影响力指数

86.62/100

前 0.8%

全站排名 #521

发表论文32 篇

平均评分5.4

年均产出10.7 篇/年

Jie Fu

Research Scientist@IQuest Research·中国·OpenReview

研究方向

Autoformalization · Safe AI · Deep Reinforcement Learning · Language Models · Deep Learning · AI for Science

6.0

UltraLLaDA: Scaling the Context Length to 128K for Diffusion Large Language Models

ICLR 2026Poster

5.0

Off-Policy Token Clipped Supervised Fine-Tuning Yields a Robust Cold-Start

ICLR 2026Rejected

4.5

Local Success Does Not Compose: Benchmarking Large Language Models for Compositional Formal Verification

ICLR 2026Poster

4.0

SurveyBench: How Well Can LLM(-Agents) Write Academic Surveys?

ICLR 2026Rejected

4.0

VeriEquivBench: An Equivalence Score for Ground-Truth-Free Evaluation of Formally Verifiable Code

ICLR 2026Poster

通讯

1.5

Atomos: Hierarchical Reasoning From Atomic Steps

ICLR 2026Rejected

通讯

6.7

VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text

ICLR 2025Poster

6.5

MuPT: A Generative Symbolic Music Pretrained Transformer

ICLR 2025Poster

6.4

Thinker: Learning to Think Fast and Slow

NeurIPS 2025Poster

三作

6.3

MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation

ICLR 2025Poster

5.8

Layerwise Recurrent Router for Mixture-of-Experts

ICLR 2025Poster

通讯

5.5

ECG Instruction Tuning on Multimodal LLMs for Report Generation: Benchmark and Evaluation

ICLR 2025Rejected

5.5

MIO: A Foundation Model on Multimodal Tokens

ICLR 2025Rejected

4.0

Towards Efficient and No Forgetting Domain Continual Pretraining by Mitigating the Stability Gap

合作者 (20)