Search Results for author:
Found 35 papers, 19 papers with code
Benchmarking Meaning Representations in Neural Semantic Parsing
Thus, the impact of meaning representation on semantic parsing is less understood.
PSE-Net: Channel Pruning for Convolutional Neural Networks with Parallel-subnets Estimator
Channel Pruning is one of the most widespread techniques used to compress deep neural networks while maintaining their performances.
SWE-bench-java: A GitHub Issue Resolving Benchmark for Java
GitHub issue resolving is a critical task in software engineering, recently gaining significant attention in both industry and academia.
L^2CL: Embarrassingly Simple Layer-to-Layer Contrastive Learning for Graph Collaborative Filtering
Surprisingly, we find that L2CL, using only one-hop contrastive learning paradigm, is able to capture intrinsic semantic structures and improve the quality of node representation, leading to a simple yet effective architecture.
QVD: Post-training Quantization for Video Diffusion Models
Furthermore, we investigate significant inter-channel disparities and asymmetries in the activation of video diffusion models, resulting in low coverage of quantization levels by individual channels and increasing the challenge of quantization.
Foundation Model Engineering: Engineering Foundation Models Just as Engineering Software
By treating data and models as the source code, Foundation Models (FMs) become a new type of software.
CodeR: Issue Resolving with Multi-Agent and Task Graphs
GitHub issue resolving recently has attracted significant attention from academia and industry.
Ranked #1 on
Bug fixing
on SWE-bench-lite
MESIA: Understanding and Leveraging Supplementary Nature of Method-level Comments for Automatic Comment Generation
In this paper, we raise the awareness of the supplementary nature of method-level comments and propose a new metric named MESIA (Mean Supplementary Information Amount) to assess the extent of supplementary information that a code comment can provide.
InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models
We conduct a systematic evaluation for over 100 latest code LLMs on InfiBench, leading to a series of novel and insightful findings.
Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm
To improve the contextual learning capabilities of LLMs in text-to-SQL, a workflow paradigm method is proposed, aiming to enhance the attention and problem-solving scope of LLMs through decomposition.
Using LLM to select the right SQL Query from candidates
We propose an automatic test case generation method that first generates a database and then uses LLMs to predict the ground truth, which is the expected execution results of the ground truth SQL query on this database.
Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software Deployment
To mitigate this issue, AI software compression plays a crucial role, which aims to compress model size while keeping high performance.
Data Transformation to Construct a Dataset for Generating Entity-Relationship Model from Natural Language
To address this issue, in this paper, we report our insight that there exists a high similarity between the task of NL2ERM and the increasingly popular task of text-to-SQL, and propose a data transformation algorithm that transforms the existing data of text-to-SQL into the data of NL2ERM.
EasyVolcap: Accelerating Neural Volumetric Video Research
Volumetric video is a technology that digitally records dynamic events such as artistic performances, sporting events, and remote conversations.
FMRT: Learning Accurate Feature Matching with Reconciliatory Transformer
However, these methods only integrate long-range context information among keypoints with a fixed receptive field, which constrains the network from reconciling the importance of features with different receptive fields to realize complete image perception, hence limiting the matching accuracy.
Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenes
This paper aims to tackle the challenge of dynamic view synthesis from multi-view videos.
OFVL-MS: Once for Visual Localization across Multiple Indoor Scenes
In this work, we seek to predict camera poses across scenes with a multi-task learning manner, where we view the localization of each scene as a new task.
OlaGPT: Empowering LLMs With Human-like Problem-Solving Abilities
At present, most approaches focus on chains of thought (COT) and tool use, without considering the adoption and application of human cognitive frameworks.
Reliability Assurance for Deep Neural Network Architectures Against Numerical Defects
To assure high reliability against numerical defects, in this paper, we propose the RANUM approach including novel techniques for three reliability assurance tasks: detection of potential numerical defects, confirmation of potential-defect feasibility, and suggestion of defect fixes.
OAMatcher: An Overlapping Areas-based Network for Accurate Local Feature Matching
Local feature matching is an essential component in many visual applications.
DeepMatcher: A Deep Transformer-based Network for Robust and Accurate Local Feature Matching
In this work, we propose DeepMatcher, a deep Transformer-based network built upon our investigation of local feature matching in detector-free methods.
CO-Net: Learning Multiple Point Cloud Tasks at Once with A Cohesive Network
Finally, we propose a sign-based gradient surgery to promote the training of CO-Net, thereby emphasizing the usage of task-shared parameters and guaranteeing that each task can be thoroughly optimized.
Poly-PC: A Polyhedral Network for Multiple Point Cloud Tasks at Once
In this work, we show that it is feasible to perform multiple tasks concurrently on point cloud with a straightforward yet effective multi-task network.
MDL-NAS: A Joint Multi-Domain Learning Framework for Vision Transformer
Technically, MDL-NAS constructs a coarse-to-fine search space, where the coarse search space offers various optimal architectures for different tasks while the fine search space provides fine-grained parameter sharing to tackle the inherent obstacles of multi-domain learning.
Double Sampling Randomized Smoothing
To overcome this hurdle, we propose a Double Sampling Randomized Smoothing (DSRS) framework, which exploits the sampled probability from an additional smoothing distribution to tighten the robustness certification of the previous smoothed classifier.
On the Certified Robustness for Ensemble Models and Beyond
Thus, to explore the conditions that guarantee to provide certifiably robust ensemble ML models, we first prove that diversified gradient and large confidence margin are sufficient and necessary conditions for certifiably robust ensemble models under the model-smoothness assumption.
SoK: Certified Robustness for Deep Neural Networks
Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on a wide range of tasks.
Adversarial Attack on Large Scale Graph
Currently, most works on attacking GNNs are mainly using gradient information to guide the attack and achieve outstanding performance.
Understanding Challenges in Deploying Deep Learning Based Software: An Empirical Study
Deep learning (DL) becomes increasingly pervasive, being used in a wide range of software applications.
Software Engineering
A Survey of Adversarial Learning on Graphs
To bridge this gap, we investigate and summarize the existing works on graph adversarial learning tasks systemically.
TSS: Transformation-Specific Smoothing for Robustness Certification
Moreover, to the best of our knowledge, TSS is the first approach that achieves nontrivial certified robustness on the large-scale ImageNet dataset.
SemRegex: A Semantics-Based Approach for Generating Regular Expressions from Natural Language Specifications
Recent research proposes syntax-based approaches to address the problem of generating programs from natural language specifications.
MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks
In particular, given a target model, our framework includes multiple models (constructed from the target model) to form a model family.
Testing Untestable Neural Machine Translation: An Industrial Case
To fill the gap of lacking test oracle for in-vivo testing of an NMT system, in this paper, we propose a new approach for automatically identifying translation failures, without requiring reference translations for a translation task; our approach can directly serve as a test oracle for in-vivo testing.
Want a Good Answer? Ask a Good Question First!
Community Question Answering (CQA) websites have become valuable repositories which host a massive volume of human knowledge.
