Related papers: Automata Learning with an Incomplete but Inductive…

Vision-Language-Action (VLA) models rely on current observations, including images, language instructions, and robot states, to predict actions and complete tasks. While accurate visual perception is crucial for precise action prediction…

Analyzing the reasoning patterns of students in science classrooms is critical for understanding knowledge construction mechanism and improving instructional practice to maximize cognitive engagement, yet manual coding of classroom…

A major problem with Active Learning (AL) is high training costs since models are typically retrained from scratch after every query round. We start by demonstrating that standard AL on neural networks with warm starting fails, both to…

There is an increasing interest in applying recent advances in AI to automated reasoning, as it may provide useful heuristics in reasoning over formalisms in first-order, second-order, or even meta-logics. To facilitate this research, we…

Active learning of timed languages is concerned with the inference of timed automata from observed timed words. The agent can query for the membership of words in the target language, or propose a candidate model and verify its equivalence…

Multimodal learning often encounters the under-optimized problem and may perform worse than unimodal learning. Existing approaches attribute this issue to imbalanced learning across modalities and tend to address it through gradient…

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…

There are various types of disability egress in world like blindness, deafness, and Physical disabilities. It is quite difficult to deal with people with disability. Learning disability (LD) is types of disability totally different from…

In this paper we present ISA, an approach for learning and exploiting subgoals in episodic reinforcement learning (RL) tasks. ISA interleaves reinforcement learning with the induction of a subgoal automaton, an automaton whose edges are…

Large Audio Language Models (LALMs) excel at perception but struggle with complex reasoning requiring precise acoustic measurements. While external tools can extract fine-grained features like exact tempo or pitch, effective integration…

Semi-supervised medical image segmentation studies have shown promise in training models with limited labeled data. However, current dominant teacher-student based approaches can suffer from the confirmation bias. To address this challenge,…

Adapting large language models (LLMs) to specialized financial reasoning typically requires expensive fine-tuning that produces model-locked expertise. Training-free alternatives have emerged, yet our experiments show that leading methods…

Large language models (LLMs) have demonstrated strong performance on formal language tasks, yet whether this reflects genuine symbolic reasoning or pattern matching on familiar constructions remains unclear. We introduce a benchmark for…

Model-agnostic meta-learning (MAML) is a meta-learning technique to train a model on a multitude of learning tasks in a way that primes the model for few-shot learning of new tasks. The MAML algorithm performs well on few-shot learning…

We present an extended automata learning framework that combines active automata learning with deductive inference. The learning algorithm asks membership and equivalence queries as in the original framework, but it is also given advice,…

Active Learning (AL) is a family of machine learning (ML) algorithms that predates the current era of artificial intelligence. Unlike traditional approaches that require labeled samples for training, AL iteratively selects unlabeled samples…

In this paper, we proposed to apply meta learning approach for low-resource automatic speech recognition (ASR). We formulated ASR for different languages as different tasks, and meta-learned the initialization parameters from many…

Large Language Models (LLMs) are increasingly used in Spoken Language Understanding (SLU), where effective multimodal learning depends on the alignment between audio and text. Despite various fusion methods, no standard metric exists to…

We propose DFAMiner, a passive learning tool for learning minimal separating deterministic finite automata (DFA) from a set of labelled samples. Separating automata are an interesting class of automata that occurs generally in regular model…

Supervised fine-tuning (SFT) on visual instruction data often improves perceptual capabilities in vision-language models (VLMs) while degrading reasoning performance, creating a persistent reasoning tax during post-training. We investigate…