arXiv:2603.09085v2 Announce Type: replace-cross Abstract: By capturing the prevailing sentiment and market mood, textual data has become increasingly vital for forecasting commodity prices, particularly in metal markets. However, the effectiveness of lightweight, finetuned large language models (LLMs) in extracting predictive signals for aluminum prices, and the specific market conditions under which these signals are most […]
Denoising the Future: Top-p Distributions for Moving Through Time
arXiv:2506.07578v4 Announce Type: replace-cross Abstract: Inference in dynamic probabilistic models is a complex task involving expensive operations. In particular, for Hidden Markov Models, the whole state space has to be enumerated for advancing in time. Even states with negligible probabilities are considered, resulting in computational inefficiency and possibly increased noise due to the propagation of […]
ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning
arXiv:2603.28610v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) achieve stronger visual understanding by scaling input fidelity, yet the resulting visual token growth makes jointly sustaining high spatial resolution and long temporal context prohibitive. We argue that the bottleneck lies not in how post-encoding representations are compressed but in the volume of pixels the […]
Multi-Level Knowledge Distillation and Dynamic Self-Supervised Learning for Continual Learning
arXiv:2508.12692v3 Announce Type: replace-cross Abstract: Class-incremental with repetition (CIR), where previously trained classes repeatedly introduced in future tasks, is a more realistic scenario than the traditional class incremental setup, which assumes that each task contains unseen classes. CIR assumes that we can easily access abundant unlabeled data from external sources, such as the Internet. Therefore, […]
IMPACT: Influence Modeling for Open-Set Time Series Anomaly Detection
arXiv:2603.29183v1 Announce Type: cross Abstract: Open-set anomaly detection (OSAD) is an emerging paradigm designed to utilize limited labeled data from anomaly classes seen in training to identify both seen and unseen anomalies during testing. Current approaches rely on simple augmentation methods to generate pseudo anomalies that replicate unseen anomalies. Despite being promising in image data, […]
MMFace-DiT: A Dual-Stream Diffusion Transformer for High-Fidelity Multimodal Face Generation
arXiv:2603.29029v1 Announce Type: cross Abstract: Recent multimodal face generation models address the spatial control limitations of text-to-image diffusion models by augmenting text-based conditioning with spatial priors such as segmentation masks, sketches, or edge maps. This multimodal fusion enables controllable synthesis aligned with both high-level semantic intent and low-level structural layout. However, most existing approaches typically […]
Evaluating a Data-Driven Redesign Process for Intelligent Tutoring Systems
arXiv:2603.29094v1 Announce Type: cross Abstract: Past research has defined a general process for the data-driven redesign of educational technologies and has shown that in carefully-selected instances, this process can help make systems more effective. In the current work, we test the generality of the approach by applying it to four units of a middle-school mathematics […]
ChartDiff: A Large-Scale Benchmark for Comprehending Pairs of Charts
arXiv:2603.28902v1 Announce Type: new Abstract: Charts are central to analytical reasoning, yet existing benchmarks for chart understanding focus almost exclusively on single-chart interpretation rather than comparative reasoning across multiple charts. To address this gap, we introduce ChartDiff, the first large-scale benchmark for cross-chart comparative summarization. ChartDiff consists of 8,541 chart pairs spanning diverse data sources, […]
Deep Learning-Based Anomaly Detection in Spacecraft Telemetry on Edge Devices
arXiv:2603.29375v1 Announce Type: cross Abstract: Spacecraft anomaly detection is critical for mission safety, yet deploying sophisticated models on-board presents significant challenges due to hardware constraints. This paper investigates three approaches for spacecraft telemetry anomaly detection — forecasting & threshold, direct classification, and image classification — and optimizes them for edge deployment using multi-objective neural architecture […]
Impact of enriched meaning representations for language generation in dialogue tasks: A comprehensive exploration of the relevance of tasks, corpora and metrics
arXiv:2603.29518v1 Announce Type: cross Abstract: Conversational systems should generate diverse language forms to interact fluently and accurately with users. In this context, Natural Language Generation (NLG) engines convert Meaning Representations (MRs) into sentences, directly influencing user perception. These MRs usually encode the communicative function (e.g., inform, request, confirm) via DAs and enumerate the semantic content […]
ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning
arXiv:2603.28610v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) achieve stronger visual understanding by scaling input fidelity, yet the resulting visual token growth makes jointly sustaining high spatial resolution and long temporal context prohibitive. We argue that the bottleneck lies not in how post-encoding representations are compressed but in the volume of pixels the […]
Not All News Is Equal: Topic- and Event-Conditional Sentiment from Finetuned LLMs for Aluminum Price Forecasting
arXiv:2603.09085v2 Announce Type: replace-cross Abstract: By capturing the prevailing sentiment and market mood, textual data has become increasingly vital for forecasting commodity prices, particularly in metal markets. However, the effectiveness of lightweight, finetuned large language models (LLMs) in extracting predictive signals for aluminum prices, and the specific market conditions under which these signals are most […]