Search Results for author:
Found 11 papers, 4 papers with code
Agent as Cerebrum, Controller as Cerebellum: Implementing an Embodied LMM-based Agent on Drones
In this study, we present a novel paradigm for industrial robotic embodied agents, encapsulating an 'agent as cerebrum, controller as cerebellum' architecture.
Bit Cipher -- A Simple yet Powerful Word Representation System that Integrates Efficiently with Language Models
While Large Language Models (LLMs) become ever more dominant, classic pre-trained word embeddings sustain their relevance through computational efficiency and nuanced linguistic interpretation.
Explicit Foundation Model Optimization with Self-Attentive Feed-Forward Neural Units
We will discuss a general result about feed-forward neural networks and then extend this solution to compositional (mult-layer) networks, which are applied to a simplified transformer block containing feed-forward and self-attention layers.
Reducing the Need for Backpropagation and Discovering Better Optima With Explicit Optimizations of Neural Networks
Iterative differential approximation methods that rely upon backpropagation have enabled the optimization of neural networks; however, at present, they remain computationally expensive, especially when training models at scale.
ROMO: Retrieval-enhanced Offline Model-based Optimization
Data-driven black-box model-based optimization (MBO) problems arise in a great number of practical application scenarios, where the goal is to find a design over the whole space maximizing a black-box target function based on a static offline dataset.
AgentSims: An Open-Source Sandbox for Large Language Model Evaluation
With ChatGPT-like large language models (LLM) prevailing in the community, how to evaluate the ability of LLMs is an open question.
SurroundNet: Towards Effective Low-Light Image Enhancement
Although Convolution Neural Networks (CNNs) has made substantial progress in the low-light image enhancement task, one critical problem of CNNs is the paradox of model complexity and performance.
Knowledge Distillation via Instance-level Sequence Learning
Recently, distillation approaches are suggested to extract general knowledge from a teacher network to guide a student network.
Dual Discriminator Adversarial Distillation for Data-free Model Compression
Then the generated samples are used to train the compact student network under the supervision of the teacher.
Similarity Transfer for Knowledge Distillation
The proposed approach promotes the performance of student model as the virtual sample created by multiple images produces a similar probability distribution in the teacher and student networks.
Highlight Every Step: Knowledge Distillation via Collaborative Teaching
Knowledge distillation aims to train a compact student network by transferring knowledge from a larger pre-trained teacher model.
