Search Results for author:
Found 79 papers, 28 papers with code
Detecting Health Advice in Medical Research Literature
We also conducted a case study that applied this prediction model to retrieve specific health advice on COVID-19 treatments from LitCovid, a large COVID research literature portal, demonstrating the usefulness of retrieving health advice sentences as an advanced research literature navigation function for health researchers and the general public.
“Devils Are in the Details”: Annotating Specificity of Clinical Advice from Medical Literature
Prior studies have raised concerns over specificity issues in clinical advice.
Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?
Together, our LSDBench and RHS framework address the unique challenges of high-NSD long-video tasks, setting a new standard for evaluating and improving LVLMs in this domain.
Modular Customization of Diffusion Models via Blockwise-Parameterized Low-Rank Adaptation
In contrast, instant merging methods often cause identity loss and interference of individual merged concepts and are usually limited to a small number of concepts.
Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement
Traditional methods for reasoning segmentation rely on supervised fine-tuning with categorical labels and simple descriptions, limiting its out-of-domain generalization and lacking explicit reasoning processes.
Effective LLM Knowledge Learning via Model Generalization
We found and verified that knowledge learning for LLMs can be deemed as an implicit supervised task hidden in the autoregressive pre-training objective.
Divergent Thoughts toward One Goal: LLM-based Multi-Agent Collaboration System for Electronic Design Automation
Recently, with the development of tool-calling capabilities in large language models (LLMs), these models have demonstrated significant potential for automating electronic design automation (EDA) flows by interacting with EDA tool APIs via EDA scripts.
TorchResist: Open-Source Differentiable Resist Simulator
Recent decades have witnessed remarkable advancements in artificial intelligence (AI), including large language models (LLMs), image and video generative models, and embodied AI systems.
CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference
Large language models (LLMs) achieve impressive performance by scaling model parameters, but this comes with significant inference overhead.
Causal Interpretations in Observational Studies: The Role of Sociocultural Backgrounds and Team Dynamics
The prevalence of drawing causal conclusions from observational studies has raised concerns about potential exaggeration in science communication.
Generative Video Propagation
Large-scale video generation models have the inherent ability to realistically model natural scenes.
DreamOmni: Unified Image Generation and Editing
We begin by analyzing existing frameworks and the requirements of downstream tasks, proposing a unified framework that integrates both T2I models and various editing tasks.
FlexPose: Pose Distribution Adaptation with Limited Guidance
We treat the representation of human pose joint coordinates as skeleton image and transfer a pre-trained pose annotation generator with only a few annotation guidance.
VisionZip: Longer is Better but Not Necessary in Vision Language Models
To address this, we introduce VisionZip, a simple yet effective method that selects a set of informative tokens for input to the language model, reducing visual token redundancy and improving efficiency while maintaining model performance.
Ranked #176 on
Visual Question Answering
on MM-Vet
MixPE: Quantization and Hardware Co-design for Efficient LLM Inference
Transformer-based large language models (LLMs) have achieved remarkable success as model sizes continue to grow, yet their deployment remains challenging due to significant computational and memory demands.
FuseGPT: Learnable Layers Fusion of Generative Pre-trained Transformers
In this paper, we propose FuseGPT, a novel methodology to recycle the pruned transformer blocks to further recover the model performance.
RTLRewriter: Methodologies for Large Models aided RTL Code Optimization
Our comparative analysis with established compilers such as Yosys and E-graph demonstrates significant improvements, highlighting the benefits of integrating large models into the early stages of circuit design.
Intelligent OPC Engineer Assistant for Semiconductor Manufacturing
Advancements in chip design and manufacturing have enabled the processing of complex tasks such as deep learning and natural language processing, paving the way for the development of artificial general intelligence (AGI).
Differentiable Edge-based OPC
Optical proximity correction (OPC) is crucial for pushing the boundaries of semiconductor manufacturing and enabling the continued scaling of integrated circuits.
Customized Retrieval Augmented Generation and Benchmarking for EDA Tool Documentation QA
Retrieval augmented generation (RAG) enhances the accuracy and reliability of generative AI models by sourcing factual information from external databases, which is extensively employed in document-grounded question-answering (QA) tasks.
MoreauPruner: Robust Pruning of Large Language Models against Weight Perturbations
Our numerical results suggest the robustness of MoreauPruner against weight perturbations, and indicate the MoreauPruner's successful accuracy-based scores in comparison to several existing pruning methods.
LLM-Enhanced Bayesian Optimization for Efficient Analog Layout Constraint Generation
Analog layout synthesis faces significant challenges due to its dependence on manual processes, considerable time requirements, and performance instability.
GNNavigator: Towards Adaptive Training of Graph Neural Networks via Automatic Guideline Exploration
Graph Neural Networks (GNNs) succeed significantly in many applications recently.
CAMO: Correlation-Aware Mask Optimization with Modulated Reinforcement Learning
Optical proximity correction (OPC) is a vital step to ensure printability in modern VLSI manufacturing.
HDLdebugger: Streamlining HDL debugging with Large Language Models
In the domain of chip design, Hardware Description Languages (HDLs) play a pivotal role.
