Related papers: LINC: Decoupling Local Consequence Scoring from Hi…
Large language models (LLMs) are typically governed by post-training alignment (e.g., RLHF or DPO), which yields a largely static policy during deployment and inference. However, real-world safety is a full-lifecycle problem: static…
Click-Through Rate (CTR) prediction, a core task in recommendation systems, estimates user click likelihood using historical behavioral data. Modeling user behavior sequences as text to leverage Language Models (LMs) for this task has…
This paper concerns a deep learning approach to relevance ranking in information retrieval (IR). Existing deep IR models such as DSSM and CDSSM directly apply neural networks to generate ranking scores, without explicit understandings of…
Multimodal Large Language Models (MLLMs) have achieved impressive results on vision-language benchmarks, yet it remains unclear whether these benchmarks assess genuine global reasoning or allow success via localized visual cues. Existing…
Dual decomposition provides a tractable framework for designing algorithms for finding the most probable (MAP) configuration in graphical models. However, for many real-world inference problems, the typical decomposition has a large…
HPC systems expose many configuration parameters that jointly drive competing objectives. Existing tools such as autotuners recommend good configurations but do not identify minimal changes for a near-miss configuration to meet a…
The latent representation in learned image compression encompasses channel-wise, local spatial, and global spatial correlations, which are essential for the entropy model to capture for conditional entropy minimization. Efficiently…
In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile. Our analysis reveals that the fundamental limitation lies in an inductive gap, models…
This paper introduces a new approach to improve the performance of the Capacitated Vehicle Routing Problem with Time Windows (CVRPTW) solvers for a high number of nodes. It proposes to cluster nodes together using Recursive-DBSCAN - an…
Learning-to-rank (LTR) algorithms are ubiquitous and necessary to explore the extensive catalogs of media providers. To avoid the user examining all the results, its preferences are used to provide a subset of relatively small size. The…
Existing neural constructive solvers for routing problems have predominantly employed transformer architectures, conceptualizing the route construction as a set-to-sequence learning task. However, their efficacy has primarily been…
Automated requirements assessment traditionally relies on universal patterns as proxies for defectiveness, implemented through rule-based heuristics or machine learning classifiers trained on large annotated datasets. However, what…
Combinatorial optimization has found applications in numerous fields, from aerospace to transportation planning and economics. The goal is to find an optimal solution among a finite set of possibilities. The well-known challenge one faces…
Recent progress has shown that large-scale pre-training using contrastive image-text pairs can be a promising alternative for high-quality visual representation learning from natural language supervision. Benefiting from a broader source of…
Deep reinforcement learning has enabled human-level or even super-human performance in various types of games. However, the amount of exploration required for learning is often quite large. Deep reinforcement learning also has super-human…
Model checkers and consistency checkers detect critical errors in router configurations, but these tools require significant manual effort to develop and maintain. LLM-based Q&A models have emerged as a promising alternative, allowing users…
Existing website fingerprinting and traffic classification solutions do not work well when the evaluation context changes, as their performances often heavily rely on context-specific assumptions. To clarify this problem, we take three…
Large vision-language contrastive models (VLCMs), such as CLIP, have become foundational, demonstrating remarkable success across a variety of downstream tasks. Despite their advantages, these models, akin to other foundational systems,…
In this article we compare the performances of a logistic regression and a feed forward neural network for credit scoring purposes. Our results show that the logistic regression gives quite good results on the dataset and the neural network…
Recent work has demonstrated the effectiveness of formulating decision making as supervised learning on offline-collected trajectories. Powerful sequence models, such as GPT or BERT, are often employed to encode the trajectories. However,…