← Authors

Ankit Singh Rawat

35 papers · 2015–2025 · 6 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (6) 🐝 Cross-Pollinator (15) πŸƒ Academic Marathon (10) 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (12) 🧭 Keyword Pioneer 🀝 Dynamic Duo (24) πŸ‘‘ Triple Crown πŸ† Keyword Champion (2) ⚑ Prolific Year (5) πŸ”₯ Unstoppable (7) ❓ The Questioner (4) πŸ—ƒοΈ Keyword Collector (98) πŸ’Ž Century Club (35)

Conferences

ICLR (13) ICML (10) NIPS (7) AISTATS (3) ACL (1) EMNLP (1)

Top co-authors

Sanjiv Kumar (24) Aditya Krishna Menon (9) Sashank Reddi (8) Seungyeon Kim (8) Manzil Zaheer (7) Felix Yu (6) Srinadh Bhojanapalli (5) Wittawat Jitkrittum (4) Aditya K Menon (4) Andreas Veit (4)

Keywords

representation learning (4) neural network (3) gradient descent (3) knowledge distillation (3) attention mechanism (3) embedding dimension (2) large language model (2) transformer architecture (2) information retrieval (2) nearest neighbor (2) certified robustness (1) local learning (1) embedding learning (1) natural language processing (1) sparse recovery (1) federated learning (1) embedding space (1) bayesian inference (1) text generation (1) in-context learning (1)

Papers

Faster Cascades via Speculative Decoding ICLR 2025
Language Model Cascades: Token-Level Uncertainty And Beyond ICLR 2024
From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers ICML 2024
A Statistical Framework for Data-dependent Retrieval-Augmented Models ICML 2024
Dual-Encoders for Extreme Multi-label Classification ICLR 2024
Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond NIPS 2024
USTAD: Unified Single-model Training Achieving Diverse Scores for Information Retrieval ICML 2024
DistillSpec: Improving Speculative Decoding via Knowledge Distillation ICLR 2024
Think before you speak: Training Language Models With Pause Tokens ICLR 2024
Analysis of Plan-based Retrieval for Grounded Text Generation EMNLP 2024
Mechanics of Next Token Prediction with Self-Attention AISTATS 2024
Teacher Guided Training: An Efficient Framework for Knowledge Transfer ICLR 2023
Large Language Models with Controllable Working Memory ACL 2023
Supervision Complexity and its Role in Knowledge Distillation ICLR 2023
The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers ICLR 2023
Serving Graph Compression for Graph Neural Networks ICLR 2023
A Statistical Perspective on Retrieval-Based Models ICML 2023
On the Role of Attention in Prompt-tuning ICML 2023
In defense of dual-encoders for neural ranking ICML 2022
RankDistil: Knowledge Distillation for Ranking AISTATS 2021
Long-tail learning via logit adjustment ICLR 2021
A statistical perspective on distillation ICML 2021
Disentangling Sampling and Labeling Bias for Learning in Large-output Spaces ICML 2021
Overparameterisation and worst-case generalisation: friend or foe? ICLR 2021
Federated Learning with Only Positive Labels ICML 2020
Can gradient clipping mitigate label noise? ICLR 2020
Are Transformers universal approximators of sequence-to-sequence functions? ICLR 2020
Adversarial robustness via robust low rank representations NIPS 2020
Robust large-margin learning in hyperbolic space NIPS 2020
O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers NIPS 2020
Low-Rank Bottleneck in Multi-head Attention Models ICML 2020
Multilabel reductions: what is my loss optimising? NIPS 2019
Lifting high-dimensional non-linear models with Gaussian regressors AISTATS 2019
Sampled Softmax with Random Fourier Features NIPS 2019
Associative Memory via a Sparse Recovery Model NIPS 2015