ChatPattern: Layout Pattern Customization via Natural Language
Existing works focus on fixed-size layout pattern generation, while the more practical free-size pattern generation receives limited attention.
Learning-driven Physically-aware Large-scale Circuit Gate Sizing
Gate sizing plays an important role in timing optimization after physical design.
Classes Are Not Equal: An Empirical Study on Image Recognition Fairness
Second, with the proposed concept of Model Prediction Bias, we investigate the origins of problematic representation during optimization.
DiLA: Enhancing LLM Tool Learning with Differential Logic Layer
In this paper, we propose a novel differential logic layer-aided language modeling (DiLA) approach, where logical constraints are integrated into the forward and backward passes of a network layer, to provide another option for LLM tool learning.
BetterV: Controlled Verilog Generation with Discriminative Guidance
In this work, we propose a Verilog generation framework, BetterV, which fine-tunes the large language models (LLMs) on processed domain-specific datasets and incorporates generative discriminators for guidance on particular design demands.
Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks
Using PESC during instruction tuning, our best sparse model outperforms other sparse and dense models and exhibits superior general capabilities compared to GPT-3. 5.
Ranked #6 on
Common Sense Reasoning
on ARC (Easy)
p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models
In this paper, we present a novel modeling framework that recasts adapter tuning after attention as a graph message passing process on attention graphs, where the projected query and value features and attention matrix constitute the node features and the graph adjacency matrix, respectively.
TinyFormer: Efficient Transformer Design and Deployment on Tiny Devices
To the best of our knowledge, SparseEngine is the first deployment framework capable of performing inference of sparse models with transformer on MCUs.
On the Distributed Evaluation of Generative Models
On the other hand, several applications of generative models concern distributed settings, e. g. the federated learning setting, where the reference data for conducting evaluation are provided by several clients in a network.
ChatEDA: A Large Language Model Powered Autonomous Agent for EDA
The integration of a complex set of Electronic Design Automation (EDA) tools to enhance interoperability is a critical concern for circuit designers.
Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks
Neural architecture search (NAS) for Graph neural networks (GNNs), called NAS-GNNs, has achieved significant performance over manually designed GNN architectures.
Decoupled Kullback-Leibler Divergence Loss
In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) Divergence loss that consists of 1) a weighted Mean Square Error (wMSE) loss and 2) a Cross-Entropy loss incorporating soft labels.
Towards Versatile and Efficient Visual Knowledge Integration into Pre-trained Language Models with Cross-Modal Adapters
To inject visual knowledge into PLMs, existing methods incorporate either the text or image encoder of vision-language models (VLMs) to encode the visual information and update all the original parameters of PLMs for knowledge fusion.
GPU-accelerated Matrix Cover Algorithm for Multiple Patterning Layout Decomposition
Multiple patterning lithography (MPL) is regarded as one of the most promising ways of overcoming the resolution limitations of conventional optical lithography due to the delay of next-generation lithography technology.
DiffPattern: Layout Pattern Generation via Discrete Diffusion
Deep generative models dominate the existing literature in layout pattern generation.
DevelSet: Deep Neural Level Set for Instant Mask Optimization
To further enhance printability and fast iterative convergence, we propose a novel deep neural network delicately designed with level set intrinsic principles to facilitate the joint optimization of DNN and GPU accelerated level set optimizer.
A High-Performance Accelerator for Super-Resolution Processing on Embedded GPU
Recent years have witnessed impressive progress in super-resolution (SR) processing.
Physics-Informed Optical Kernel Regression Using Complex-valued Neural Fields
Lithography is fundamental to integrated circuit fabrication, necessitating large computation overhead.
AdaOPC: A Self-Adaptive Mask Optimization Framework For Real Design Patterns
We inspect the pattern distribution on a design layer and find that different sub-regions have different pattern complexity.
Efficient Deep Space Filling Curve
By modeling the pixel grid as a graph, they first adopt GNN to predict the edge weights and then generate a minimum spanning tree (MST) based on the predictions, which is further used to construct the SFC.
Generalized Parametric Contrastive Learning
Based on theoretical analysis, we observe that supervised contrastive loss tends to bias high-frequency classes and thus increases the difficulty of imbalanced learning.
Ranked #7 on
Long-tail Learning
on iNaturalist 2018
Rethinking Graph Neural Networks for the Graph Coloring Problem
Graph coloring, a classical and critical NP-hard problem, is the problem of assigning connected nodes as different colors as possible.
Towards Real-World Video Denosing: A Practical Video Denosing Dataset and Network
Moreover, we also propose a new video denoising framework, called Recurrent Video Denoising Transformer (RVDT), which can achieve SOTA performance on PVDD and other current video denoising benchmarks.
DSGN++: Exploiting Visual-Spatial Relation for Stereo-based 3D Detectors
First, to effectively lift the 2D information to stereo volume, we propose depth-wise plane sweeping (DPS) that allows denser connections and extracts depth-guided features.
Eventor: An Efficient Event-Based Monocular Multi-View Stereo Accelerator on FPGA Platform
In this paper, Eventor is proposed as a fast and efficient EMVS accelerator by realizing the most critical and time-consuming stages including event back-projection and volumetric ray-counting on FPGA.
