Related papers: Introducing SKYSET - a Quintuple Approach for Impr…
A system of nested dichotomies is a method of decomposing a multi-class problem into a collection of binary problems. Such a system recursively applies binary splits to divide the set of classes into two subsets, and trains a binary…
We propose UniSeg3D, a unified 3D scene understanding framework that achieves panoptic, semantic, instance, interactive, referring, and open-vocabulary segmentation tasks within a single model. Most previous 3D segmentation approaches are…
Curriculum learning strategies in prior multi-task learning approaches arrange datasets in a difficulty hierarchy either based on human perception or by exhaustively searching the optimal arrangement. However, human perception of difficulty…
Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model. Previous KD methods typically train a student by minimizing a task-related loss and…
Knowledge tracing (KT) in programming education presents unique challenges due to the complexity of coding tasks and the diverse methods students use to solve problems. Although students' questions often contain valuable signals about their…
Machine comprehension of text is an important problem in natural language processing. A recently released dataset, the Stanford Question Answering Dataset (SQuAD), offers a large number of real questions and their answers created by humans…
Fine-grained Entity Typing is a tough task which suffers from noise samples extracted from distant supervision. Thousands of manually annotated samples can achieve greater performance than millions of samples generated by the previous…
Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents…
Existing text-driven infrared and visible image fusion approaches often rely on textual information at the sentence level, which can lead to semantic noise from redundant text and fail to fully exploit the deeper semantic value of textual…
Stripe-like space target detection (SSTD) plays a key role in enhancing space situational awareness and assessing spacecraft behaviour. This domain faces three challenges: the lack of publicly available datasets, interference from stray…
Search engines are considered the primary tool to assist and empower learners in finding information relevant to their learning goals-be it learning something new, improving their existing skills, or just fulfilling a curiosity. While…
Large language models (LLMs) now perform strongly on many public math suites, yet frontier separation within mathematics increasingly suffers from ceiling effects. We present two complementary benchmarks: SKYLENAGE-ReasoningMATH, a…
While scientists increasingly recognize the importance of metadata in describing their data, spreadsheets remain the preferred tool for supplying this information despite their limitations in ensuring compliance and quality. Various tools…
Large multimodal language models (MLLMs) have revolutionized natural language processing and visual understanding, but often contain outdated or inaccurate information. Current multimodal knowledge editing evaluations are limited in scope…
Knowledge distillation (KD) transfers knowledge from large teacher models to compact student models, enabling efficient deployment on resource constrained devices. While diverse KD methods, including response based, feature based, and…
Text segmentation is a fundamental task in natural language processing, where documents are split into contiguous sections. However, prior research in this area has been constrained by limited datasets, which are either small in scale,…
We introduce a new paradigm of learning for reasoning, understanding, and prediction, as well as the scaffolding network to implement this paradigm. The scaffolding network embodies an incremental learning approach that is formulated as a…
We report on novel investigations into training models that make sentences concise. We define the task and show that it is different from related tasks such as summarization and simplification. For evaluation, we release two test sets,…
Cross-lingual Text Classification (CLC) consists of automatically classifying, according to a common set C of classes, documents each written in one of a set of languages L, and doing so more accurately than when naively classifying each…
We propose the new task of K principal concept identification for dataset summarizarion. The objective is to find a set of K concepts that best explain the variation within the dataset. Concepts are high-level human interpretable terms such…