Tianlong Chen

~Tianlong_Chen1

论文总数

25.0

年均投稿

5.4

平均评分

接收情况21/50

会议分布

ICLR

NeurIPS

ICML

COLM

发表论文 (50 篇)

202537 篇

4.0

Evaluating topological fitness of human brain-inspired sub-circuits in Echo State Networks

ICLR 2025withdrawn

3.5

Receptor-Specific Diffusion Model: Towards Generating Protein-Protein Structures with Customized Perturbing and Sampling

ICLR 2025Rejected

6.5

Adapt-$\infty$: Scalable Continual Multimodal Instruction Tuning via Dynamic Data Selection

ICLR 2025Poster

6.8

BrainMoE: Cognition Joint Embedding via Mixture-of-Expert Towards Robust Brain Foundation Model

NeurIPS 2025Poster

4.6

Multimodal Graph-LLM: Leveraging Graph-Enhanced LLMs for Multimodal Healthcare Predictions

ICLR 2025withdrawn

3.5

Oldie but Goodie: Re-illuminating Label Propagation on Graphs with Partially Observed Features

ICLR 2025withdrawn

6.4

Multi-Agent Debate for LLM Judges with Adaptive Stability Detection

NeurIPS 2025Poster

4.8

Replicate and Quantize: A Plug-and-Play Strategy for Load Balancing in Sparse Mixture-of-Experts LLMs

ICLR 2025Rejected

4.3

Fantastic Experts and How to Find Them: A Multi-Dimensional Study for Experts-Level Sparsification in Mixture-of-Experts

ICLR 2025Rejected

5.5

$\texttt{UQ-Merge}$: UNCERTAINTY GUIDED MULTIMODAL LARGE LANGUAGE MODEL MERGING

ICLR 2025withdrawn

4.0

SCALE: Augmenting Content Analysis via LLM Agents and AI-Human Collaboration

ICLR 2025withdrawn

5.5

$\texttt{I$^2$MoE}$: Interpretable Multimodal Interaction-aware Mixture-of-Experts

ICML 2025Poster

6.0

One Token Embedding Is Enough to Deadlock Your Large Reasoning Model

NeurIPS 2025Poster

5.5

Sparse MoE as a New Retriever: Addressing Missing Modality Problem in Incomplete Multimodal Data

ICLR 2025Rejected

7.3

Graph Sparsification via Mixture of Graphs

ICLR 2025Spotlight

5.3

Beyond Fixed Resolution: Enhancing VLLMs with Adaptive Input Scaling

ICLR 2025withdrawn

3.5

Enhancing single-cell Multi-Modal Multi-Task Learning via Sparse Mixture-of-Experts

ICLR 2025withdrawn

4.3

Regularized Optimal Transport for Single-Cell Temporal Trajectory Analysis

ICLR 2025Rejected

3.0

FM-TS: Flow Matching for Time Series Generation

ICLR 2025Rejected

4.0

Glider: Global and Local Instruction-Driven Expert Router

ICLR 2025withdrawn

6.6

Occult: Optimizing Collaborative Communications across Experts for Accelerated Parallel MoE Training and Inference

ICML 2025Poster

6.3

PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches

ICLR 2025Poster

6.3

More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment

COLM 2025Poster

6.1

Modalities Contribute Unequally: Enhancing Medical Multi-modal Learning through Adaptive Modality Token Re-balancing

ICML 2025Poster

7.0

Mozart: Modularized and Efficient MoE Training on 3.5D Wafer-Scale Chiplet Architectures

NeurIPS 2025Spotlight

4.5

Toward Generalizability of Graph-based Imputation on Biomedical Tabular-based Missing Data

ICLR 2025withdrawn

7.2

G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks

ICML 2025Spotlight

7.8

$\texttt{BetaConform}$: Efficient MAP Estimation of LLM Ensemble Judgment Performance with Prior Transfer

NeurIPS 2025Poster

6.0

Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems

ICLR 2025Poster

3.0

FairSkin: Fair Diffusion for Skin Disease Image Geneartion

ICLR 2025withdrawn

7.0

Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility

ICLR 2025Poster

5.8

Composable Interventions for Language Models

ICLR 2025Poster

5.5

Understanding Prejudice and Fidelity of Diverge-to-Converge Multi-Agent Systems

ICLR 2025Rejected

202413 篇

6.0

Tuning-Free Accountable Intervention for LLM Deployment - A Metacognitive Approach

ICLR 2024Rejected

5.7

Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At Once

ICLR 2024Rejected

7.5

Sparse MoE with Language Guided Routing for Multilingual Machine Translation

ICLR 2024Poster

5.6

($\texttt{PEEP}$) $\textbf{P}$redicting $\textbf{E}$nzym$\textbf{e}$ $\textbf{P}$romiscuity with its Molecule Mate – an Attentive Metric Learning Solution

