Search Results for author:
Found 54 papers, 14 papers with code
Verified Lifting of Deep learning Operators
To address this gap, this work introduces a novel framework for the verified lifting of deep learning operators, which synthesizes high-level mathematical formulas from low-level implementations.
World-Consistent Data Generation for Vision-and-Language Navigation
Vision-and-Language Navigation (VLN) is a challenging task that requires an agent to navigate through photorealistic environments following natural-language instructions.
KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems
Embodied AI agents responsible for executing interconnected, long-sequence household tasks often face difficulties with in-context memory, leading to inefficiencies and errors in task execution.
DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization
Current text-to-image (T2I) synthesis diffusion models raise misuse concerns, particularly in creating prohibited or not-safe-for-work (NSFW) images.
CodeV: Empowering LLMs for Verilog Generation through Multi-Level Summarization
Instruction-tuned large language models (LLMs) have demonstrated remarkable performance in automatically generating code for general-purpose programming languages like Python.
TensorTEE: Unifying Heterogeneous TEE Granularity for Efficient Secure Collaborative Tensor Computing
However, existing heterogeneous TEE designs are inefficient for collaborative computing due to fine and different memory granularities between CPU and NPU.
InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct
Recent advancements in open-source code large language models (LLMs) have been driven by fine-tuning on the data generated from powerful closed-source LLMs, which are expensive to obtain.
NLPerturbator: Studying the Robustness of Code LLMs to Natural Language Variations
Large language models (LLMs) achieve promising results in code generation based on a given natural language description.
Adversarial Contrastive Decoding: Boosting Safety Alignment of Large Language Models via Opposite Prompt Optimization
With the widespread application of Large Language Models (LLMs), it has become a significant concern to ensure their safety and prevent harmful responses.
Prompt-based Visual Alignment for Zero-shot Policy Transfer
With explicit constraints of semantic information, PVA can learn unified cross-domain representation under limited access to cross-domain data and achieves great zero-shot generalization ability in unseen domains.
Enhancing Repository-Level Code Generation with Integrated Contextual Information
Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks.
PillarHist: A Quantization-aware Pillar Feature Encoder based on Height-aware Histogram
To address above issue, we first unveil the importance of different input information during PFE and identify the height dimension as a key factor in enhancing 3D detection performance.
I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models
Post-training quantization (PTQ) serves as a potent technique to accelerate the inference of large language models (LLMs).
Luban: Building Open-Ended Creative Agents via Autonomous Embodied Verification
In this work, we introduce autonomous embodied verification techniques for agents to fill the gap, laying the groundwork for creative tasks.
Reasoning Runtime Behavior of a Program with LLM: How Far Are We?
Code reasoning is one of the most essential abilities of code LLMs, but existing benchmarks for code reasoning are not sufficient.
Assessing and Understanding Creativity in Large Language Models
This paper aims to establish an efficient framework for assessing the level of creativity in LLMs.
Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting
Although neural networks have made remarkable advancements in various applications, they require substantial computational and memory resources.
Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?
Although these studies have demonstrated the ability to protect images, it is essential to consider that these methods may not be entirely applicable in real-world scenarios.
Context Shift Reduction for Offline Meta-Reinforcement Learning
In this paper, we propose a novel approach called Context Shift Reduction for OMRL (CSRO) to address the context shift problem with only offline datasets.
Self-driven Grounding: Large Language Model Agents with Automatical Language-aligned Skill Learning
Large language models (LLMs) show their powerful automatic reasoning and planning capability with a wealth of semantic knowledge about the human world.
EditSum: A Retrieve-and-Edit Framework for Source Code Summarization
Besides the patternized words, a code summary also contains important keywords, which are the key to reflecting the functionality of the code.
Pushing the Limits of Machine Design: Automated CPU Design with AI
By efficiently exploring a search space of unprecedented size 10^{10^{540}}, which is the largest one of all machine-designed objects to our best knowledge, and thus pushing the limits of machine design, our approach generates an industrial-scale RISC-V CPU within only 5 hours.
Online Prototype Alignment for Few-shot Policy Transfer
Domain adaptation in reinforcement learning (RL) mainly deals with the changes of observation when transferring the policy to a new environment.
Flew Over Learning Trap: Learn Unlearnable Samples by Progressive Staged Training
Unlearning techniques are proposed to prevent third parties from exploiting unauthorized data, which generate unlearnable samples by adding imperceptible perturbations to data for public publishing.
Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitation
This imperceptible protective noise makes the data almost unlearnable for diffusion models, i. e., diffusion models trained or fine-tuned on the protected data cannot generate high-quality and diverse images related to the protected training data.
ANPL: Towards Natural Programming with Interactive Decomposition
We deploy ANPL on the Abstraction and Reasoning Corpus (ARC), a set of unique tasks that are challenging for state-of-the-art AI systems, showing it outperforms baseline programming systems that (a) without the ability to decompose tasks interactively and (b) without the guarantee that the modules can be correctly composed together.
Conceptual Reinforcement Learning for Language-Conditioned Tasks
Recently, the language-conditioned policy is proposed to facilitate policy transfer through learning the joint representation of observation and text that catches the compact and invariant information across environments.
