影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
85.93/100
前 0.9%
全站排名 #551
发表论文17 篇
平均评分
年均产出5.7 篇/年
Samet Oymak
研究方向
reinforcement learning · optimization · statistical learning · deep learning · language models and reasoning · structured data and forecasting
22
Continuous Chain of Thought Enables Parallel Exploration and Reasoning
ICLR 2026Poster
通讯21
SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG
ICLR 2026Poster
三作29
Mitigating Participation Imbalance Bias in Asynchronous Federated Learning Under Client Heterogeneity
ICLR 2026Rejected
28
BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning
NeurIPS 2025Poster
通讯16
Extrapolation by Association: Length Generalization Transfer In Transformers
NeurIPS 2025Spotlight
20
Theoretical Insights into In-context Learning with Unlabeled Data
NeurIPS 2025Poster
通讯17
Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
ICML 2025Spotlight
20
High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws
ICLR 2025Spotlight
通讯15
Gating is Weighting: Understanding Gated Linear Attention through In-context Learning
COLM 2025Poster
通讯23
Attention with Trained Embeddings Provably Selects Important Tokens
NeurIPS 2025Poster
三作10
Test-Time Training Provably Improves Transformers as In-context Learners
ICML 2025Poster
通讯23
Gating is Weighting: Understanding Gated Linear Attention through In-context Learning
ICLR 2025Rejected
通讯17
Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
ICLR 2025Rejected