Related papers: Training-Free Time Series Classification via In-Co…

This work studies the problem of time series analysis with generalist (or foundation) models, which are models trained across many data domains. Drawing inspiration from the widespread success of large language models, we consider the…

While transformer-based Large Language Models (LLMs) theoretically support massive context windows, they suffer from severe performance degradation when processing long numerical sequences. We attribute this failure to the attention…

While vision-language-action (VLA) models for embodied agents integrate perception, reasoning, and control, they remain constrained by two critical weaknesses: first, during grasping tasks, the action tokens generated by the language model…

Large language models (LLMs) have demonstrated remarkable capabilities across a range of text-generation tasks. However, LLMs still struggle with problems requiring multi-step decision-making and environmental feedback, such as online…

Test-time adaptation (TTA) adapts the pre-trained models during inference using unlabeled test data and has received a lot of research attention due to its potential practical value. Unfortunately, without any label supervision, existing…

The rapid advancement of Large Language Models (LLMs) has sparked growing interest in their application to time series analysis tasks. However, their ability to perform complex reasoning over temporal data in real-world application domains…

With the rapid advancement of post-training techniques for reasoning and information seeking, large language models (LLMs) can incorporate a large quantity of retrieved knowledge to solve complex tasks. However, the limited context window…

Pretrained language models (PLMs) like BERT provide strong semantic representations but are costly and opaque, while symbolic models such as the Tsetlin Machine (TM) offer transparency but lack semantic generalization. We propose a semantic…

Modern language agents must operate over long-horizon, multi-turn histories, yet deploying such agents with Small Language Models (SLMs) remains fundamentally difficult. Full-context prompting causes context overflow, flat retrieval exposes…

Recent advancements in Large Language Models (LLMs) have created new opportunities to enhance performance on complex reasoning tasks by leveraging test-time computation. However, existing scaling methods have key limitations: parallel…

Context engineering for large language model (LLM) agents requires distinguishing pragmatically useful information from misleading distractors. We introduce Entropic Context Shaping (ECS), an information-theoretic framework that measures…

Entropy minimization (EM) trains the model to concentrate even more probability mass on its most confident outputs. We show that this simple objective alone, without any labeled data, can substantially improve large language models' (LLMs)…

Test-time scaling (TTS) has emerged as a powerful paradigm for improving the reasoning ability of Large Language Models (LLMs) by allocating additional computation at inference, yet its application to multimodal systems such as…

Deep learning is playing an increasingly important role in time series analysis. We focused on time series forecasting using attention free mechanism, a more efficient framework, and proposed a new architecture for time series prediction…

Given a textual description, the task of referring expression comprehension (REC) involves the localisation of the referred object in an image. Multimodal large language models (MLLMs) have achieved high accuracy on REC benchmarks through…

Many conversational agents in the market today follow a standard bot development framework which requires training intent classifiers to recognize user input. The need to create a proper set of training examples is often the bottleneck in…

Pretrained language models have become the standard approach for many NLP tasks due to strong performance, but they are very expensive to train. We propose a simple and efficient learning framework, TLM, that does not rely on large-scale…

The remarkable performance of Large Language Models (LLMs) can be enhanced with test-time computation, which relies on external tools and even other deep learning models. However, existing approaches for integrating non-text modality…

Test-time alignment (TTA) aims to adapt models to specific rewards during inference. However, existing methods tend to either under-optimise or over-optimise (reward hack) the target reward function. We propose Null-Text Test-Time Alignment…

Topic modeling is a research field finding increasing applications: historically from document retrieving, to sentiment analysis and text summarization. Large Language Models (LLM) are currently a major trend in text processing, but few…