Search Results for author:
Found 43 papers, 29 papers with code
RePO: ReLU-based Preference Optimization
Aligning large language models (LLMs) with human preferences is critical for real-world deployment, yet existing methods like RLHF face computational and stability challenges.
Bizard: A Community-Driven Platform for Accelerating and Enhancing Biomedical Data Visualization
Bizard is a novel visualization code repository designed to simplify data analysis in biomedical research.
Automated Hypothesis Validation with Agentic Sequential Falsifications
Hypotheses are central to information acquisition, decision-making, and discovery.
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1.
Ranked #1 on
Multi-task Language Understanding
on MMLU
(using extra training data)
Future-Conditioned Recommendations with Multi-Objective Controllable Decision Transformer
Our empirical findings emphasize the controllable recommendation strategy's ability to produce item sequences according to different objectives while maintaining performance that is competitive with current recommendation strategies across various objectives.
DeepSeek-V3 Technical Report
We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
SPRec: Leveraging Self-Play to Debias Preference Alignment for Large Language Model-based Recommendations
Large language models (LLMs) have attracted significant attention in recommendation systems.
Toward Generalizing Visual Brain Decoding to Unseen Subjects
Prior works typically focus on decoding brain activity of individuals based on the observation that different subjects exhibit different brain activities, while it remains unclear whether brain decoding can be generalized to unseen subjects.
MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts
LLM Unlearning, a post-hoc approach to remove this information from trained LLMs, offers a promising solution to mitigate these risks.
RelBench: A Benchmark for Deep Learning on Relational Databases
We use RelBench to conduct the first comprehensive study of Relational Deep Learning (RDL) (Fey et al., 2024), which combines graph neural network predictive models with (deep) tabular models that extract initial entity-level representations from raw tables.
TrialBench: Multi-Modal Artificial Intelligence-Ready Clinical Trial Datasets
Clinical trials are pivotal for developing new medical treatments, yet they typically pose some risks such as patient mortality, adverse events, and enrollment failure that waste immense efforts spanning over a decade.
ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models
Inspired by the awesome development of role-playing agents, we propose an ESC Evaluation framework (ESC-Eval), which uses a role-playing agent to interact with ESC models, followed by a manual evaluation of the interactive dialogues.
AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning
Large language model (LLM) agents have demonstrated impressive capabilities in utilizing external tools and knowledge to boost accuracy and reduce hallucinations.
Optimizing Large Model Training through Overlapped Activation Recomputation
Our comprehensive evaluation using GPT models with 1. 3B-20B parameters shows that both OPT and HEU outperform the state-of-the-art recomputation approaches (e. g., Megatron-LM and Checkmake) by 1. 02-1. 53x.
MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
In this paper, we present MLLMGuard, a multidimensional safety evaluation suite for MLLMs, including a bilingual image-text evaluation dataset, inference utilities, and a lightweight evaluator.
BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments
Agents based on large language models have shown great potential in accelerating scientific discovery by leveraging their rich background knowledge and reasoning capabilities.
STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases
To address the gap, we develop STARK, a large-scale Semi-structure retrieval benchmark on Textual and Relational Knowledge Bases.
From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities
Multi-modal Large Language Models (MLLMs) have shown impressive abilities in generating reasonable responses with respect to multi-modal contents.
Relational Deep Learning: Graph Representation Learning on Relational Databases
The core idea is to view relational databases as a temporal, heterogeneous graph, with a node for each row in each table, and edges specified by primary-foreign key links.
Flames: Benchmarking Value Alignment of LLMs in Chinese
The widespread adoption of large language models (LLMs) across various regions underscores the urgent need to evaluate their alignment with human values.
Fake Alignment: Are LLMs Really Aligned Well?
The growing awareness of safety concerns in large language models (LLMs) has sparked considerable interest in the evaluation of safety.
Alleviating Matthew Effect of Offline Reinforcement Learning in Interactive Recommendation
Through theoretical analyses, we find that the conservatism of existing methods fails in pursuing users' long-term satisfaction.
