Related papers: You Only Evaluate Once: A Tree-based Rerank Method…

Modern recommender systems perform large-scale retrieval by first embedding queries and item candidates in the same unified space, followed by approximate nearest neighbor search to select top candidates given a query embedding. In this…

Dialog response ranking is used to rank response candidates by considering their relation to the dialog history. Although researchers have addressed this concept for open-domain dialogs, little attention has been focused on task-oriented…

Generative recommendation has recently emerged as a promising paradigm in information retrieval. However, generative ranking systems are still understudied, particularly with respect to their effectiveness and feasibility in large-scale…

The objective of this research is to optimize the eleventh iteration of You Only Look Once (YOLOv11) by developing size-specific modified versions of the architecture. These modifications involve pruning unnecessary layers and reconfiguring…

Recent advances in path-based explainable recommendation systems have attracted increasing attention thanks to the rich information provided by knowledge graphs. Most existing explainable recommendations only utilize static knowledge graphs…

Although deep learning has demonstrated remarkable capability in learning from unstructured data, modern tree-based ensemble models remain superior in extracting relevant information and learning from structured datasets. While several…

Decision trees are a commonly used class of machine learning models valued for their interpretability and versatility, capable of both classification and regression. We propose ZTree, a novel decision tree learning framework that replaces…

The usage of neural network models puts multiple objectives in conflict with each other: Ideally we would like to create a neural model that is effective, efficient, and interpretable at the same time. However, in most instances we have to…

Class Incremental Learning (CIL) is inspired by the human ability to learn new classes without forgetting previous ones. CIL becomes more challenging in real-world scenarios when the samples in each incremental step are imbalanced. This…

Integrating large language models (LLMs) into closed-loop robotic task planning has become increasingly popular within embodied artificial intelligence. Previous efforts mainly focused on leveraging the strong reasoning abilities of LLMs to…

Industrial systems such as recommender systems and online advertising, have been widely equipped with multi-stage architectures, which are divided into several cascaded modules, including matching, pre-ranking, ranking and re-ranking. As a…

Low-Rank Adaptation (LoRA) has emerged as one of the most widely used parameter-efficient fine-tuning (PEFT) methods for adapting large language models (LLMs) to downstream tasks. While highly effective in single-task settings, it struggles…

Test-time reinforcement learning generates multiple candidate answers via repeated rollouts and performs online updates using pseudo-labels constructed by majority voting. To reduce overhead and improve exploration, prior work introduces…

Parameter-efficient fine-tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA), offer an efficient way to adapt large language models with reduced computational costs. However, their performance is limited by the small number of…

Modern large-scale ranking systems operate within a sophisticated landscape of competing objectives, operational constraints, and evolving product requirements. Progress in this domain is increasingly bottlenecked by the engineering context…

Recent advancements in large language models (LLMs) have highlighted their potential across a variety of tasks, but their performance still heavily relies on the design of effective prompts. Existing methods for automatic prompt…

We introduce E3Solver, a unification-based solver for programming-by-example (PBE) participating in the 2017 edition of the SyGuS Competition. Our tool proceeds in two phases. First, for each individual example, we enumerate a terminal…

Retrieval in Retrieval-Augmented Generation(RAG) must ensure that retrieved passages are not only individually relevant but also collectively form a comprehensive set. Existing approaches primarily rerank top-k passages based on their…

Reinforcement learning with verifiable rewards (RLVR) has proven effective in enhancing the reasoning of large language models (LLMs). Monte Carlo Tree Search (MCTS)-based extensions improve upon vanilla RLVR (e.g., GRPO) by providing…

Occlusions pose a significant challenge to optical flow algorithms that even rely on global evidences. We consider an occluded point to be one that is imaged in the reference frame but not in the next. Estimating the motion of these points…