Search Results for author:
Found 75 papers, 34 papers with code
Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation
To address these issues, we propose a framework that adaptively selects and aggregates knowledge from diverse LLMs to build a single, stronger model, avoiding the high memory overhead of ensemble and inflexible weight merging.
BioDSA-1K: Benchmarking Data Science Agents for Biomedical Research
We propose BioDSA-1K as a foundation for building and evaluating generalizable, trustworthy AI agents for biomedical discovery.
TrialPanorama: Database and Benchmark for Systematic Review and Design of Clinical Trials
This structured and ontology-grounded design enables TrialPanorama to serve as a unified, extensible resource for a wide range of clinical trial tasks, including trial planning, design, and summarization.
s3: You Don't Need That Much Data to Train a Search Agent via RL
Retrieval-augmented generation (RAG) systems empower large language models (LLMs) to access external knowledge during inference.
High-Precision Overlay Registration via Spatial-Terminal Iterative Learning in Roll-to-Roll Manufacturing
In this paper, we propose a Spatial-Terminal Iterative Learning Control (STILC) method integrated with PID control to iteratively learn and reduce registration error cycle-by-cycle, converging it to zero.
In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents
Large Language Models (LLMs) have made significant progress in open-ended dialogue, yet their inability to retain and retrieve relevant information from long-term interactions limits their effectiveness in applications requiring sustained personalization.
Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translation
To address this, we propose Magnet, a principled framework for synthesizing high-quality training trajectories to enhance the function calling capability of large language model agents in multi-turn conversations with humans.
DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning
We introduce DeepRetrieval, a reinforcement learning (RL) approach that trains LLMs for query generation through trial and error without supervised data (reference query).
PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving
Recent agent frameworks and inference-time algorithms often struggle with complex planning problems due to limitations in verifying generated plans or reasoning and varying complexity of instances within a single task.
Universal Model Routing for Efficient LLM Inference
Large language models' significant advances in capabilities are accompanied by significant increases in inference costs.
When One LLM Drools, Multi-LLM Collaboration Rules
This position paper argues that in many realistic (i. e., complex, contextualized, subjective) scenarios, one LLM is not enough to produce a reliable output.
Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems
We propose Heterogeneous Swarms, an algorithm to design multi-LLM systems by jointly optimizing model roles and weights.
A foundation model for human-AI collaboration in medical literature mining
Here, we present LEADS, an AI foundation model for study search, screening, and data extraction from medical literature.
Reverse Thinking Makes LLMs Stronger Reasoners
Reverse thinking plays a crucial role in human reasoning.
SynRL: Aligning Synthetic Clinical Trial Data with Human-preferred Clinical Endpoints Using Reinforcement Learning
In this paper, we propose SynRL which leverages reinforcement learning to improve the performance of patient data generators by customizing the generated data to meet the user-specified requirements for synthetic data outcomes and endpoints.
Can Large Language Models Replace Data Scientists in Biomedical Research?
To address this gap, we developed a benchmark of data science coding tasks derived from the analyses of 39 published studies.
A Perspective for Adapting Generalist AI to Specialized Medical AI Applications and Their Challenges
The integration of Large Language Models (LLMs) into medical applications has sparked widespread interest across the healthcare industry, from drug discovery and development to clinical decision support, assisting telemedicine, medical devices, and healthcare insurance applications.
Demystifying Large Language Models for Medicine: A Primer
We then review the strategies, such as prompt engineering and fine-tuning, to adapt standard LLMs to specialized medical tasks.
OmnixR: Evaluating Omni-modality Language Models on Reasoning across Modalities
To address this, OmnixR offers two evaluation variants: (1)synthetic subset: a synthetic dataset generated automatically by translating text into multiple modalities--audio, images, video, and hybrids (Omnify).
Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
Extensive experiments demonstrate that Model Swarms could flexibly adapt LLM experts to a single task, multi-task domains, reward models, as well as diverse human interests, improving over 12 model composition baselines by up to 21. 0% across tasks and contexts.
Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
To address these limitations, we introduce Speculative Knowledge Distillation (SKD), a novel approach that leverages cooperation between student and teacher models to generate high-quality training data on-the-fly while aligning with the student's inference-time distribution.
Accelerating Clinical Evidence Synthesis with Large Language Models
Here, we introduce TrialMind, a generative artificial intelligence (AI) pipeline for facilitating human-AI collaboration in three crucial tasks for evidence synthesis: study search, screening, and data extraction.
Panacea: A foundation model for clinical trial search, summarization, design, and recruitment
To address this challenge, we propose a clinical trial foundation model named Panacea, designed to handle multiple tasks, including trial search, trial summarization, trial design, and patient-trial matching.
Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization
Large language models (LLMs), even when specifically trained to process long input contexts, struggle to capture relevant information located in the middle of their input.
CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation
Grounded generation aims to equip language models (LMs) with the ability to produce more credible and accountable responses by accurately citing verifiable sources.
Continual Learning of Large Language Models: A Comprehensive Survey
In this survey, we provide a comprehensive overview of the current research progress on LLMs within the context of CL.
CodecLM: Aligning Language Models with Tailored Synthetic Data
To this end, we introduce CodecLM, a general framework for adaptively generating high-quality synthetic data for LLM alignment with different downstream instruction distributions and LLMs.
ADAPT to Robustify Prompt Tuning Vision Transformers
The performance of deep models, including Vision Transformers, is known to be vulnerable to adversarial attacks.
TriSum: Learning Summarization Ability from Large Language Models with Structured Rationale
To overcome this, we introduce TriSum, a framework for distilling LLMs' text summarization abilities into a compact, local model.
GenRES: Rethinking Evaluation for Generative Relation Extraction in the Era of Large Language Models
The field of relation extraction (RE) is experiencing a notable shift towards generative relation extraction (GRE), leveraging the capabilities of large language models (LLMs).
PILOT: Legal Case Outcome Prediction with Case Law
We demonstrate the importance of accurately identifying precedent cases and mitigating the temporal shift when making predictions for case law, as our method shows a significant improvement over the prior methods that focus on civil law case outcome predictions.
Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
We propose the Chain-of-Table framework, where tabular data is explicitly used in the reasoning chain as a proxy for intermediate thoughts.
Ranked #4 on
Table-based Fact Verification
on TabFact
BioBridge: Bridging Biomedical Foundation Models via Knowledge Graphs
Foundation models (FMs) are able to leverage large volumes of unlabeled data to demonstrate superior performance across a wide range of tasks.
UniPredict: Large Language Models are Universal Tabular Classifiers
Specifically, we train a single LLM on an aggregation of 169 tabular datasets with diverse targets and compare its performance against baselines that are trained on each dataset separately.
CITING: Large Language Models Create Curriculum for Instruction Tuning
Specifically, we employ a teacher LLM to create a curriculum for instruction tuning of the student LLM, namely Curriculum Instruction TunING (CITING).
LMDX: Language Model-based Document Information Extraction and Localization
The main obstacles to adopting LLMs for this task include the absence of layout encoding within LLMs, which is critical for high quality extraction, and the lack of a grounding mechanism to localize the predicted entities within the document.
MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models
Large language models (LLMs) have achieved remarkable performance in natural language understanding and generation tasks.
Matching Patients to Clinical Trials with Large Language Models
The TrialGPT-Ranking scores are highly correlated with human judgments and outperform the best-competing models by 43. 8% in ranking and excluding trials.
PyTrial: Machine Learning Software and Benchmark for Clinical Trial Applications
The code is available at https://github. com/RyanWangZf/PyTrial.
SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended)
Text-to-SQL, the process of translating natural language into Structured Query Language (SQL), represents a transformative application of large language models (LLMs), potentially revolutionizing how humans interact with data.
MediTab: Scaling Medical Tabular Data Predictors via Data Consolidation, Enrichment, and Refinement
Tabular data prediction has been employed in medical applications such as patient health risk prediction.
AutoTrial: Prompting Language Models for Clinical Trial Design
Clinical trials are critical for drug development.
DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning
Rehearsal-based approaches are a mainstay of continual learning (CL).
SPOT: Sequential Predictive Modeling of Clinical Trial Outcome with Meta-Learning
Accurate trial outcome prediction based on historical trial data promises better trial investment decisions and more trial success.
Robust Meta Learning for Image based tasks
However, learning such a model is not possible in standard machine learning frameworks as the distribution of the test data is unknown.
Invariant Meta Learning for Out-of-Distribution Generalization
Modern deep learning techniques have illustrated their excellent capabilities in many areas, but relies on large training data.
SAIF: Sparse Adversarial and Imperceptible Attack Framework
Adversarial attacks hamper the decision-making ability of neural networks by perturbing the input signal.
QueryForm: A Simple Zero-shot Form Entity Query Framework
Zero-shot transfer learning for document understanding is a crucial yet under-investigated scenario to help reduce the high cost involved in annotating document entities.
MedCLIP: Contrastive Learning from Unpaired Medical Images and Text
Existing vision-text contrastive learning like CLIP aims to match the paired image and caption embeddings while pushing others apart, which improves representation transferability and supports zero-shot prediction.
