PaperHub

Sham M. Kakade

~Sham_M._Kakade1

29
论文总数
14.5
年均投稿
6.3
平均评分
接收情况22/29
会议分布
ICLR
17
NeurIPS
7
ICML
3
COLM
2

发表论文 (29 篇)

202518

7.0
3

Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

COLM 2025Poster
5.5
4

Universal Length Generalization with Turing Programs

ICML 2025Poster
6.8
4

Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems

ICLR 2025Poster
7.0
3

The Role of Sparsity for Length Generalization in LLMs

ICML 2025Poster
7.8
4

Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions

ICML 2025Oral
7.0
4

Interpreting the linear structure of vision-language model embedding spaces

COLM 2025Poster
7.0
4

Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models

ICLR 2025Oral
4.5
4

Soup to go: mitigating forgetting during continual learning with model averaging

ICLR 2025Rejected
6.8
6

Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond

ICLR 2025Poster
5.3
4

Multi-Agent Reinforcement Learning from Human Feedback: Data Coverage and Algorithmic Techniques

ICLR 2025Rejected
6.0
4

Deconstructing What Makes a Good Optimizer for Autoregressive Language Models

ICLR 2025Poster
6.3
4

A New Perspective on Shampoo's Preconditioner

ICLR 2025Poster
4.7
3

Universal length generalization with Turing Programs

ICLR 2025Rejected
6.6
5

Eliminating Position Bias of Language Models: A Mechanistic Approach

ICLR 2025Poster
6.3
4

SOAP: Improving and Stabilizing Shampoo using Adam for Language Modeling

ICLR 2025Poster
6.8
5

How Does Critical Batch Size Scale in Pre-training?

ICLR 2025Poster
7.8
4

EvoLM: In Search of Lost Language Model Training Dynamics

NeurIPS 2025Oral
7.0
4

Mixture of Parrots: Experts improve memorization more than reasoning

ICLR 2025Poster

202411