Tianlong Chen

AudioTrust: Benchmarking The Multifaceted Trustworthiness of Audio Large Language Models

FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning

The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation

Probing to Refine: Reinforcement Distillation of LLM Reasoners via Explanatory Inversion

UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Decision-Making

Are We Merely Justifying Results ex Post Facto? Quantifying Explanatory Inversion in Post-Hoc Model Explanations

Can Large Language Models Assess and Reframe Psychological Attribution: A Benchmark and Analysis

Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder

Adaptive Thinking: Large Language Models Know When to Think in Latent Space

Select the Key, Then Generate the Rest: Improving Multi-Modal Learning with Limited Data Budget

DD-Ranking: Rethinking the Evaluation of Dataset Distillation

CellDuality: Unlocking Biological Reasoning in LLMs with Self-Supervised RLVR

Towards Global Expert-Level Mixed-Precision Quantization for Mixture-of-Experts LLMs

$GEM$: 3D Gaussian Splatting for Efficient and Accurate Cryo-EM Reconstruction

SPATIA: Multimodal Model for Prediction and Generation of Spatial Cell Phenotypes

TRUST: A Decentralized Framework for Auditing Large Language Model Reasoning

Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration

AsyncSpade: Efficient Test-Time Scaling with Asynchronous Sparse Decoding

Symbolic Mixture-of-Experts: Adaptive Skill-based Routing for Heterogeneous Reasoning

CAR-LoRA: Training Compression-Aware and Robust LoRA Adapters for Evolving LLMs

Learning Flexible Large Multimodal Models with Arbitrary Modality Combinations

AlphaFormer: End-to-End Symbolic Regression of Alpha Factors with Transformers

How Long Do Model Patches Last? A Temporal Perspective on PortLLM

DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillation

(Be Cautious!) Bio-Foundation Models Are Not Yet Robust to Biological Plausible Perturbations and ML Transformations

PPBOOST: PROGRESSIVE PROMPT BOOSTING FOR TEXT-DRIVEN MEDICAL IMAGE SEGMENTATION

The Adaptive Interrogator: Detecting Trojan LLMs in Multi-Agent Systems via Evolved Conversational Strategies

Adaptive Sensor Selection for Power Efficient 3D Object Detection on Autonomous Driving

Stable-SPAM: How to Stably Train Large Language Models in 4-Bit

Symbiotic Cooperation for Web Agents: Harnessing Complementary Strengths of Large and Small LLMs

Towards Personalized Parameter Generation via Data-Conditioned Mapping

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

Fit-LoRA: Fit Your LoRAs to Pruned LLMs Without Additional Training or Data

Scaffold–Substituent Differentiated Diffusion for Hierarchical Molecule Generation

Make Optimization Once and for All with Fine-grained Guidance

ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows

Calibrating the Voice of Doubt: How LLMs Diverge from Humans in Verbal Uncertainty

Can GRPO Help LLMs Transcend Their Pretraining Origin?

$EditCast3D$: Single-Frame-Guided 3D Editing with Video Propagation and View Selection

Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction

Beyond Invariance: A Feature-Strength Framework for OOD Generalization

$BetaConform$: Efficient MAP Estimation of LLM Ensemble Judgment Performance with Prior Transfer

Graph Sparsification via Mixture of Graphs

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

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

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

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

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

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

Multi-Agent Debate for LLM Judges with Adaptive Stability Detection

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

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

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

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

One Token Embedding Is Enough to Deadlock Your Large Reasoning Model

Composable Interventions for Language Models

$I$^2$MoE$: Interpretable Multimodal Interaction-aware Mixture-of-Experts

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

$UQ-Merge$: UNCERTAINTY GUIDED MULTIMODAL LARGE LANGUAGE MODEL MERGING

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

Beyond Fixed Resolution: Enhancing VLLMs with Adaptive Input Scaling

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

$LLaPA$: Harnessing Language Models for Protein Enzyme Function

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

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

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

Regularized Optimal Transport for Single-Cell Temporal Trajectory Analysis

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

Benchmark on Drug Target Interaction Modeling from a Structure Perspective

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

Glider: Global and Local Instruction-Driven Expert Router

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

GraphRCG: Self-Conditioned Graph Generation

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

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

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

FM-TS: Flow Matching for Time Series Generation

FairSkin: Fair Diffusion for Skin Disease Image Geneartion