Search Results for author:
Found 15 papers, 4 papers with code
ARL2: Aligning Retrievers for Black-box Large Language Models via Self-guided Adaptive Relevance Labeling
Retrieval-augmented generation enhances large language models (LLMs) by incorporating relevant information from external knowledge sources.
Adapting LLM Agents with Universal Feedback in Communication
To optimize agent interactions for task-specific learning with our universal buffer and pipeline, we introduce diverse communication patterns tailored for both single-agent and multi-agent environments.
ToolQA: A Dataset for LLM Question Answering with External Tools
To address this issue, we introduce a new dataset called ToolQA, which is designed to faithfully evaluate LLMs' ability to use external tools for question answering.
Generation-Augmented Query Expansion For Code Retrieval
Pre-trained language models have achieved promising success in code retrieval tasks, where a natural language documentation query is given to find the most relevant existing code snippet.
GNN is a Counter? Revisiting GNN for Question Answering
To open the black box of GNN and investigate these problems, we dissect state-of-the-art GNN modules for QA and analyze their reasoning capability.
Ranked #12 on
Question Answering
on OpenBookQA
TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Device
Secondly, TSM has high efficiency; it achieves a high frame rate of 74fps and 29fps for online video recognition on Jetson Nano and Galaxy Note8.
How to Design Sample and Computationally Efficient VQA Models
In multi-modal reasoning tasks, such as visual question answering (VQA), there have been many modeling and training paradigms tested.
Differentiable End-to-End Program Executor for Sample and Computationally Efficient VQA
We present a differentiable end-to-end program executor (DePe), which addresses Visual Question Answering (VQA) in a sample and computationally efficient manner.
Hardware-Centric AutoML for Mixed-Precision Quantization
Compared with conventional methods, our framework is fully automated and can specialize the quantization policy for different neural network architectures and hardware architectures.
APQ: Joint Search for Network Architecture, Pruning and Quantization Policy
However, training this quantization-aware accuracy predictor requires collecting a large number of quantized <model, accuracy> pairs, which involves quantization-aware finetuning and thus is highly time-consuming.
GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning
Our transferable optimization method makes transistor sizing and design porting more effective and efficient.
Design Automation for Efficient Deep Learning Computing
Moreover, we shorten the design cycle by 200x than previous work, so that we can afford to design specialized neural network models for different hardware platforms.
HAQ: Hardware-Aware Automated Quantization with Mixed Precision
Compared with conventional methods, our framework is fully automated and can specialize the quantization policy for different neural network architectures and hardware architectures.
SnapQuant: A Probabilistic and Nested Parameterization for Binary Networks
During the training phase, we generate binary weights on-the-fly since what we actually maintain is the policy network, and all the binary weights are used in a burn-after-reading style.
Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks
Through explicitly regularizing the loss perturbation and the weight approximation error in an incremental way, we show that such a new optimization method is theoretically reasonable and practically effective.
