PaperHub

Ruoxi Jia

~Ruoxi_Jia1

25
论文总数
12.5
年均投稿
6.0
平均评分
接收情况17/25
会议分布
ICLR
16
NeurIPS
4
COLM
3
ICML
2

发表论文 (25 篇)

202518 篇

6.4
5

LLMs Can Plan Only If We Tell Them

ICLR 2025Poster
4.5
4

CONCORD: Concept-informed Diffusion for Dataset Distillation

ICLR 2025withdrawn
5.0
4

SCOPE: Scalable and Adaptive Evaluation of Misguided Safety Refusal in LLMs

ICLR 2025Rejected
5.3
4

LLM Spark: Critical Thinking Evaluation of Large Language Models

ICLR 2025Rejected
6.1
4

LLMs Can Reason Faster Only If We Let Them

ICML 2025Poster
4.8
4

Fast and Noise-Robust Diffusion Solvers for Inverse Problems: A Frequentist Approach

ICLR 2025Rejected
7.5
4

Data Shapley in One Training Run

ICLR 2025Oral
6.5
4

Data-Centric Human Preference with Rationales for Direct Preference Alignment

COLM 2025Poster
6.4
4

Probing Hidden Knowledge Holes in Unlearned LLMs

NeurIPS 2025Poster
5.3
4

Data-Centric Human Preference Optimization with Rationales

ICLR 2025Rejected
5.5
4

Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning

ICML 2025Poster
8.0
4

Capturing the Temporal Dependence of Training Data Influence

ICLR 2025Oral
5.5
4

AutoScale: Automatic Prediction of Compute-optimal Data Compositions for Training LLMs

ICLR 2025Rejected
5.3
3

AutoScale: Scale-Aware Data Mixing for Pre-Training LLMs

COLM 2025Poster
6.5
4

Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data

ICLR 2025Poster
7.5
4

AIR-BENCH 2024: A Safety Benchmark based on Regulation and Policies Specified Risk Categories

ICLR 2025Spotlight
7.3
4

LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models

COLM 2025Poster
6.8
4

SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

ICLR 2025Poster
合作者 (20)