Search Results for author:
Found 56 papers, 23 papers with code
Reducing Distributional Uncertainty by Mutual Information Maximisation and Transferable Feature Learning
Distributional uncertainty exists broadly in many real-world applications, one of which in the form of domain discrepancy.
Autellix: An Efficient Serving Engine for LLM Agents as General Programs
Large language model (LLM) applications are evolving beyond simple chatbots into dynamic, general-purpose agentic programs, which scale LLM calls and output tokens to help AI agents reason, explore, and solve complex tasks.
Automating Prompt Leakage Attacks on Large Language Models Using Agentic Approach
We define prompt leakage as a critical threat to secure LLM deployment and introduce a framework for testing the robustness of LLMs using agentic teams.
NLGR: Utilizing Neighbor Lists for Generative Rerank in Personalized Recommendation Systems
To address these issues, we propose a utilizing Neighbor Lists model for Generative Reranking (NLGR), which aims to improve the performance of the generator in the combinatorial space.
AnimateAnything: Consistent and Controllable Animation for Video Generation
We present a unified controllable video generation approach AnimateAnything that facilitates precise and consistent video manipulation across various conditions, including camera trajectories, text prompts, and user motion annotations.
EcoAct: Economic Agent Determines When to Register What Action
Recent advancements have enabled Large Language Models (LLMs) to function as agents that can perform actions using external tools.
Steering Large Language Models between Code Execution and Textual Reasoning
Textual reasoning has inherent limitations in solving tasks with challenges in math, logics, optimization, and searching, which is unlikely to be solved by simply scaling up the model and data size.
Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface
Agents, as user-centric tools, are increasingly deployed for human task delegation, assisting with a broad spectrum of requests by generating thoughts, engaging with user proxies, and producing action plans.
AutoGen Studio: A No-Code Developer Tool for Building and Debugging Multi-Agent Systems
Multi-agent systems, where multiple agents (generative AI models + tools) collaborate, are emerging as an effective pattern for solving long-running, complex tasks in numerous domains.
Adaptive In-conversation Team Building for Language Model Agents
Leveraging multiple large language model (LLM) agents has shown to be a promising approach for tackling complex tasks, while the effective design of multiple agents for a particular application remains an art.
Assessing and Verifying Task Utility in LLM-Powered Applications
The rapid development of Large Language Models (LLMs) has led to a surge in applications that facilitate collaboration among multiple agents, assisting humans in their daily tasks.
Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
Large language models (LLMs) excel in most NLP tasks but also require expensive cloud servers for deployment due to their size, while smaller models that can be deployed on lower cost (e. g., edge) devices, tend to lag behind in terms of response quality.
Text-Driven Diverse Facial Texture Generation via Progressive Latent-Space Refinement
SDS boosts GANs with more generative modes, while GANs promote more efficient optimization of SDS.
Budget-aware Query Tuning: An AutoML Perspective
We further extend our study from tuning a single query to tuning a workload with multiple queries, and we call this generalized problem budget-aware workload tuning (WT), which aims for minimizing the execution time of the entire workload.
Mora: Enabling Generalist Video Generation via A Multi-Agent Framework
Existing open-source methods struggle to achieve comparable performance, often hindered by ineffective agent collaboration and inadequate training data quality.
StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows
In StateFlow, we distinguish between "process grounding" (via state and state transitions) and "sub-task solving" (through actions within a state), enhancing control and interpretability of the task-solving procedure.
Offline Training of Language Model Agents with Functions as Learnable Weights
Researchers and practitioners have recently reframed powerful Large Language Models (LLMs) as agents, enabling them to automate complex tasks largely via the use of specialized functions.
Towards better Human-Agent Alignment: Assessing Task Utility in LLM-Powered Applications
The rapid development in the field of Large Language Models (LLMs) has led to a surge in applications that facilitate collaboration among multiple agents to assist humans in their daily tasks.
Spatio-temporal Prompting Network for Robust Video Feature Extraction
Then, these video prompts are prepended to the patch embeddings of the current frame as the updated input for video feature extraction.
EcoAssistant: Using LLM Assistant More Affordably and Accurately
Today, users ask Large language models (LLMs) as assistants to answer queries that require external knowledge; they ask about the weather in a specific city, about stock prices, and even about where specific locations are within their neighborhood.
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks.
Instruction Mining: Instruction Data Selection for Tuning Large Language Models
Large language models (LLMs) are initially pretrained for broad capabilities and then finetuned with instruction-following datasets to improve their performance in interacting with humans.
MathChat: Converse to Tackle Challenging Math Problems with LLM Agents
Employing Large Language Models (LLMs) to address mathematical problems is an intriguing research endeavor, considering the abundance of math problems expressed in natural language across numerous science and engineering fields.
HyperTime: Hyperparameter Optimization for Combating Temporal Distribution Shifts
In this work, we propose a hyperparameter optimization method named \emph{HyperTime} to find hyperparameters robust to potential temporal distribution shifts in the unseen test data.
CF-Font: Content Fusion for Few-shot Font Generation
Content and style disentanglement is an effective way to achieve few-shot font generation.
Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference
Large Language Models (LLMs) have sparked significant interest in their generative capabilities, leading to the development of various commercial applications.
ACE: Adaptive Constraint-aware Early Stopping in Hyperparameter Optimization
Deploying machine learning models requires high model quality and needs to comply with application constraints.
Mining Robust Default Configurations for Resource-constrained AutoML
Automatic machine learning (AutoML) is a key enabler of the mass deployment of the next generation of machine learning systems.
Bounding the Last Mile: Efficient Learned String Indexing
RSS achieves this by using the minimal string prefix to sufficiently distinguish the data unlike most learned approaches which index the entire string.
FairAutoML: Embracing Unfairness Mitigation in AutoML
In this work, we propose an Automated Machine Learning (AutoML) system to search for models not only with good prediction accuracy but also fair.
Geometry Attention Transformer with Position-aware LSTMs for Image Captioning
In recent years, transformer structures have been widely applied in image captioning with impressive performance.
An Empirical Study on Hyperparameter Optimization for Fine-Tuning Pre-trained Language Models
We find that using the same time budget, HPO often fails to outperform grid search due to two reasons: insufficient time budget and overfitting.
ChaCha for Online AutoML
We propose the ChaCha (Champion-Challengers) algorithm for making an online choice of hyperparameters in online learning settings.
Attention-guided Temporally Coherent Video Object Matting
Experimental results show that our method can generate high-quality alpha mattes for various videos featuring appearance change, occlusion, and fast motion.
Active Boundary Loss for Semantic Segmentation
This paper proposes a novel active boundary loss for semantic segmentation.
DynaTune: Dynamic Tensor Program Optimization in Deep Neural Network Compilation
Recently, the DL compiler, together with Learning to Compile has proven to be a powerful technique for optimizing deep learning models.
ECONOMIC HYPERPARAMETER OPTIMIZATION WITH BLENDED SEARCH STRATEGY
We study the problem of using low cost to search for hyperparameter configurations in a large search space with heterogeneous evaluation cost and model quality.
AdaTune: Adaptive Tensor Program Compilation Made Efficient
Deep learning models are computationally intense, and implementations often have to be highly optimized by experts or hardware vendors to be usable in practice.
A Matrix Chernoff Bound for Markov Chains and Its Application to Co-occurrence Matrices
Our result gives the first bound on the convergence rate of the co-occurrence matrix and the first sample complexity analysis in graph representation learning.
Faster Graph Embeddings via Coarsening
As computing Schur complements is expensive, we give a nearly-linear time algorithm that generates a coarsened graph on the relevant vertices that provably matches the Schur complement in expectation in each iteration.
Frugal Optimization for Cost-related Hyperparameters
To address this problem, we develop a new cost-frugal HPO solution.
Qd-tree: Learning Data Layouts for Big Data Analytics
For a given workload, however, such techniques are unable to optimize for the important metric of the number of blocks accessed by a query.
Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks
For multi-domain DST, the data sparsity problem is also a major obstacle due to the increased number of state candidates.
Ranked #12 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.1
TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural Network
Taxonomies consist of machine-interpretable semantics and provide valuable knowledge for many web applications.
FLAML: A Fast and Lightweight AutoML Library
We study the problem of using low computational cost to automate the choices of learners and hyperparameters for an ad-hoc training dataset and error metric, by conducting trials of different configurations on the given training data.
NetSMF: Large-Scale Network Embedding as Sparse Matrix Factorization
Previous research shows that 1) popular network embedding benchmarks, such as DeepWalk, are in essence implicitly factorizing a matrix with a closed form, and 2)the explicit factorization of such matrix generates more powerful embeddings than existing methods.
ALEX: An Updatable Adaptive Learned Index
The original work by Kraska et al. shows that a learned index beats a B+Tree by a factor of up to three in search time and by an order of magnitude in memory footprint.
Selectivity Estimation for Range Predicates using Lightweight Models
Query optimizers depend on selectivity estimates of query predicates to produce a good execution plan.
ABC: Efficient Selection of Machine Learning Configuration on Large Dataset
A machine learning configuration refers to a combination of preprocessor, learner, and hyperparameters.
Identifying Outlier Arms in Multi-Armed Bandit
Outlier detection is a powerful method to narrow down the attention to a few objects after the data for them are collected.
Identifying Semantically Deviating Outlier Documents
A document outlier is a document that substantially deviates in semantics from the majority ones in a corpus.
Scalable Topical Phrase Mining from Text Corpora
Our solution combines a novel phrase mining framework to segment a document into single and multi-word phrases, and a new topic model that operates on the induced document partition.
Scalable and Robust Construction of Topical Hierarchies
Automated generation of high-quality topical hierarchies for a text collection is a dream problem in knowledge engineering with many valuable applications.
KERT: Automatic Extraction and Ranking of Topical Keyphrases from Content-Representative Document Titles
We introduce KERT (Keyphrase Extraction and Ranking by Topic), a framework for topical keyphrase generation and ranking.