Ultra-low Precision Multiplication-free Training for Deep Neural Networks
The energy-efficient works try to decrease the precision of multiplication or replace the multiplication with energy-efficient operations such as addition or bitwise shift, to reduce the energy consumption of FP32 multiplications.
Online Symbolic Regression with Informative Query
Symbolic regression, the task of extracting mathematical expressions from the observed data $\{ \vx_i, y_i \}$, plays a crucial role in scientific discovery.
LGN-Net: Local-Global Normality Network for Video Anomaly Detection
Existing unsupervised VAD methods tend to learn normality from training sets consisting of only normal videos and regard instances deviating from such normality as anomalies.
Poison Attack and Defense on Deep Source Code Processing Models
The attackers aim to inject insidious backdoors into models by poisoning the training data with poison samples.
CodeEditor: Learning to Edit Source Code with Pre-trained Models
Pre-trained models are first pre-trained with pre-training tasks and fine-tuned with the code editing task.
Causality-driven Hierarchical Structure Discovery for Reinforcement Learning
To address this issue, we propose CDHRL, a causality-driven hierarchical reinforcement learning framework, leveraging a causality-driven discovery instead of a randomness-driven exploration to effectively build high-quality hierarchical structures in complicated environments.
Object-Category Aware Reinforcement Learning
Object-oriented reinforcement learning (OORL) is a promising way to improve the sample efficiency and generalization ability over standard RL.
Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks
This work proposes Themis, a software/hardware system to defend against adversarial patches for real-time robust video object detection.
Neural Program Synthesis with Query
In this work, we propose a query-based framework that trains a query neural network to generate informative input-output examples automatically and interactively from a large query space.
Toward Robust Spiking Neural Network Against Adversarial Perturbation
To the best of our knowledge, this is the first analysis on robust training of SNNs.
DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection
Autonomous driving faces great safety challenges for a lack of global perspective and the limitation of long-range perception capabilities.
Information retrieval for label noise document ranking by bag sampling and group-wise loss
To fit bag sampling well, after query and document are encoded, the global features of each group are extracted by convolutional layer and max-pooling to improve the model's resistance to the impact of labeling noise, finally, calculate the LCE group-wise loss.
Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis
Point cloud completion is a generation and estimation issue derived from the partial point clouds, which plays a vital role in the applications in 3D computer vision.
ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers
Our experimental results show that the certified accuracy is increased from 36. 3% (the state-of-the-art certified detection) to 60. 4% on the ImageNet dataset, largely pushing the certified defenses for practical use.
Learning Controllable Elements Oriented Representations for Reinforcement Learning
Deep Reinforcement Learning (deep RL) has been successfully applied to solve various decision-making problems in recent years.
Hindsight Value Function for Variance Reduction in Stochastic Dynamic Environment
In this paper, we propose to replace the state value function with a novel hindsight value function, which leverages the information from the future to reduce the variance of the gradient estimate for stochastic dynamic environments.
Rubik: A Hierarchical Architecture for Efficient Graph Learning
Graph convolutional network (GCN) emerges as a promising direction to learn the inductive representation in graph data commonly used in widespread applications, such as E-commerce, social networks, and knowledge graphs.
Hardware Architecture
HyGCN: A GCN Accelerator with Hybrid Architecture
In this work, we first characterize the hybrid execution patterns of GCNs on Intel Xeon CPU.
Distributed, Parallel, and Cluster Computing
Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradient
Recently, backpropagation through time inspired learning algorithms are widely introduced into SNNs to improve the performance, which brings the possibility to attack the models accurately given Spatio-temporal gradient maps.
Comprehensive SNN Compression Using ADMM Optimization and Activity Regularization
As well known, the huge memory and compute costs of both artificial neural networks (ANNs) and spiking neural networks (SNNs) greatly hinder their deployment on edge devices with high efficiency.
Effective and Efficient Batch Normalization Using Few Uncorrelated Data for Statistics' Estimation
We identify that the effectiveness expects less data correlation while the efficiency expects regular execution pattern.
Neural Network Model Extraction Attacks in Edge Devices by Hearing Architectural Hints
As neural networks continue their reach into nearly every aspect of software operations, the details of those networks become an increasingly sensitive subject.
Cryptography and Security Hardware Architecture
FPSA: A Full System Stack Solution for Reconfigurable ReRAM-based NN Accelerator Architecture
In this paper, we propose a full system stack solution, composed of a reconfigurable architecture design, Field Programmable Synapse Array (FPSA) and its software system including neural synthesizer, temporal-to-spatial mapper, and placement & routing.
Programmable Neural Network Trojan for Pre-Trained Feature Extractor
Existing studies have explored the outsourced training attack scenario and transfer learning attack scenario in some small datasets for specific domains, with limited numbers of fixed target classes.
Batch Normalization Sampling
In this paper, we propose alleviating this problem through sampling only a small fraction of data for normalization at each iteration.
Dynamic Sparse Graph for Efficient Deep Learning
We propose to execute deep neural networks (DNNs) with dynamic and sparse graph (DSG) structure for compressive memory and accelerative execution during both training and inference.
Crossbar-aware neural network pruning
Crossbar architecture based devices have been widely adopted in neural network accelerators by taking advantage of the high efficiency on vector-matrix multiplication (VMM) operations.
