Julian McAuley

How to train data-efficient LLMs

Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions

FASA: FREQUENCY-AWARE SPARSE ATTENTION

MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization

Steering Autoregressive Music Generation with Recursive Feature Machines

Importance Sampling for Multi-Negative Multimodal Direct Preference Optimization

BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses

AMPS: Adaptive Modality Preference Steering via Functional Entropy

Token-Efficient Item Representation via Images for LLM Recommender Systems

MEM-$\alpha$: LEARNING MEMORY CONSTRUCTION VIA REINFORCEMENT LEARNING

GSPRec: Temporal-Aware Graph Spectral Filtering for Recommendation

FERA: Uncertainty-aware Federated Reasoning for Large Language Models

Pctx: Tokenizing Personalized Context for Generative Recommendation

WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization

Contextual Bandits with LLM-Derived Priors and Adaptive Calibration

Presto! Distilling Steps and Layers for Accelerating Music Generation

In-context Ranking Preference Optimization

Listwise Preference Diffusion Optimization for User Behavior Trajectories Prediction

OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models

REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing

Traceable and Explainable Multimodal Large Language Models: An Information-Theoretic View

M+: Extending MemoryLLM with Scalable Long-Term Memory

ActionPiece: Contextually Tokenizing Action Sequences for Generative Recommendation

Large Scale Knowledge Washing

Mastering Task Arithmetic: $\tau$Jp as a Key Indicator for Weight Disentanglement

A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models

Self-Updatable Large Language Models by Integrating Context into Model Parameters

TeaserGen: Generating Teasers for Long Documentaries

CoMMIT: Coordinated Instruction Tuning for Multimodal Large Language Models