Aditi Raghunathan
~Aditi_Raghunathan1
21
论文总数
10.5
年均投稿
平均评分
接收情况16/21
会议分布
ICLR
13
NeurIPS
3
ICML
3
COLM
2
发表论文 (21 篇)
202512 篇
4
Mitigating Modal Imbalance in Multimodal Reasoning
COLM 2025Poster
4
Testing the Limits of Jailbreaking with the Purple Problem
ICLR 2025Rejected
4
Reasoning as an Adaptive Defense for Safety
NeurIPS 2025Poster
4
Memorization Sinks: Isolating Memorization during LLM Training
ICML 2025Poster
4
Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance
ICLR 2025Oral
3
Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction
ICML 2025Oral
4
Weight ensembling improves reasoning in language models
COLM 2025Poster
4
Lowering Data Diversity can Accelerate Training: Case Studies in Synthetic Tasks
ICLR 2025Rejected
4
Repetition Improves Language Model Embeddings
ICLR 2025Poster
4
Dissecting Adversarial Robustness of Multimodal LM Agents
ICLR 2025Poster
4
Overtrained Language Models Are Harder to Fine-Tune
ICML 2025Poster
4
Scaling Laws for Precision
ICLR 2025Oral
20249 篇
4
Understanding Catastrophic Forgetting in Language Models via Implicit Inference
ICLR 2024Poster
6
Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning
ICLR 2024Poster
4
Why is SAM Robust to Label Noise?
ICLR 2024Poster
4
Reliable Test-Time Adaptation via Agreement-on-the-Line
ICLR 2024Rejected
4
ALP: Action-Aware Embodied Learning for Perception
ICLR 2024Rejected
4
Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line
NeurIPS 2024Poster
4
T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
ICLR 2024Poster
4
Predicting the Performance of Foundation Models via Agreement-on-the-line
ICLR 2024Rejected
4
Predicting the Performance of Foundation Models via Agreement-on-the-Line
NeurIPS 2024Poster