Pulkit Agrawal
~Pulkit_Agrawal1
16
论文总数
8.0
年均投稿
平均评分
接收情况10/16
会议分布
ICLR
10
NeurIPS
4
COLM
1
ICML
1
发表论文 (16 篇)
20259 篇
4
Language Model Personalization via Reward Factorization
COLM 2025Poster
4
Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning
ICLR 2025Poster
5
Collective Model Intelligence Requires Compatible Specialization
ICLR 2025Rejected
4
Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective
ICML 2025Spotlight
4
From Context to Concept: Concept Encoding in In-Context Learning
ICLR 2025Rejected
6
ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization
ICLR 2025Poster
4
Diffusion Policy Policy Optimization
ICLR 2025Poster
4
Self-Adapting Language Models
NeurIPS 2025Poster
4
ImageNet-RIB Benchmark: Large Pre-Training Datasets Don't Guarantee Robustness after Fine-Tuning
ICLR 2025Rejected
20247 篇
3
Going Beyond Heuristics by Imposing Policy Improvement as a Constraint
NeurIPS 2024Poster
4
Training Neural Networks from Scratch with Parallel Low-Rank Adapters
ICLR 2024Rejected
3
Grid Cell-Inspired Fragmentation and Recall for Efficient Map Building
ICLR 2024Rejected
3
Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient
NeurIPS 2024Poster
4
Inverse Decision Making via Inverse Generative Modeling
ICLR 2024withdrawn
3
Few-Shot Task Learning through Inverse Generative Modeling
NeurIPS 2024Poster
4
Curiosity-driven Red-teaming for Large Language Models
ICLR 2024Poster