Search Results for author:
Found 14 papers, 10 papers with code
mixSeq: A Simple Data Augmentation Methodfor Neural Machine Translation
Data augmentation, which refers to manipulating the inputs (e. g., adding random noise, masking specific parts) to enlarge the dataset, has been widely adopted in machine learning.
Cross-document Misinformation Detection based on Event Graph Reasoning
Inspired by this process, we propose a novel task of cross-document misinformation detection.
VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning
Extensive evaluation of 24 LVLMs demonstrates that human-written critiques significantly enhance the performance after correction, showcasing the potential of the self-improvement strategy.
VDebugger: Harnessing Execution Feedback for Debugging Visual Programs
Visual programs are executable code generated by large language models to address visual reasoning problems.
Re-ReST: Reflection-Reinforced Self-Training for Language Agents
Finetuning language agents with reasoning-action trajectories is effective, but obtaining these trajectories from human annotations or stronger models is costly and sometimes impractical.
DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation
We construct the DACO dataset, containing (1) 440 databases (of tabular data) collected from real-world scenarios, (2) ~2k query-answer pairs that can serve as weak supervision for model training, and (3) a concentrated but high-quality test set with human refined annotations that serves as our main evaluation benchmark.
Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data
To address this gap, we introduce the Quantitative Reasoning with Data (QRData) benchmark, aiming to evaluate Large Language Models' capability in statistical and causal reasoning with real-world data.
Retrieval-Based Transformer for Table Augmentation
In this paper, we introduce a novel approach toward automatic data wrangling in an attempt to alleviate the effort of end-users, e. g. data analysts, in structuring dynamic views from data lakes in the form of tabular data.
OpenPI-C: A Better Benchmark and Stronger Baseline for Open-Vocabulary State Tracking
Open-vocabulary state tracking is a more practical version of state tracking that aims to track state changes of entities throughout a process without restricting the state space and entity space.
Text-to-Table: A New Way of Information Extraction
We first employ a seq2seq model fine-tuned from a pre-trained language model to perform the task.
Learning to Use Future Information in Simultaneous Translation
For wait-k inference, we observe that wait-m training with $m>k$ in simultaneous NMT (i. e., using more future information for training than inference) generally outperforms wait-k training.
Temporally Correlated Task Scheduling for Sequence Learning
In many applications, a sequence learning task is usually associated with multiple temporally correlated auxiliary tasks, which are different in terms of how much input information to use or which future step to predict.
Neural Maximum Common Subgraph Detection with Guided Subgraph Extraction
Maximum Common Subgraph (MCS) is defined as the largest subgraph that is commonly present in both graphs of a graph pair.
Adaptive Period Embedding for Representing Oriented Objects in Aerial Images
While almost all previous object detectors for aerial images directly regress the angle of objects, they use complex rules to calculate the angle, and their performance is limited by the rule design.
Ranked #45 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