Enabling tabular deep learning when $d \gg n$ with an auxiliary knowledge graph
However, for tabular datasets with extremely high $d$-dimensional features but limited $n$ samples (i. e. $d \gg n$), machine learning models struggle to achieve strong performance due to the risk of overfitting.
Uncertainty Quantification over Graph with Conformalized Graph Neural Networks
We establish a permutation invariance condition that enables the validity of CP on graph data and provide an exact characterization of the test-time coverage.
Learn to Explore: on Bootstrapping Interactive Data Exploration with Meta-learning
The process of data exploration can be viewed as the process of training a classifier, which determines whether a database tuple is interesting to a user.
TuneUp: A Simple Improved Training Strategy for Graph Neural Networks
Extensive evaluation of TuneUp on five diverse GNN architectures, three types of prediction tasks, and both transductive and inductive settings shows that TuneUp significantly improves the performance of the base GNN on tail nodes, while often even improving the performance on head nodes.
Adaptive Pseudo-labeling for Quantum Calculations
Machine learning models have recently shown promise in predicting molecular quantum chemical properties.
Machine Learning Applications for Therapeutic Tasks with Genomics Data
Thanks to the increasing availability of genomics and other biomedical data, many machine learning approaches have been proposed for a wide range of therapeutic discovery and development tasks.
Graph Representation Learning in Biomedicine
Biomedical networks (or graphs) are universal descriptors for systems of interacting elements, from molecular interactions and disease co-morbidity to healthcare systems and scientific knowledge.
Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development
Here, we introduce Therapeutics Data Commons (TDC), the first unifying platform to systematically access and evaluate machine learning across the entire range of therapeutics.
Ranked #4 on
TDC ADMET Benchmarking Group
on tdcommons
HINT: Hierarchical Interaction Network for Trial Outcome Prediction Leveraging Web Data
Next, these embeddings will be fed into the knowledge embedding module to generate knowledge embeddings that are pretrained using external knowledge on pharmaco-kinetic properties and trial risk from the web.
An Interpretable End-to-end Fine-tuning Approach for Long Clinical Text
Unstructured clinical text in EHRs contains crucial information for applications including decision support, trial matching, and retrospective research.
MolDesigner: Interactive Design of Efficacious Drugs with Deep Learning
The efficacy of a drug depends on its binding affinity to the therapeutic target and pharmacokinetics.
SumGNN: Multi-typed Drug Interaction Prediction via Efficient Knowledge Graph Summarization
Furthermore, most previous works focus on binary DDI prediction whereas the multi-typed DDI pharmacological effect prediction is a more meaningful but harder task.
scGNN: scRNA-seq Dropout Imputation via Induced Hierarchical Cell Similarity Graph
Single-cell RNA sequencing provides tremendous insights to understand biological systems.
Graph Meta Learning via Local Subgraphs
G-Meta learns how to quickly adapt to a new task using only a handful of nodes or edges in the new task and does so by learning from data points in other graphs or related, albeit disjoint label sets.
SkipGNN: Predicting Molecular Interactions with Skip-Graph Networks
Here, we present SkipGNN, a graph neural network approach for the prediction of molecular interactions.
MolTrans: Molecular Interaction Transformer for Drug Target Interaction Prediction
Drug target interaction (DTI) prediction is a foundational task for in silico drug discovery, which is costly and time-consuming due to the need of experimental search over large drug compound space.
DeepPurpose: a Deep Learning Library for Drug-Target Interaction Prediction
Accurate prediction of drug-target interactions (DTI) is crucial for drug discovery.
Ranked #2 on
Drug Discovery
on KIBA
Clinical XLNet: Modeling Sequential Clinical Notes and Predicting Prolonged Mechanical Ventilation
Clinical notes contain rich data, which is unexploited in predictive modeling compared to structured data.
CASTER: Predicting Drug Interactions with Chemical Substructure Representation
Adverse drug-drug interactions (DDIs) remain a leading cause of morbidity and mortality.
ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission
Clinical notes contain information about patients that goes beyond structured data like lab values and medications.
EpiRL: A Reinforcement Learning Agent to Facilitate Epistasis Detection
Epistasis (gene-gene interaction) is crucial to predicting genetic disease.