PromptEHR: Conditional Electronic Healthcare Records Generation with Prompt Learning
Accessing longitudinal multimodal Electronic Healthcare Records (EHRs) is challenging due to privacy concerns, which hinders the use of ML for healthcare applications.
Pruning Adversarially Robust Neural Networks without Adversarial Examples
Adversarial pruning compresses models while preserving robustness.
SparCL: Sparse Continual Learning on the Edge
SparCL achieves both training acceleration and accuracy preservation through the synergy of three aspects: weight sparsity, data efficiency, and gradient sparsity.
Artificial Intelligence for In Silico Clinical Trials: A Review
In silico trials are clinical trials conducted digitally through simulation and modeling as an alternative to traditional clinical trials.
Trial2Vec: Zero-Shot Clinical Trial Document Similarity Search using Self-Supervision
We propose a zero-shot clinical trial retrieval method, Trial2Vec, which learns through self-supervision without annotating similar clinical trials.
TransTab: Learning Transferable Tabular Transformers Across Tables
Can we leverage model pretraining on multiple distinct tables?
DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning
Continual learning aims to enable a single model to learn a sequence of tasks without catastrophic forgetting.
Deep Learning on Multimodal Sensor Data at the Wireless Edge for Vehicular Network
Beam selection for millimeter-wave links in a vehicular scenario is a challenging problem, as an exhaustive search among all candidate beam pairs cannot be assuredly completed within short contact times.
Learning to Prompt for Continual Learning
The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central challenge.
SurvTRACE: Transformers for Survival Analysis with Competing Events
In medicine, survival analysis studies the time duration to events of interest such as mortality.
PAC-Bayes Information Bottleneck
Then, we build an IIW-based information bottleneck on the trade-off between accuracy and information complexity of NNs, namely PIB.
Deep Bayesian Unsupervised Lifelong Learning
We develop a fully Bayesian inference framework for ULL with a novel end-to-end Deep Bayesian Unsupervised Lifelong Learning (DBULL) algorithm, which can progressively discover new clusters without forgetting the past with unlabelled data while learning latent representations.
Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness
We investigate the HSIC (Hilbert-Schmidt independence criterion) bottleneck as a regularizer for learning an adversarially robust deep neural network classifier.
Lifelong Learning based Disease Diagnosis on Clinical Notes
Current deep learning based disease diagnosis systems usually fall short in catastrophic forgetting, i. e., directly fine-tuning the disease diagnosis model on new tasks usually leads to abrupt decay of performance on previous tasks.
Open-World Class Discovery with Kernel Networks
We study an Open-World Class Discovery problem in which, given labeled training samples from old classes, we need to discover new classes from unlabeled test samples.
Learn-Prune-Share for Lifelong Learning
In lifelong learning, we wish to maintain and update a model (e. g., a neural network classifier) in the presence of new classification tasks that arrive sequentially.
Instance-wise Feature Grouping
Moreover, the features that belong to each group, and the important feature groups may vary per sample.
Finding Influential Instances for Distantly Supervised Relation Extraction
Distant supervision (DS) is a strong way to expand the datasets for enhancing relation extraction (RE) models but often suffers from high label noise.
Online Disease Self-diagnosis with Inductive Heterogeneous Graph Convolutional Networks
We propose a Healthcare Graph Convolutional Network (HealGCN) to offer disease self-diagnosis service for online users based on Electronic Healthcare Records (EHRs).
Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback
Counterfactual learning for dealing with missing-not-at-random data (MNAR) is an intriguing topic in the recommendation literature since MNAR data are ubiquitous in modern recommender systems.
On the Fairness of Randomized Trials for Recommendation with Heterogeneous Demographics and Beyond
Observed events in recommendation are consequence of the decisions made by a policy, thus they are usually selectively labeled, namely the data are Missing Not At Random (MNAR), which often causes large bias to the estimate of true outcomes risk.
Less Is Better: Unweighted Data Subsampling via Influence Function
In the time of Big Data, training complex models on large-scale data sets is challenging, making it appealing to reduce data volume for saving computation resources by subsampling.
Streaming Adaptive Nonparametric Variational Autoencoder
We develop a data driven approach to perform clustering and end-to-end feature learning simultaneously for streaming data that can adaptively detect novel clusters in emerging data.
Collaborative Deep Reinforcement Learning for Multi-Object Tracking
To address this, we develop a deep prediction-decision network in our C-DRL, which simultaneously detects and predicts objects under a unified network via deep reinforcement learning.
