Sanjeda Akter
4 papers · 2025–2026 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Renaissance Researcher
(5)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(13)
π
Cross-Pollinator
(15)
Conferences
ACL (2)
EMNLP (2)
Top co-authors
Keywords
model compression
(1)
reinforcement learning
(1)
offline reinforcement learning
(1)
bayesian learning
(1)
bayesian inference
(1)
bayesian reinforcement learning
(1)
posterior sampling
(1)
constraint propagation
(1)
subspace selection
(1)
model pruning
(1)
fisher information matrix
(1)
state-space model
(1)
memory efficiency
(1)
language model
(1)
graph attention network
(1)
robotic control
(1)
meta reinforcement learning
(1)
inference efficiency
(1)
edge deployment
(1)
inference acceleration
(1)
Papers
Adaptive Constraint Propagation: Scaling Structured Inference for Large Language Models via Meta-Reinforcement Learning
ACL 2026
Beyond Variance: Knowledge-Aware LLM Compression via Fisher-Aligned Subspace Diagnostics
ACL 2026
Cache-Efficient Posterior Sampling for Reinforcement Learning with LLM-Derived Priors Across Discrete and Continuous Domains
EMNLP 2025
Efficient Unstructured Pruning of Mamba State-Space Models for Resource-Constrained Environments
EMNLP 2025