Fengzhuo Zhang
11 papers · 2021–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Interdisciplinary Bridge π Renaissance Researcher (7) π Conference Polyglot (6) π Academic Marathon (5) πΊοΈ Taxonomy Completionist (22)
πΊοΈ
Taxonomy Completionist
(22)
π§
Keyword Pioneer
π
Grand Slam
π§¬
Topic Evolution
π₯
Unstoppable
(5)
π
Century Club
(10)
β
The Questioner
Conferences
NIPS (3)
ACL (2)
ICML (2)
AAAI (1)
AISTATS (1)
ICLR (1)
JMLR (1)
Top co-authors
Keywords
speculative decoding
(3)
nash equilibrium
(2)
structure learning
(1)
attention mechanism
(1)
video understanding
(1)
efficient computing
(1)
relational reasoning
(1)
model-based reinforcement learning
(1)
robust estimation
(1)
graphon estimation
(1)
generalization bound
(1)
diffusion model
(1)
kernel embedding
(1)
gaussian graphical model
(1)
spectral method
(1)
proximal policy optimization
(1)
model-free reinforcement learning
(1)
sparse attention
(1)
inference acceleration
(1)
video language model
(1)
Papers
LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
ACL 2026
Annealed Relaxation of Speculative Decoding for Faster Autoregressive Image Generation
AAAI 2026
What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization
AISTATS 2025
When Attention Sink Emerges in Language Models: An Empirical View
ICLR 2025
Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs
ACL 2025
BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms
ICML 2025
From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems
ICML 2024
Learning Regularized Graphon Mean-Field Games with Unknown Graphons
JMLR 2024
Learning Regularized Monotone Graphon Mean-Field Games
NIPS 2023
Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL
NIPS 2022
Robustifying Algorithms of Learning Latent Trees with Vector Variables
NIPS 2021