ICLR 2024Rejected

7.0

GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning

NeurIPS 2024Poster

5.3

Sparse MoE as a New Treatment: Addressing Forgetting, Fitting, Learning Issues in Multi-Modal Multi-Task Learning

ICLR 2024Rejected

4.5

Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective

ICLR 2024Rejected

3.7

Regularized Optimal Transport for Temporal Trajectory Analysis in Single-Cell Data

ICLR 2024Rejected

6.3

Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy

ICLR 2024Spotlight

5.2

Toward Generalizability of Graph-based Imputation on Bio-Medical Missing Data

ICLR 2024Rejected

5.8

($\texttt{PASS}$) Visual Prompt Locates Good Structure Sparisty through a Recurent HyperNetwork

ICLR 2024Rejected

6.0

GTBench: Uncovering the Strategic Reasoning Capabilities of LLMs via Game-Theoretic Evaluations

NeurIPS 2024Poster

6.3

Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts

NeurIPS 2024Spotlight

合作者 (20)

Tianlong Chen

发表论文 (50 篇)

202537 篇

Evaluating topological fitness of human brain-inspired sub-circuits in Echo State Networks

Receptor-Specific Diffusion Model: Towards Generating Protein-Protein Structures with Customized Perturbing and Sampling

Adapt-$\infty$: Scalable Continual Multimodal Instruction Tuning via Dynamic Data Selection

BrainMoE: Cognition Joint Embedding via Mixture-of-Expert Towards Robust Brain Foundation Model

Examining Post-Training Quantization for Mixture-of-Experts: A Benchmark

Benchmark on Drug Target Interaction Modeling from a Structure Perspective

GraphRCG: Self-Conditioned Graph Generation

$\texttt{LLaPA}$: Harnessing Language Models for Protein Enzyme Function

Multimodal Graph-LLM: Leveraging Graph-Enhanced LLMs for Multimodal Healthcare Predictions

Oldie but Goodie: Re-illuminating Label Propagation on Graphs with Partially Observed Features

Multi-Agent Debate for LLM Judges with Adaptive Stability Detection

Replicate and Quantize: A Plug-and-Play Strategy for Load Balancing in Sparse Mixture-of-Experts LLMs

Fantastic Experts and How to Find Them: A Multi-Dimensional Study for Experts-Level Sparsification in Mixture-of-Experts

$\texttt{UQ-Merge}$: UNCERTAINTY GUIDED MULTIMODAL LARGE LANGUAGE MODEL MERGING

SCALE: Augmenting Content Analysis via LLM Agents and AI-Human Collaboration

$\texttt{I$^2$MoE}$: Interpretable Multimodal Interaction-aware Mixture-of-Experts

One Token Embedding Is Enough to Deadlock Your Large Reasoning Model

Sparse MoE as a New Retriever: Addressing Missing Modality Problem in Incomplete Multimodal Data

Graph Sparsification via Mixture of Graphs

Beyond Fixed Resolution: Enhancing VLLMs with Adaptive Input Scaling

Enhancing single-cell Multi-Modal Multi-Task Learning via Sparse Mixture-of-Experts

Regularized Optimal Transport for Single-Cell Temporal Trajectory Analysis

FM-TS: Flow Matching for Time Series Generation

Glider: Global and Local Instruction-Driven Expert Router

Occult: Optimizing Collaborative Communications across Experts for Accelerated Parallel MoE Training and Inference

PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches

More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment

Modalities Contribute Unequally: Enhancing Medical Multi-modal Learning through Adaptive Modality Token Re-balancing

Mozart: Modularized and Efficient MoE Training on 3.5D Wafer-Scale Chiplet Architectures

Toward Generalizability of Graph-based Imputation on Biomedical Tabular-based Missing Data

G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks

$\texttt{BetaConform}$: Efficient MAP Estimation of LLM Ensemble Judgment Performance with Prior Transfer

Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems

FairSkin: Fair Diffusion for Skin Disease Image Geneartion

Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility

Composable Interventions for Language Models

Understanding Prejudice and Fidelity of Diverge-to-Converge Multi-Agent Systems

202413 篇

Tuning-Free Accountable Intervention for LLM Deployment - A Metacognitive Approach

Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At Once

Sparse MoE with Language Guided Routing for Multilingual Machine Translation

($\texttt{PEEP}$) $\textbf{P}$redicting $\textbf{E}$nzym$\textbf{e}$ $\textbf{P}$romiscuity with its Molecule Mate – an Attentive Metric Learning Solution

GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning

Sparse MoE as a New Treatment: Addressing Forgetting, Fitting, Learning Issues in Multi-Modal Multi-Task Learning

Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective

Regularized Optimal Transport for Temporal Trajectory Analysis in Single-Cell Data

Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy

Toward Generalizability of Graph-based Imputation on Bio-Medical Missing Data

($\texttt{PASS}$) Visual Prompt Locates Good Structure Sparisty through a Recurent HyperNetwork

GTBench: Uncovering the Strategic Reasoning Capabilities of LLMs via Game-Theoretic Evaluations

Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts