Once trained, neural networks memorize information in diffusely encoded parameters, making it difficult to forget in support of the right to be forgotten. Unlearning aims to remove the influence of data, with performance measured against a retrained model that excludes the data. However, understanding the behavior of gold-standard retraining remains underexplored. We compare original and retrained models and observe that most prediction changes occur in peripheral samples near decision boundaries. Consequently, we propose PeriUn, a selective strategy that unlearns only peripheral samples to mimic retrained model behavior with minimal disruption, unlike prior works that remove the entire request. Combined with the Random Label based method, PeriUn significantly improves both generalization and privacy metrics. Specifically, on TinyImageNet with VGG16, PeriUn increases the Tug-of-War score by 22 points compared to the strongest. Besides, the MIA gap score surpasses the state-of-the-art method, improving by 8.7 points after applying PeriUn. Further analyses confirm that PeriUn better preserves the feature space and aligns closely with the retrained model.

Recent advances in neural networks have enabled agents to perform high-level reasoning in complex environments, where robust environmental understanding must often be obtained from accumulated observations rather than from fixed scene labels. Existing spatial abstractions commonly rely on scene-level representations, object-presence cues, scene graphs, or language-grounded category prompts; depending on the task, these abstractions can either discard distributional object evidence or introduce additional structure that is not directly grounded in the agent’s own experience. To address this information abstraction imbalance, we design an object-centric spatial abstraction (OSA) that models environments as empirical distributions over object embeddings. Building on this abstraction, we present PEU-OSA, a Probabilistic Environment Understanding framework via Object-centric Spatial Abstraction. PEU-OSA comprises three conceptual modules: an object perception module, the OSA module, and a memory component. Scene observations are transformed into object representations, abstracted into empirical distributions through OSA, and accumulated in memory for comparison with new observations. The OSA module captures three fundamental relationships in the latent space via kernel density estimation: object-object, object-environment, and environment-environment relationships. To characterize when these measurements are reliable, we propose the ( )-Statistically Separable (EDS) function, which quantifies the separability and concentration of object representations and provides theoretical conditions and empirical evidence for OSA estimates. We evaluate PEU-OSA through EDS-based analysis on ImageNet, scene classification on Places, chained inference in Replica, and applicability studies for embodied agents in Replica and Minecraft. In a Replica chained-inference setting designed to test generalization to unseen environments, PEU-OSA improves top-1 retrieval accuracy from 0.36 with CLIP-based vision-language retrieval to 0.78, suggesting that object-distribution memory can provide a useful grounding source when scene-level language retrieval is insufficient. These findings support PEU-OSA as an annotation-free, experience-grounded framework for probabilistic environment understanding across recognition, reasoning, and embodied memory scenarios.

Neural networks learn effective feature representations, which can be transferred to new tasks without additional training. While larger datasets are known to improve feature transfer, the theoretical conditions for the success of such transfer remain unclear. This work investigates feature transfer in networks trained for classification to identify the conditions that enable effective clustering in unseen classes. We first reveal that higher similarity between training and unseen distributions leads to improved Cohesion and Separability. We then show that feature expressiveness is enhanced when inputs are similar to the training classes, while the features of irrelevant inputs remain indistinguishable. We validate our analysis on synthetic and benchmark datasets, including CAR, CUB, SOP, ISC, and ImageNet. Our analysis highlights the importance of the similarity between training classes and the input distribution for successful feature transfer.

Recent machine learning algorithms have been developed using well-curated datasets, which often require substantial cost and resources. On the other hand, the direct use of raw data often leads to overfitting towards frequently occurring class information. To address class imbalances cost-efficiently, we propose an active data filtering process during self-supervised pre-training in our novel framework, Duplicate Elimination (DUEL). This framework integrates an active memory inspired by human working memory and introduces distinctiveness information, which measures the diversity of the data in the memory, to optimize both the feature extractor and the memory. The DUEL policy, which replaces the most duplicated data with new samples, aims to enhance the distinctiveness information in the memory and thereby mitigate class imbalances. We validate the effectiveness of the DUEL framework in class-imbalanced environments, demonstrating its robustness and providing reliable results in downstream tasks. We also analyze the role of the DUEL policy in the training process through various metrics and visualizations.

The map fusion for multi-robot simultaneous localization and mapping (SLAM) consistently combines robot maps built independently into the global map. An established approach to map fusion is utilizing rendezvous, which refers to an encounter between multiple agents, to calculate the transformation into the global map. However, previous works using rendezvous have a limitation in that they are unreliable for certain circumstances, where the amount of agent observations or overlapping landmarks is limited. This work proposes a novel map fusion system which robustly fuses local maps in challenging rendezvous that lack shared information. Our system utilizes the single visual perception from rendezvous and estimates the relative pose between agents with the DOPE. Then our scheme transforms local maps with an estimated relative pose and predicts the misalignment from approximated maps by utilizing the attention mechanism of the vision transformer. Comparisons with the Hough transform-based method show that ours is significantly better when the overlap between local maps is insufficient. We also verify the robustness of our system against a similar real-world scenario.

Current robotic hand manipulation narrowly operates with objects in predictable positions in limited environments. Thus, when the location of the target object deviates severely from the expected location, a robot sometimes responds in an unexpected way, especially when it operates with a human. For safe robot operation, we propose the EXit-aware Object Tracker (EXOT) on a robot hand camera that recognizes an object's absence during manipulation. The robot decides whether to proceed by examining the tracker's bounding box output containing the target object. We adopt an out-of-distribution classifier for more accurate object recognition since trackers can mistrack a background as a target object. To the best of our knowledge, our method is the first approach of applying an out-of-distribution classification technique to a tracker output. We evaluate our method on the first-person video benchmark dataset, TREK-150, and on the custom dataset, RMOT-223, that we collect from the UR5e robot. Then we test our tracker on the UR5e robot in real-time with a conveyor-belt sushi task, to examine the tracker's ability to track target dishes and to determine the exit status. Our tracker shows 38% higher exit-aware performance than a baseline method. The dataset and the code will be released at https://github.com/hskAlena/EXOT.

Recently, adversarial imitation learning has shown a scalable reward acquisition method for inverse reinforcement learning (IRL) problems. However, estimated reward signals often become uncertain and fail to train a reliable statistical model since the existing methods tend to solve hard optimization problems directly. Inspired by a first-order optimization method called mirror descent, this paper proposes to predict a sequence of reward functions, which are iterative solutions for a constrained convex problem. IRL solutions derived by mirror descent are tolerant to the uncertainty incurred by target density estimation since the amount of reward learning is regulated with respect to local geometric constraints. We prove that the proposed mirror descent update rule ensures robust minimization of a Bregman divergence in terms of a rigorous regret bound of $\mathcal{O}(1/T)$ for step sizes $\{\eta_t\}_{t=1}^{T}$. Our IRL method was applied on top of an adversarial framework, and it outperformed existing adversarial methods in an extensive suite of benchmarks.

We introduce a novel perception-action-learning system for mobile social-service robots. The state-of-the-art deep learning techniques were incorporated into each module which significantly improves the performance in solving social service tasks. The system not only demonstrated fast and robust performance in a homelike environment but also achieved the highest score in the RoboCup2017@Home Social Standard Platform League (SSPL) held in Nagoya, Japan.