Han Liu

On Differential Private $\ell_1$, $\ell_2$ and $\ell_p^p$ Distance Queries

Universal Approximation with Softmax Attention

In-Context Algorithm Emulation in Fixed-Weight Transformers

UNDERSTANDING TRANSFORMERS FOR TIME SERIES FORECASTING: A CASE STUDY ON MOIRAI

Capturing Uncertainty in Regression via Conditional Diffusion Models

Sci2Pol: Evaluating and Fine-tuning LLMs on Scientific-to-Policy Brief Generation

Spatial Mental Modeling from Limited Views

GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models

LOBBen-TM: A Benchmark Study of Limit Order Book Prediction with Temporal Modeling

Induction Head Implementation Across Diverse Transformer Weight Constructions

A Theoretical Analysis of Discrete Flow Matching Generative Models

Minimalist Softmax Attention Provably Learns Constrained Boolean Functions

MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse

Observational Scaling Laws in LLM-based Embodied Decision Making

Hopformer: Homogeneity-Pursuit Transformer for Time Series Forecasting

Unary Feedback as Observation: Incentivizing Self-Reflection in Large Language Models via Multi-Turn RL

Decoupled Alignment for Robust Plug-and-Play Adaptation

PromptFE: Automated Feature Engineering by Prompting

Are Hallucinations Bad Estimations?

Genome-Factory: A Library for Tuning, Deploying, and Interpreting Genomic Models

StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars

AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning

On Structured State-Space Duality

POLO: Preference-Guided Multi-Turn Reinforcement Learning for Lead Optimization

On Differentially Private String Distances

Conv-CoA: Open-domain Question Answering via Conversational Chain-of-Action with Hopfield Retriever

MathViz-Bench: Evaluating Text-to-Image Models on Visually Solving Math Problems

Pareto-Optimal Energy Alignment for Designing Nature-Like Antibodies

Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models

MetaFind: Scene-Aware 3D Asset Retrieval for Coherent Metaverse Scene Generation

Fast and Low-Cost Genomic Foundation Models via Outlier Removal

Investigating Hallucinations of Time Series Foundation Models through Signal Subspace Analysis

Attention Mechanism, Max-Affine Partition, and Universal Approximation

High-Order Flow Matching: Unified Framework and Sharp Statistical Rates

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency

On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality

In-Context Deep Learning via Transformer Models

In-Context Learning as Conditioned Associative Memory Retrieval

Nonparametric Modern Hopfield Models

Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models

DNABERT-S: Pioneering Species Differentiation with Species-Aware DNA Embeddings

BOOST: Enhanced Jailbreak of Large Language Model via Slient eos Tokens

SPARQ: Outlier-free SpeechLM with Fast Adaptation and Robust Quantization

Automated Feature Engineering by Prompting

Pretrained Transformers are Deep Optimizers: Provable In-Context Learning for Deep Model Training

AlignAb: Pareto-Optimal Energy Alignment for Designing Nature-Like Antibodies

On Differentially Private String Distances

Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?

Can Transformers Perform PCA ?

A Benchmark Study For Limit Order Book (LOB) Models and Time Series Forecasting Models on LOB Data

Explainable Sequential Optimization

Decoupled Alignment for Robust Plug-and-Play Adaptation

HeteGraph-Mamba: Heterogeneous Graph Learning via Selective State Space Model

Transformers Learn Bayesian Networks Autoregressively In-Context

GenomeOcean: Efficient Foundation Model for Genome Generation

SWGA: A Distributed Hyperparameter Search Method for Time Series Prediction Models

A Comprehensive Framework for Benchmarking Algorithms Across Hyperparameter Spaces

MambaFormer-MOE: Mamba-Transformer-based Mixture-of-Experts for Time Series Prediction

RDAS: A Low Latency and High Throughput Raw Data Engine for Machine Learning Systems