaling up, allowing them to quickly adapt to downstream tasks with only a few demonstration examples prepended in the input sequence.…
We consider the task of performing probabilistic inference with probabilistic logical models. Many algorithms for approximate inference with such models are based on sampling. From a logic programming perspective, sampling boils down to…
Classifier-guided diffusion models generate conditional samples by augmenting the reverse-time score with the gradient of the log-probability predicted by a probabilistic classifier. In practice, this classifier is usually obtained by…
In-Context Learning (ICL) enhances the performance of large language models (LLMs) with demonstrations. However, obtaining these demonstrations primarily relies on manual effort. In most real-world scenarios, users are often unwilling or…
In this work, we introduce a novel paradigm for generalized In-Context Learning (ICL), termed Indirect In-Context Learning. In Indirect ICL, we explore demonstration selection strategies tailored for two distinct real-world scenarios:…
Software developers frequently reuse source code from repositories as it saves development time and effort. Code clones accumulated in these repositories hence represent often repeated functionalities and are candidates for reuse in an…
Mechanism-targeted synthetic data is increasingly proposed as a way to steer pretraining toward desirable capabilities, but it remains unclear how such interventions should be evaluated. We study this question for in-context learning (ICL)…
Massive, multi-language, monolithic repositories form the backbone of many modern, complex software systems. To ensure consistent code quality while still allowing fast development cycles, Continuous Integration (CI) is commonly applied.…
Many active learning methods belong to the retraining-based approaches, which select one unlabeled instance, add it to the training set with its possible labels, retrain the classification model, and evaluate the criteria that we base our…
Inference for high-dimensional logistic regression models using penalized methods has been a challenging research problem. As an illustration, a major difficulty is the significant bias of the Lasso estimator, which limits its direct…
The reasoning ability of large language models (LLMs) can be unleashed with reinforcement learning (RL) (OpenAI, 2024; DeepSeek-AI et al., 2025a; Zeng et al., 2025). The success of existing RL attempts in LLMs usually rely on high-quality…