PaperHub

Sanjiv Kumar

~Sanjiv_Kumar1

30
论文总数
15.0
年均投稿
6.1
平均评分
接收情况22/30
会议分布
ICLR
21
NeurIPS
6
ICML
3

发表论文 (30 篇)

202518

6.6
4

LAuReL: Learned Augmented Residual Layer

ICML 2025Poster
6.5
4

Reasoning with Latent Thoughts: On the Power of Looped Transformers

ICLR 2025Poster
6.0
4

Scalable In-context Ranking with Generative Models

NeurIPS 2025Poster
4.8
3

Structured Preconditioners in Adaptive Optimization: A Unified Analysis

ICML 2025Poster
4.5
4

Mimetic Initialization Helps State Space Models Learn to Recall

ICLR 2025Rejected
4.8
5

No more hard-prompts: SoftSRV prompting for synthetic data generation

ICLR 2025Rejected
5.4
5

On the Role of Depth and Looping for In-Context Learning with Task Diversity

ICLR 2025Rejected
3.5
4

Asymmetric Embedding Models for Hierarchical Retrieval: Provable Constructions and a Pretrain-Finetune Recipe

ICLR 2025Rejected
6.4
4

Analyzing Similarity Metrics for Data Selection for Language Model Pretraining

NeurIPS 2025Poster
6.4
4

Hierarchical Retrieval: The Geometry and a Pretrain-Finetune Recipe

NeurIPS 2025Poster
7.5
4

Better autoregressive regression with LLMs via regression-aware fine-tuning

ICLR 2025Spotlight
5.7
3

Faster Cascades via Speculative Decoding

ICLR 2025Oral
6.8
4

Efficient stagewise pretraining via progressive subnetworks

ICLR 2025Poster
8.7
3

LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization

ICLR 2025Oral
6.3
3

Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation

ICML 2025Poster
5.5
4

A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs

ICLR 2025Rejected
5.5
4

Spark Transformer: How Many FLOPs is a Token Worth?

ICLR 2025Rejected
6.8
4

Spark Transformer: Reactivating Sparsity in Transformer FFN and Attention

NeurIPS 2025Poster

202412