Tianle Cai
23 papers · 2019–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (13) π Conference Polyglot (6)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π
Academic Marathon
(6)
π
Triple Crown
ποΈ
Keyword Collector
(86)
β‘
Prolific Year
(8)
π
Century Club
(23)
β
The Questioner
(2)
Conferences
NIPS (9)
ICML (7)
ICLR (4)
CVPR (1)
ECCV (1)
NAACL (1)
Top co-authors
Research topics
Keywords
model compression
(3)
large language model
(3)
attention mechanism
(2)
transformer architecture
(2)
graph neural network
(2)
learning theory
(2)
model optimization
(2)
self-attention mechanism
(1)
adversarial robustness
(1)
lottery ticket hypothesis
(1)
certified robustness
(1)
image generation
(1)
semi-supervised learning
(1)
domain generalization
(1)
representation learning
(1)
graph classification
(1)
robust optimization
(1)
label propagation
(1)
batch normalization
(1)
domain adaptation
(1)
Papers
CommVQ: Commutative Vector Quantization for KV Cache Compression
ICML 2025
MATH-Perturb: Benchmarking LLMsβ Math Reasoning Abilities against Hard Perturbations
ICML 2025
Unnatural Languages Are Not Bugs but Features for LLMs
ICML 2025
SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models
ICLR 2025
Training-Free Activation Sparsity in Large Language Models
ICLR 2025
Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling
NIPS 2024
DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
CVPR 2024
FlexAttention for Efficient High-Resolution Vision-Language Models
ECCV 2024
Large Language Models as Tool Makers
ICLR 2024
REST: Retrieval-Based Speculative Decoding
NAACL 2024
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
ICML 2024
BitDelta: Your Fine-Tune May Only Be Worth One Bit
NIPS 2024
SnapKV: LLM Knows What You are Looking for Before Generation
NIPS 2024
What Makes Convolutional Models Great on Long Sequence Modeling?
ICLR 2023
Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding
NIPS 2021
A Theory of Label Propagation for Subpopulation Shift
ICML 2021
GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
ICML 2021
Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons
ICML 2021
Do Transformers Really Perform Badly for Graph Representation?
NIPS 2021
Towards a Theoretical Framework of Out-of-Distribution Generalization
NIPS 2021
Locally Differentially Private (Contextual) Bandits Learning
NIPS 2020
Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot
NIPS 2020
Convergence of Adversarial Training in Overparametrized Neural Networks
NIPS 2019