Dongsheng Li

Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization

Improving Diffusion Models for Class-imbalanced Training Data via Capacity Manipulation

Online Pseudo-Zeroth-Order Training of Neuromorphic Spiking Neural Networks

Exploring Interpretability for Visual Prompt Tuning with Cross-layer Concepts

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Reasoning-Driven Multimodal LLM for Domain Generalization

Joint Adaptation of Uni-modal Foundation Models for Multi-modal Alzheimer's Disease Diagnosis

EgoBrain: Synergizing Minds and Eyes For Human Action Understanding

Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading

SortedRL: Accelerating RL Training for LLMs through Online Length-aware Scheduling

What are Key Factors for Updates in RL for LLM Reasoning?

Context-Aware Alignment: Adapting Large Language Models to Individual Historical Data

Architectural Plasticity for Continual Learning

What Makes a Good Diffusion Planner for Decision Making?

Accelerating Block Coordinate Descent for LLM Finetuning via Landscape Expansion

Learning to Instruct for Visual Instruction Tuning

Toward Relative Positional Encoding in Spiking Transformers

How Do Large Language Models Understand Graph Patterns? A Benchmark for Graph Pattern Comprehension

MMInference: Accelerating Pre-filling for Long-Context Visual Language Models via Modality-Aware Permutation Sparse Attention

Chain-of-Model Learning for Language Model

SCBench: A KV Cache-Centric Analysis of Long-Context Methods

Omni-DNA: A Genomic Model Supporting Sequence Understanding, Long-context, and Textual Annotation

SimSort: A Data-Driven Framework for Spike Sorting by Large-Scale Electrophysiology Simulation

pMoE: Prompting Diverse Experts Together Wins More in Visual Adaptation

NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals

Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model Inference

DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation

Is classification all you need for radiology report generation?

Habitizing Diffusion Planning for Efficient and Effective Decision Making

Accelerating Block Coordinate Descent for LLM Finetuning via Landscape Correction

SeCom: On Memory Construction and Retrieval for Personalized Conversational Agents

Stand on Two Shoulders: Dynamically Merging Tokens from General and Medical Experts

Mitigate Position Bias in Large Language Models via Scaling a Single Dimension

Large Learning Rates without the Agonizing Pain: Dispelling the Curse of Singularities in Deep Neural Networks

Learning Robust Representations for Medical Images via Unifying (Self-)Supervisions

Protecting Minorities in Diffusion Models via Capacity Allocation

Efficiently pre-training language models with mixtures of cluster-oriented, trainability-aware experts

Benchmark Dataset for Radiology Report Generation with Instructions and Contexts

The VEP Booster: A Closed-Loop AI System for Visual EEG Biomarker Auto-generation

Sparse Training: Do All Tokens Matter for Long Sequence Generalization?