20 accepted papers
Chinese characters are a unique blend of language and art, featuring diverse artistic styles. Mastering these styles requires extensive practice and limits public participation. To encourage broader participation, we developed a real-time, interactive tool that supports multiple Chinese character ar…
State-of-the-art multimodal web agents, powered by Multimodal Large Language Models (MLLMs), can autonomously execute many web tasks by processing user instructions and interacting with graphical user interfaces (GUIs). Current strategies for building web agents rely on (i) the generalizability of u…
Legal contracts in the custody and fund services domain govern critical aspects such as key provider responsibilities, fee schedules, and indemnification rights. However, it is challenging for an off-the-shelf Large Language Model (LLM) to ingest these contracts due to the lengthy unstructured strea…
Recent advancements in language modeling have shown promising results when applied to time series data. In particular, fine-tuning pre-trained large language models (LLMs) for time series classification tasks has achieved state-of-the-art (SOTA) performance on standard benchmarks. However, these LLM…
Existing knowledge editing works for MultiModal Large Language Models primarily focus on text-oriented, coarse-grained scenarios, where modifying textual content alone is sufficient. As a result, they fail to capture the unique challenges of multimodal editing, particularly when visual information i…
Cognitive Diagnosis Modeling aims to infer students' proficiency level on knowledge concepts from their response logs. Existing methods typically model students’ response processes as the interaction between students and exercises or concepts based on hand-crafted or deeply-learned interaction funct…
Large Language Models (LLMs) offer the potential for automatic time series analysis and reporting, which is a critical task across many domains, spanning healthcare, finance, climate, energy, and many more. In this paper, we propose a framework for rigorously evaluating the capabilities of LLMs on t…
Cognitive diagnosis is a fundamental yet critical research task in the field of intelligent education, which aims to discover the proficiency level of different students on specific knowledge concepts. Despite the effectiveness of existing efforts, previous methods always considered the mastery leve…
Assembly tasks are challenging for robot manipulation because the robot must reason over the composed effects of actions and execute multi-objective behaviors. Robots typically use predefined priorities provided by users to determine how to compose controller behaviors, but we want the robot to auto…
Recent advances in computational perception have significantly improved the ability of autonomous robots to perform state estimation with low entropy. Such advances motivate a reconsideration of robot decision-making under uncertainty. Current approaches to solving sequential decision-making problem
In this paper, we propose a novel conditional convolution network, named location-variable convolution, to model the dependencies of the waveform sequence. Different from the use of unified convolution kernels in WaveNet to capture the dependencies of arbitrary waveform, the location-variable convol…
For autonomous service robots to successfully perform long horizon tasks in the real world, they must act intelligently in partially observable environments. Most Task and Motion Planning approaches assume full observability of their state space, making them ineffective in stochastic and partially o…
We aim for mobile robots to function in a variety of common human environments, which requires them to efficiently search previously unseen target objects. We can exploit background knowledge about common spatial relations between landmark objects and target objects to narrow down search space. In t…
Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel. AlignTTS is based on a Feed-Forward Transformer which generates mel-spectrum from a sequence of characters, and the duration of each character is determined by a duration predictor. Instea…
This paper leverages the graph-to-sequence method in neural text-to-speech (GraphTTS), which maps the graph embedding of the input sequence to spectrograms. The graphical inputs consist of node and edge representations constructed from input texts. The encoding of these graphical inputs incorporates…
We aim for mobile robots to function in a variety of common human environments. Such robots need to be able to reason about the locations of previously unseen target objects. Landmark objects can help this reasoning by narrowing down the search space significantly. More specifically, we can exploit…
We present Tangent Space Belief Propagation (TSBP) as a method for graph denoising to improve the robustness of manifold learning algorithms. Dimension reduction by manifold learning relies heavily on the accurate selection of nearest neighbors, which has proven an open problem for sparse and noisy
We present a filtering-based method for semantic mapping to simultaneously detect objects and localize their 6 degree-of-freedom pose. For our method, called Contextual Temporal Mapping (or CT-Map), we represent the semantic map as a belief over object classes and poses across an observed scene. Inf…
We present the Semantic Robot Programming (SRP) paradigm as a convergence of robot programming by demonstration and semantic mapping. In SRP, a user can directly program a robot manipulator by demonstrating a snapshot of their intended goal scene in workspace. The robot then parses this goal as a sc…
In order to perform autonomous sequential manipulation tasks, perception in cluttered scenes remains a critical challenge for robots. In this paper, we propose a probabilistic approach for robust sequential scene estimation and manipulation - Sequential Scene Understanding and Manipulation (SUM). SU…