Yingyan Celine Lin
12 papers · 2023–2026 · 7 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (25) π Conference Polyglot Β· Silver π Keyword Champion (2) ποΈ Keyword Collector (67)
β‘
Prolific Year Β· Productive
π
Renaissance Researcher
(6)
π
Century Club Β· Bronze
Top co-authors
Research topics
Machine Learning
(10)
Application Areas
(8)
Artificial Intelligence
(7)
Core AI
(7)
Deep Learning
(5)
Natural Language Processing
(3)
Architectures
(3)
Optimization & Theory Β· Machine Learning
(3)
Generation
(2)
Models
(2)
Optimization & Theory Β· Deep Learning
(2)
Computer Vision
(1)
Reinforcement Learning
(1)
Robotics
(1)
Speech & Audio
(1)
Keywords
state space model
(3)
token filtering
(2)
attention mechanism
(2)
hidden state
(2)
long-context understanding
(2)
automatic speech recognition
(1)
knowledge transfer
(1)
image generation
(1)
meta tokens
(1)
cross-scene generalization
(1)
receptive field
(1)
efficient computing
(1)
diffusion model
(1)
efficient inference
(1)
neural radiance field
(1)
adversarial perturbation
(1)
novel view synthesis
(1)
inference optimization
(1)
dynamic routing
(1)
imitation learning
(1)
Papers
Think Hard Only When Needed: A Hybrid Best-of-N and Beam Search for Efficient Test-Time Compute
EACL 2026
Fewer Denoising Steps or Cheaper Per-Step Inference: Towards Compute-Optimal Diffusion Model Deployment
ICCV 2025
Hymba: A Hybrid-head Architecture for Small Language Models
ICLR 2025
LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models
ICML 2025
LAMB: A Training-Free Method to Enhance the Long-Context Understanding of SSMs via Attention-Guided Token Filtering
ACL 2025
Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers
CVPR 2025
LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement
ICLR 2025
SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies
CoRL 2025
Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration
ICML 2024
When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models
ICML 2024
Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modular Learning
ICML 2023
NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations
ICML 2023