PaperHub

Diyi Yang

~Diyi_Yang2

21
论文总数
10.5
年均投稿
6.2
平均评分
接收情况17/21
会议分布
ICLR
10
NeurIPS
5
COLM
5
ICML
1

发表论文 (21 篇)

202512 篇

5.8
4

Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers

ICLR 2025Poster
4.0
3

Dynamic Skill Adaptation for Large Language Models

ICLR 2025Rejected
6.8
4

Information Retrieval Induced Safety Degradation in AI Agents

NeurIPS 2025Poster
7.3
4

Blackbox Model Provenance via Palimpsestic Membership Inference

NeurIPS 2025Spotlight
6.8
5

Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors

ICML 2025Poster
7.0
4

The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning

COLM 2025Poster
6.8
5

When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration

NeurIPS 2025Poster
5.0
3

No Preference Left Behind: Group Distributional Preference Optimization

ICLR 2025Poster
4.8
4

Distilling an End-to-End Voice Assistant Without Instruction Training Data

ICLR 2025Rejected
6.3
4

Aligning Language Models with Demonstrated Feedback

ICLR 2025Poster
5.0
4

SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?

ICLR 2025Poster
8.7
4

OpenCUA: Open Foundations for Computer-Use Agents

NeurIPS 2025Spotlight

20249 篇

5.8
4

DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph

NeurIPS 2024Poster
6.2
5

Training Socially Aligned Language Models on Simulated Social Interactions

ICLR 2024Poster
5.5
6

Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimization

ICLR 2024Rejected
6.5
4

DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks

ICLR 2024Spotlight
6.7
3

A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration

COLM 2024Poster
5.5
4

Enhanced Visual Instruction Tuning for Text-Rich Image Understanding

ICLR 2024Rejected
6.5
4

Best Practices and Lessons Learned on Synthetic Data

COLM 2024Poster
6.5
4

Mapping the Increasing Use of LLMs in Scientific Papers

COLM 2024Poster
6.5
4

Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data

COLM 2024Poster
合作者 (20)