PaperHub

Dongsheng Li

~Dongsheng_Li2

45
论文总数
22.5
年均投稿
5.7
平均评分
接收情况26/45
会议分布
ICLR
29
NeurIPS
13
ICML
3

发表论文 (45 篇)

202527 篇

4.5
4

Protecting Minorities in Diffusion Models via Capacity Allocation

ICLR 2025withdrawn
6.3
4

pMoE: Prompting Diverse Experts Together Wins More in Visual Adaptation

ICLR 2025Poster
5.5
4

Habitizing Diffusion Planning for Efficient and Effective Decision Making

ICML 2025Poster
5.3
4

Accelerating Block Coordinate Descent for LLM Finetuning via Landscape Correction

ICLR 2025Rejected
7.3
4

Accelerating Block Coordinate Descent for LLM Finetuning via Landscape Expansion

NeurIPS 2025Poster
6.4
5

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

NeurIPS 2025Poster
6.3
4

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

ICLR 2025Poster
7.5
4

What Makes a Good Diffusion Planner for Decision Making?

ICLR 2025Spotlight
4.8
4

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

ICLR 2025Rejected
3.5
4

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

ICLR 2025withdrawn
5.8
4

DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation

ICLR 2025Poster
7.3
4

Learning to Instruct for Visual Instruction Tuning

NeurIPS 2025Poster
6.4
4

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

NeurIPS 2025Poster
4.8
4

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

ICLR 2025Rejected
5.3
4

SeCom: On Memory Construction and Retrieval for Personalized Conversational Agents

ICLR 2025Poster
7.3
4

Toward Relative Positional Encoding in Spiking Transformers

NeurIPS 2025Spotlight
7.0
4

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

ICLR 2025Poster
3.8
4

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

ICLR 2025withdrawn
6.5
6

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

ICLR 2025Poster
7.0
3

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

ICML 2025Poster
4.4
5

Benchmark Dataset for Radiology Report Generation with Instructions and Contexts

ICLR 2025Rejected
4.8
4

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

ICLR 2025withdrawn
4.4
5

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

ICLR 2025withdrawn
5.8
4

Is classification all you need for radiology report generation?

ICLR 2025Rejected
6.1
4

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

ICML 2025Poster
4.6
5

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

ICLR 2025Rejected
6.8
4

Chain-of-Model Learning for Language Model

NeurIPS 2025Poster

202418 篇

4.8
4

LSPT: Long-term Spatial Prompt Tuning for Visual Representation Learning

ICLR 2024Rejected
5.8
4

Addressing Signal Delay in Deep Reinforcement Learning

ICLR 2024Spotlight
5.5
4

Enhancing Mutual Information Estimation in Self-Interpretable Graph Neural Networks

ICLR 2024Rejected
5.8
5

LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression

ICLR 2024Rejected
6.0
4

Towards Editing Time Series

NeurIPS 2024Poster
4.5
4

Holmex: Human-Guided Spurious Correlation Detection and Black-box Model Fixing

ICLR 2024Rejected
5.8
5

CNN Kernels Can Be the Best Shapelets

ICLR 2024Poster
6.5
4

Advancing Spiking Neural Networks for Sequential Modeling with Central Pattern Generators

NeurIPS 2024Spotlight
5.5
4

Understanding and Improving Training-free Loss-based Diffusion Guidance

NeurIPS 2024Poster
4.8
4

EEG2Video: Towards Decoding Dynamic Visual Perception from EEG Signals

NeurIPS 2024Poster
4.3
4

Toward Open-ended Embodied Tasks Solving

ICLR 2024Rejected
5.3
4

Unified Medical Image Pre-training in Language-Guided Common Semantic Space

ICLR 2024Rejected
6.5
4

Training-free Multi-objective Diffusion Model for 3D Molecule Generation

ICLR 2024Poster
4.8
4

TaskBench: Benchmarking Large Language Models for Task Automation

ICLR 2024Rejected
6.0
5

Once Read is Enough: Domain-specific Pretraining-free Language Models with Cluster-guided Sparse Experts for Long-tail Domain Knowledge

NeurIPS 2024Poster
5.2
5

Large Multimodal Model for Real-World Radiology Report Generation

ICLR 2024Rejected
7.0
4

MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention

NeurIPS 2024Spotlight
5.8
4

Can Graph Learning Improve Planning in LLM-based Agents?

NeurIPS 2024Poster
合作者 (20)