PaperHub
影响力指数
76.2/100
前 1.8%
全站排名 #1,127
发表论文31 篇
平均评分4.7
年均产出10.3 篇/年

Zhen Tan

PhD student@Arizona State University·美国·OpenReview
研究方向

Trustworthy AI · Large Language Models · Multi-modal Large Language Models · Multi-Agent Systems · AI Safety & Security

6.5
16

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

ICLR 2026Poster
三作
6.0
17

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

ICLR 2026Poster
三作
5.7
23

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

ICLR 2026Poster
一作
5.5
10

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

ICLR 2026Desk Rejected
一作
5.0
24

Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder

ICLR 2026Rejected
二作
5.0
16

Dissecting Representation Misalignment in Contrastive Learning via Influence Function

ICLR 2026Poster
4.7
9

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

ICLR 2026Poster
二作
4.5
13

TRUST: A Decentralized Framework for Auditing Large Language Model Reasoning

ICLR 2026Withdrawn
二作
4.0
6

DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillation

ICLR 2026Withdrawn
二作
4.0
11

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

ICLR 2026Poster
二作
4.0
12

Who's Your Judge? On the Detectability of LLM-Generated Judgments

ICLR 2026Withdrawn
二作
4.0
6

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

ICLR 2026Rejected
3.7
7

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

ICLR 2026Withdrawn
三作
3.5
6

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

ICLR 2026Withdrawn
三作
3.0
5

Interpretable Neuropsychiatric Diagnosis via Concept-Guided Graph Neural Networks

ICLR 2026Withdrawn
三作
2.5
6

Can GRPO Help LLMs Transcend Their Pretraining Origin?

ICLR 2026Rejected
二作
2.5
5

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

ICLR 2026Withdrawn
2.4
6

Beyond Invariance: A Feature-Strength Framework for OOD Generalization

ICLR 2026Withdrawn
二作
7.8
21

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

NeurIPS 2025Poster
三作
7.5
24

CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models

ICLR 2025Spotlight
7.2
16

Editable Concept Bottleneck Models

ICML 2025Poster
6.4
24

Multi-Agent Debate for LLM Judges with Adaptive Stability Detection

NeurIPS 2025Poster
二作
5.5
22

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

ICLR 2025Rejected
一作
5.5
13

MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning

ICML 2025Poster
三作
5.3
14

Beyond Fixed Resolution: Enhancing VLLMs with Adaptive Input Scaling

ICLR 2025Withdrawn
二作
5.0
5

Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation

ICLR 2025Withdrawn
4.0
5

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

ICLR 2025Withdrawn
二作
3.5
6

GraphRCG: Self-Conditioned Graph Generation

ICLR 2025Rejected
二作
3.5
5

Understanding Reasoning in Chain-of-Thought from the Hopfieldian View

ICLR 2025Withdrawn
3.0
5

FairSkin: Fair Diffusion for Skin Disease Image Geneartion

ICLR 2025Withdrawn
三作
合作者 (20)