Vahab Mirrokni
~Vahab_Mirrokni2
31
论文总数
15.5
年均投稿
平均评分
接收情况23/31
会议分布
ICLR
12
NeurIPS
10
ICML
7
COLM
2
发表论文 (31 篇)
202521 篇
4
Improving the Variance of Differentially Private Randomized Experiments through Clustering
ICML 2025Poster
4
ClusterGen: Token Generation in Sublinear Time and Memory with Clustering KV Cache
ICLR 2025Rejected
4
Titans: Learning to Memorize at Test Time
NeurIPS 2025Poster
4
Maximum Coverage in Turnstile Streams with Applications to Fingerprinting Measures
ICLR 2025Rejected
4
Procurement Auctions via Approximately Optimal Submodular Optimization
ICML 2025Spotlight
4
Maximum Coverage in Turnstile Streams with Applications to Fingerprinting Measures
ICML 2025Poster
5
Efficient Data Selection at Scale via Influence Distillation
NeurIPS 2025Poster
4
Nested Learning: The Illusion of Deep Learning Architectures
NeurIPS 2025Poster
4
Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing
NeurIPS 2025Poster
4
Synthetic Text Generation for Training Large Language Models via Gradient Matching
ICML 2025Poster
3
TRELLIS: Learning to Compress Key-Value Memory in Attention Models
COLM 2025Poster
4
MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling
COLM 2025Poster
4
NanoMoE: Scaling Mixture of Experts to Individual Layers for Parameter-Efficient Deep Learning
ICLR 2025Rejected
4
PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts
NeurIPS 2025Spotlight
4
DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction
ICLR 2025Poster
-
Retraining with Predicted Hard Labels Provably Increases Model Accuracy
ICLR 2025desk_rejected
3
Retraining with Predicted Hard Labels Provably Increases Model Accuracy
ICML 2025Poster
3
DeepCrossAttention: Supercharging Transformer Residual Connections
ICML 2025Poster
4
Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models
ICLR 2025Poster
3
Best of Both Worlds: Advantages of Hybrid Graph Sequence Models
ICML 2025Poster
4
Towards an Understanding of Graph Sequence Models
ICLR 2025Rejected
202410 篇
5
PolySketchFormer: Fast Transformers via Sketches for Polynomial Kernels
ICLR 2024Rejected
5
Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions
ICLR 2024Poster
4
Efficiency of the First-Price Auction in the Autobidding World
NeurIPS 2024Poster
4
Autobidder's Dilemma: Why More Sophisticated Autobidders Lead to Worse Auction Efficiency
NeurIPS 2024Poster
3
High-Dimensional Geometric Streaming for Nearly Low Rank Data
ICLR 2024Rejected
4
Sensitivity Sampling for Coreset-Based Data Selection
ICLR 2024Rejected
3
HyperAttention: Long-context Attention in Near-Linear Time
ICLR 2024Poster
6
MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encoding
NeurIPS 2024Poster
3
SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization
NeurIPS 2024Poster
3
Understanding Transformer Reasoning Capabilities via Graph Algorithms
NeurIPS 2024Poster