Research
Research
Research
Research
2,185+ open-access research outputs.
Let $\mathcal A$ be an $\mathbb F$-algebra and $\omega \in \mathcal A\langle x_1, \ldots, x_m \rangle$ which defines a map $\mathcal A^m \rightarrow \mathcal A$ by evaluation, called a polynomial map …
Continual offline reinforcement learning (CORL) aims to learn a sequence of tasks from datasets collected over time while preserving performance on previously learned tasks. This setting corresponds t…
Deep Learning methods are becoming prominent in automated software bug detection; however, they lack the global understanding of the given code. Consequently, their performance tends to degrade, espec…
We study the organization of channel-level importance in transformer feed-forward networks (FFNs). Using a Fisher-style loss proxy (LP) based on activation-gradient second moments, we show that loss s…
Large language models (LLMs) have recently shown strong potential for generating project-level unit tests. However, existing state-of-the-art approaches primarily rely on execution-path information to…
We explore the sensitivity of neutrino observatories and direct dark matter detection experiments to boosted sub-GeV dark matter produced by inelastic cosmic ray collisions in the atmosphere. We revis…
This paper presents the first study on Unsupervised Domain Adaptation (UDA) for multimodal 3D panoptic segmentation (mm-3DPS), aiming to improve generalization under domain shifts commonly encountered…
Composed Image Retrieval (CIR) is a flexible image retrieval paradigm that enables users to accurately locate the target image through a multimodal query composed of a reference image and modification…
The upcoming PandaX-xT experiment will deploy over 3,000 readout channels operating at a 500 MSa/s sampling rate, generating a sustained data bandwidth up to 1.6 GB/s. To meet this demanding requireme…
Manipulating open liquid containers is challenging because liquids are highly sensitive to vessel accelerations and jerks. Although spill-free liquid manipulation has been widely studied, emergency st…
While Large Language Models (LLMs) demonstrate impressive proficiency in generating SQL queries, they fundamentally lack the capability to self-evaluate correctness without an execution oracle. This l…
Reinforcement learning (RL) enables high-frequency, closed-loop control for robotic manipulation, but scaling to long-horizon tasks with sparse or imperfect rewards remains difficult due to inefficien…
Singular configurations cause loss of task-space mobility, unbounded joint velocities, and solver divergence in inverse kinematics (IK) for serial manipulators. No existing survey bridges classical si…
Predicate pushdown is a long-standing performance optimization that filters data as early as possible in a computational workflow. In modern data pipelines, this transformation is especially important…
Simulation-based data generation has become a dominant paradigm for training robotic manipulation policies, yet existing platforms do not incorporate object affordance information into trajectory gene…
Robots are increasingly entering human-interactive scenarios that require understanding of quantity. How intelligent systems acquire abstract numerical concepts from sensorimotor experience remains a …
Mechanistic interpretability is often motivated for alignment auditing, where a model's verbal explanations can be absent, incomplete, or misleading. Yet many evaluations do not control whether black-…
In this work, we introduce a new perspective on comparative image assessment by representing an image pair as a structured composition of its regions. In contrast, existing methods focus on whole imag…
Labelling tissue components in histology whole slide images (WSIs) is prohibitively labour-intensive: a single slide may contain tens of thousands of structures--cells, nuclei, and other morphological…
This paper presents a Robust Adaptive Backstepping Impedance Control (RABIC) strategy for robots operating in contact-rich and uncertain environments. The proposed control strategy considers the compl…
Free open-access publishing with Google Scholar indexing.
Submission Guide →