Related papers: Perspectival Knowledge in PSOA RuleML: Representat…

We introduce SOMA, the Spatial Memory framework for Out-of-Vision Manipulation in Vision-Language-Action (VLA) models. Most existing VLAs implicitly assume that task-relevant objects are always visible, leading to brittle and reactive…

Domain adaptation in reinforcement learning (RL) mainly deals with the changes of observation when transferring the policy to a new environment. Many traditional approaches of domain adaptation in RL manage to learn a mapping function…

Object-centric understanding is fundamental to human vision and required for complex reasoning. Traditional methods define slot-based bottlenecks to learn object properties explicitly, while recent self-supervised vision models like DINO…

The representation of workflows and processes is essential in materials science engineering, where experimental and computational reproducibility depend on structured and semantically coherent process models. Although numerous ontologies…

Predictive modelling using machine learning has become very popular for spatial mapping of the environment. Models are often applied to make predictions far beyond sampling locations where new geographic locations might considerably differ…

This paper presents matching logic, a first-order logic (FOL) variant for specifying and reasoning about structure by means of patterns and pattern matching. Its sentences, the patterns, are constructed using variables, symbols, connectives…

System prompts in Large Language Models (LLMs) are predefined directives that guide model behaviour, taking precedence over user inputs in text processing and generation. LLM deployers increasingly use them to ensure consistent responses…

Currently, identification of crystallization pathways in polymers is being carried out using molecular simulation-based data on a preset cut-off point on a single order parameter (OP) to define nucleated or crystallized regions. Aside from…

The Choquet integral is a preference model used in Multiple Criteria Decision Aiding (MCDA) to deal with interactions between criteria. The Stochastic Multiobjective Acceptability Analysis (SMAA) is an MCDA methodology used to take into…

Multi-agent settings are quickly gathering importance in machine learning. This includes a plethora of recent work on deep multi-agent reinforcement learning, but also can be extended to hierarchical RL, generative adversarial networks and…

With the exponential increase of the protein sequence databases over time, multiple-sequence alignment (MSA) methods, like PSI-BLAST, perform exhaustive and time-consuming database search to retrieve evolutionary information. The resulting…

Visual foundation models provide strong perceptual features for robotics, but their dense representations lack explicit object-level structure, limiting robustness and contractility in manipulation tasks. We propose STORM (Slot-based…

Recently many multi-label image recognition (MLR) works have made significant progress by introducing pre-trained object detection models to generate lots of proposals or utilizing statistical label co-occurrence enhance the correlation…

Semantic proto-role labeling (SPRL) is an alternative to semantic role labeling (SRL) that moves beyond a categorical definition of roles, following Dowty's feature-based view of proto-roles. This theory determines agenthood vs. patienthood…

Sequential manipulation tasks require a robot to perceive the state of an environment and plan a sequence of actions leading to a desired goal state. In such tasks, the ability to reason about spatial relations among object entities from…

Unified opinion role labeling (ORL) aims to detect all possible opinion structures of 'opinion-holder-target' in one shot, given a text. The existing transition-based unified method, unfortunately, is subject to longer opinion terms and…

Remote sensing imagery typically arrives in the form of continuous data streams. Traditional detectors often forget previously learned categories when learning new ones; therefore, research on Remote Sensing Incremental Object Detection…

While large language models (LLMs) demonstrate impressive capabilities across numerous applications, their robustness remains a critical concern. This paper is motivated by a specific vulnerability: the order sensitivity of LLMs. This…

Existing preference alignment is a one-size-fits-all alignment mechanism, where the part of the large language model (LLM) parametric knowledge with non-preferred features is uniformly blocked to all the users. However, this part of…

Despite the success of large vision and language models (VLMs) in many downstream applications, it is unclear how well they encode compositional information. Here, we create the Attribution, Relation, and Order (ARO) benchmark to…