Search Results for author:
Found 19 papers, 11 papers with code
Navi-plus: Managing Ambiguous GUI Navigation Tasks with Follow-up
Graphical user interfaces (GUI) automation agents are emerging as powerful tools, enabling humans to accomplish increasingly complex tasks on smart devices.
SpiritSight Agent: Advanced GUI Agent with One Look
While they generally meet the requirements of compatibility and low latency, these vision-based GUI agents tend to have low accuracy due to their limitations in element grounding.
UFO: Enhancing Diffusion-Based Video Generation with a Uniform Frame Organizer
Recently, diffusion-based video generation models have achieved significant success.
MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code
Training several popular base models with this corpus significantly improves their mathematical abilities, leading to the creation of the MathCoder2 family of models.
Empowering Character-level Text Infilling by Eliminating Sub-Tokens
Alternately, some approaches considered character-level infilling, but they relied on predicting sub-tokens in inference, yet this strategy diminished ability in character-level infilling tasks due to the large perplexity of the model on sub-tokens.
ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation
Inspired by this, we present ReflectionCoder, a novel approach that effectively leverages reflection sequences constructed by integrating compiler feedback to improve one-off code generation performance.
Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset
Recent advancements in Large Multimodal Models (LMMs) have shown promising results in mathematical reasoning within visual contexts, with models approaching human-level performance on existing benchmarks such as MathVista.
Ranked #1 on
Multimodal Reasoning
on MATH-V
(using extra training data)
Integrating Large Language Models into Recommendation via Mutual Augmentation and Adaptive Aggregation
Conventional recommendation methods have achieved notable advancements by harnessing collaborative or sequential information from user behavior.
RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendation
Large Language Models (LLMs) have demonstrated remarkable capabilities and have been extensively deployed across various domains, including recommender systems.
TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise
Based on TeacherLM-7. 1B, we augmented 58 NLP datasets and taught various student models with different parameters from OPT and BLOOM series in a multi-task setting.
MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
In this paper, we present a method to fine-tune open-source language models, enabling them to use code for modeling and deriving math equations and, consequently, enhancing their mathematical reasoning abilities.
Ranked #6 on
Math Word Problem Solving
on SVAMP
(using extra training data)
Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
We found that its success can be largely attributed to its powerful skills in generating and executing code, evaluating the output of code execution, and rectifying its solution when receiving unreasonable outputs.
Ranked #6 on
Math Word Problem Solving
on MATH
Reconstruct Before Summarize: An Efficient Two-Step Framework for Condensing and Summarizing Meeting Transcripts
Meetings typically involve multiple participants and lengthy conversations, resulting in redundant and trivial content.
VCSUM: A Versatile Chinese Meeting Summarization Dataset
Compared to news and chat summarization, the development of meeting summarization is hugely decelerated by the limited data.
Learning Locality and Isotropy in Dialogue Modeling
Existing dialogue modeling methods have achieved promising performance on various dialogue tasks with the aid of Transformer and the large-scale pre-trained language models.
GroupLink: An End-to-end Multitask Method for Word Grouping and Relation Extraction in Form Understanding
Forms are a common type of document in real life and carry rich information through textual contents and the organizational structure.
DocStruct: A Multimodal Method to Extract Hierarchy Structure in Document for General Form Understanding
The table detection and handcrafted features in previous works cannot apply to all forms because of their requirements on formats.