PCL: Proxy-Based Contrastive Learning for Domain Generalization
Domain generalization refers to the problem of training a model from a collection of different source domains that can directly generalize to the unseen target domains.
Ranked #23 on
Domain Generalization
on PACS
PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Mask
In this work, we revisit the prior mask guidance proposed in ``Prior Guided Feature Enrichment Network for Few-Shot Segmentation''.
Conditional Temporal Variational AutoEncoder for Action Video Prediction
To synthesize a realistic action sequence based on a single human image, it is crucial to model both motion patterns and diversity in the action video.
Parametric Contrastive Learning
In this paper, we propose Parametric Contrastive Learning (PaCo) to tackle long-tailed recognition.
Ranked #14 on
Long-tail Learning
on iNaturalist 2018
Linking Health News to Research Literature
Accurately linking news articles to scientific research works is a critical component in a number of applications, such as measuring the social impact of a research work and detecting inaccuracies or distortions in science news.
Self Promotion in US Congressional Tweets
Prior studies have found that women self-promote less than men due to gender stereotypes.
Routing Towards Discriminative Power of Class Capsules
The activation of lower layer capsules affects the behavior of the following capsules via routing links that are constructed during training via certain routing algorithms.
Machine Learning for Electronic Design Automation: A Survey
With the down-scaling of CMOS technology, the design complexity of very large-scale integrated (VLSI) is increasing.
Fast and Efficient DNN Deployment via Deep Gaussian Transfer Learning
Firstly, a deep Gaussian process (DGP) model is built on the historical data to learn empirical knowledge.
Seeing Dynamic Scene in the Dark: A High-Quality Video Dataset With Mechatronic Alignment
Low-light video enhancement is an important task.
Rethinking Graph Neural Networks for Graph Coloring
To characterize the power of GNNs for the graph coloring problem, we first formalize the discrimination power of GNNs as the capability to assign nodes different colors.
Measuring Correlation-to-Causation Exaggeration in Press Releases
By comparing the claims made in a press release with the corresponding claims in the original research paper, we found that 22{\%} of press releases made exaggerated causal claims from correlational findings in observational studies.
Tensor Low-Rank Reconstruction for Semantic Segmentation
Then we use these rank-1 tensors to recover the high-rank context features through our proposed tensor reconstruction module (TRM).
Dive Deeper Into Box for Object Detection
Anchor free methods have defined the new frontier in state-of-the-art object detection researches where accurate bounding box estimation is the key to the success of these methods.
Attacking Split Manufacturing from a Deep Learning Perspective
The notion of integrated circuit split manufacturing which delegates the front-end-of-line (FEOL) and back-end-of-line (BEOL) parts to different foundries, is to prevent overproduction, piracy of the intellectual property (IP), or targeted insertion of hardware Trojans by adversaries in the FEOL facility.
VLSI Mask Optimization: From Shallow To Deep Learning
VLSI mask optimization is one of the most critical stages in manufacturability aware design, which is costly due to the complicated mask optimization and lithography simulation.
Automatic Layout Generation with Applications in Machine Learning Engine Evaluation
The tool currently supports both metal layer and via layer generation.
Detecting Causal Language Use in Science Findings
We then applied the prediction model to measure the causal language use in the research conclusions of about 38, 000 observational studies in PubMed.
Are Adversarial Perturbations a Showstopper for ML-Based CAD? A Case Study on CNN-Based Lithographic Hotspot Detection
There is substantial interest in the use of machine learning (ML) based techniques throughout the electronic computer-aided design (CAD) flow, particularly those based on deep learning.
DeepBillboard: Systematic Physical-World Testing of Autonomous Driving Systems
Furthermore, DeepBillboard is sufficiently robust and resilient for generating physical-world adversarial billboard tests for real-world driving under various weather conditions.
DAC-SDC Low Power Object Detection Challenge for UAV Applications
The 55th Design Automation Conference (DAC) held its first System Design Contest (SDC) in 2018.
An Evaluation of Information Extraction Tools for Identifying Health Claims in News Headlines
This study evaluates the performance of four information extraction tools (extractors) on identifying health claims in health news headlines.
A Unified Approximation Framework for Compressing and Accelerating Deep Neural Networks
To address this issue, various approximation techniques have been investigated, which seek for a light weighted network with little performance degradation in exchange of smaller model size or faster inference.
Recent Advances in Convolutional Neural Network Acceleration
We propose a taxonomy in terms of three levels, i. e.~structure level, algorithm level, and implementation level, for acceleration methods.
Cross-layer Optimization for High Speed Adders: A Pareto Driven Machine Learning Approach
In spite of maturity to the modern electronic design automation (EDA) tools, optimized designs at architectural stage may become sub-optimal after going through physical design flow.
Bridging the Gap Between Layout Pattern Sampling and Hotspot Detection via Batch Active Sampling
Layout hotpot detection is one of the main steps in modern VLSI design.
An NLP Analysis of Exaggerated Claims in Science News
The discrepancy between science and media has been affecting the effectiveness of science communication.
