Search Results for author:
Found 24 papers, 5 papers with code
On Speculative Decoding for Multimodal Large Language Models
We show that a language-only model can serve as a good draft model for speculative decoding with LLaVA 7B, bypassing the need for image tokens and their associated processing components from the draft model.
Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMs
In this paper, we propose a simple draft model training framework for direct alignment to chat-capable target models.
Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement
We empirically evaluate RSD with Llama 2 and OPT models, showing that RSD outperforms the baseline methods, consistently for fixed draft sequence length and in most cases for fixed computational budgets at LLM.
Layer-wise Auto-Weighting for Non-Stationary Test-Time Adaptation
Given the inevitability of domain shifts during inference in real-world applications, test-time adaptation (TTA) is essential for model adaptation after deployment.
Genetic Algorithms with Neural Cost Predictor for Solving Hierarchical Vehicle Routing Problems
For each higher-level decision candidate, we predict the objective function values of the underlying vehicle routing problems using a pre-trained graph neural network without actually solving the routing problems.
RL4CO: a Unified Reinforcement Learning for Combinatorial Optimization Library
To address these challenges, we introduce RL4CO, a unified Reinforcement Learning (RL) for Combinatorial Optimization (CO) library.
Generating Dispatching Rules for the Interrupting Swap-Allowed Blocking Job Shop Problem Using Graph Neural Network and Reinforcement Learning
The interrupting swap-allowed blocking job shop problem (ISBJSSP) is a complex scheduling problem that is able to model many manufacturing planning and logistics applications realistically by addressing both the lack of storage capacity and unforeseen production interruptions.
Learning context-aware adaptive solvers to accelerate quadratic programming
Convex quadratic programming (QP) is an important sub-field of mathematical optimization.
Development of AI-cloud based high-sensitivity wireless smart sensor for port structure monitoring
To overcome the complication, lots of research related to vibration-based monitoring system with sensor has been devised.
Neuro CROSS exchange: Learning to CROSS exchange to solve realistic vehicle routing problems
Inspired by CE, we propose Neuro CE (NCE), a fundamental operator of learned meta-heuristic, to solve various VRPs while overcoming the limitations of CE (i. e., the expensive $\mathcal{O}(n^4)$ search cost).
Meta-SysId: A Meta-Learning Approach for Simultaneous Identification and Prediction
In this paper, we propose Meta-SysId, a meta-learning approach to model sets of systems that have behavior governed by common but unknown laws and that differentiate themselves by their context.
Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimization
Deep reinforcement learning (DRL)-based combinatorial optimization (CO) methods (i. e., DRL-NCO) have shown significant merit over the conventional CO solvers as DRL-NCO is capable of learning CO solvers less relying on problem-specific expert domain knowledge (heuristic method) and supervised labeled data (supervised learning method).
A molecular hypergraph convolutional network with functional group information
We show that our model is able to outperform other baseline methods for most of the datasets.
Input Convex Graph Neural Networks: An Application to Optimal Control and Design Optimization
On the physical heat diffusion, we further apply ICGNN to solve a design optimization problem, which seeks to find the optimal heater allocations while considering the optimal operation of the heaters, by using a gradient-based method.
An Interpretable Web-based Glioblastoma Multiforme Prognosis Prediction Tool using Random Forest Model
Total 10, 4, and 13 features were extracted for best performing one-year survival/progression status RFC models and RSF model via the recursive feature elimination process.
Continuous-Depth Neural Models for Dynamic Graph Prediction
We introduce the framework of continuous-depth graph neural networks (GNNs).
ScheduleNet: Learn to solve multi-agent scheduling problems with reinforcement learning
We propose ScheduleNet, a RL-based real-time scheduler, that can solve various types of multi-agent scheduling problems.
Convergent Graph Solvers
We propose the convergent graph solver (CGS), a deep learning method that learns iterative mappings to predict the properties of a graph system at its stationary state (fixed point) with guaranteed convergence.
Learning to schedule job-shop problems: Representation and policy learning using graph neural network and reinforcement learning
In solving the formulated problem, the proposed framework employs a GNN to learn that node features that embed the spatial structure of the JSSP represented as a graph (representation learning) and derive the optimum scheduling policy that maps the embedded node features to the best scheduling action (policy learning).
ScheduleNet: Learn to Solve MinMax mTSP Using Reinforcement Learning with Delayed Reward
From the RL perspective, Minmax mTSP raises several significant challenges, such as the cooperation of multiple workers and the need for a well-engineered reward function.
Multi-step Estimation for Gradient-based Meta-learning
To validate our method, we experiment on meta-transfer learning and few-shot learning tasks for multiple settings.
Graph Neural Ordinary Differential Equations
We introduce the framework of continuous--depth graph neural networks (GNNs).
Domain-Agnostic Few-Shot Classification by Learning Disparate Modulators
Although few-shot learning research has advanced rapidly with the help of meta-learning, its practical usefulness is still limited because most of them assumed that all meta-training and meta-testing examples came from a single domain.
Discriminative Few-Shot Learning Based on Directional Statistics
Metric-based few-shot learning methods try to overcome the difficulty due to the lack of training examples by learning embedding to make comparison easy.
