Search Results for author:
Found 25 papers, 5 papers with code
AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations
Our experiments on two popular benchmarks -- Mind2Web & VisualWebArena -- show that using in-context demonstrations (for proprietary models) or meta-adaptation demonstrations (for meta-learned open-weights models) boosts task success rate by 3. 36% to 7. 21% over non-adapted state-of-the-art models, corresponding to a relative increase of 21. 03% to 65. 75%.
Visual-Oriented Fine-Grained Knowledge Editing for MultiModal Large Language Models
MSCKE leverages a multimodal scope classifier that integrates both visual and textual information to accurately identify and update knowledge related to specific entities within images.
LETS-C: Leveraging Language Embedding for Time Series Classification
Recent advancements in language modeling have shown promising results when applied to time series data.
TRIP-PAL: Travel Planning with Guarantees by Combining Large Language Models and Automated Planners
Travel planning is a complex task that involves generating a sequence of actions related to visiting places subject to constraints and maximizing some user satisfaction criteria.
Rating Multi-Modal Time-Series Forecasting Models (MM-TSFM) for Robustness Through a Causal Lens
AI systems are notorious for their fragility; minor input changes can potentially cause major output swings.
Evaluating Large Language Models on Time Series Feature Understanding: A Comprehensive Taxonomy and Benchmark
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.
From Pixels to Predictions: Spectrogram and Vision Transformer for Better Time Series Forecasting
Time series forecasting plays a crucial role in decision-making across various domains, but it presents significant challenges.
FlowMind: Automatic Workflow Generation with LLMs
FlowMind further simplifies user interaction by presenting high-level descriptions of auto-generated workflows, enabling users to inspect and provide feedback effectively.
Financial Time Series Forecasting using CNN and Transformer
In our experiments, we demonstrated the success of the proposed method in comparison to commonly adopted statistical and deep learning methods on forecasting intraday stock price change of S&P 500 constituents.
Self-supervised Graph Learning for Long-tailed Cognitive Diagnosis
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.
TGAVC: Improving Autoencoder Voice Conversion with Text-Guided and Adversarial Training
In this paper, a novel voice conversion framework, named $\boldsymbol T$ext $\boldsymbol G$uided $\boldsymbol A$utoVC(TGAVC), is proposed to more effectively separate content and timbre from speech, where an expected content embedding produced based on the text transcriptions is designed to guide the extraction of voice content.
SeanNet: Semantic Understanding Network for Localization Under Object Dynamics
This paper proposes a SEmantic understANding Network (SeanNet) architecture that enables an effective learning process with coupled visual and semantic inputs.
Visual Time Series Forecasting: An Image-driven Approach
In this work, we address time-series forecasting as a computer vision task.
Deep Video Prediction for Time Series Forecasting
In this paper, we propose to approach economic time series forecasting of multiple financial assets in a novel way via video prediction.
GraphPB: Graphical Representations of Prosody Boundary in Speech Synthesis
Graph-to-sequence model is proposed and formed by a graph encoder and an attentional decoder.
MelGlow: Efficient Waveform Generative Network Based on Location-Variable Convolution
In this paper, an efficient network, named location-variable convolution, is proposed to model the dependencies of waveforms.
Visual Time Series Forecasting: An Image-driven Approach
In this work, we leverage advances in deep learning to extend the field of time series forecasting to a visual setting.
Manipulation-Oriented Object Perception in Clutter through Affordance Coordinate Frames
In this work, we combine the notions of affordance and category-level pose, and introduce the Affordance Coordinate Frame (ACF).
Prosody Learning Mechanism for Speech Synthesis System Without Text Length Limit
Recent neural speech synthesis systems have gradually focused on the control of prosody to improve the quality of synthesized speech, but they rarely consider the variability of prosody and the correlation between prosody and semantics together.
Semantic Linking Maps for Active Visual Object Search
SLiM simultaneously maintains the belief over a target object's location as well as landmark objects' locations, while accounting for probabilistic inter-object spatial relations.
AlignTTS: Efficient Feed-Forward Text-to-Speech System without Explicit Alignment
Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel.
GraphTTS: graph-to-sequence modelling in neural text-to-speech
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.
A Random Interaction Forest for Prioritizing Predictive Biomarkers
Precision medicine is becoming a focus in medical research recently, as its implementation brings values to all stakeholders in the healthcare system.
Semantic Mapping with Simultaneous Object Detection and Localization
Our results demonstrate that the particle filtering based inference of CT-Map provides improved object detection and pose estimation with respect to baseline methods that treat observations as independent samples of a scene.
Robotics
Object Manipulation Learning by Imitation
We aim to enable robot to learn object manipulation by imitation.
