Sravan Babu Bodapati
10 papers · 2024–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (16) π§ Keyword Pioneer π Conference Polyglot (4)
π
Cross-Pollinator
(14)
π
Renaissance Researcher
(5)
π
Century Club
(10)
β‘
Prolific Year
(9)
Conferences
EMNLP (5)
ACL (2)
ICLR (2)
AISTATS (1)
Top co-authors
Research topics
Keywords
large language model
(4)
speculative decoding
(2)
knowledge distillation
(1)
prompt engineering
(1)
responsible ai
(1)
efficient inference
(1)
evaluation framework
(1)
model pruning
(1)
gradient optimization
(1)
generative model
(1)
state space model
(1)
tree search
(1)
context length
(1)
weight pruning
(1)
token prediction
(1)
inference acceleration
(1)
cognitive bia
(1)
transformer optimization
(1)
linear attention
(1)
inference latency
(1)
Papers
Beyond correlation: The impact of human uncertainty in measuring the effectiveness of automatic evaluation and LLM-as-a-judge
ICLR 2025
Wanda++: Pruning Large Language Models via Regional Gradients
ACL 2025
Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment
AISTATS 2025
Accelerated Test-Time Scaling with Model-Free Speculative Sampling
EMNLP 2025
LAWCAT: Efficient Distillation from Quadratic to Linear Attention with Convolution across Tokens for Long Context Modeling
EMNLP 2025
Mamba Drafters for Speculative Decoding
EMNLP 2025
Think Clearly: Improving Reasoning via Redundant Token Pruning
EMNLP 2025
Context Length Alone Hurts LLM Performance Despite Perfect Retrieval
EMNLP 2025
SeRA: Self-Reviewing and Alignment of LLMs using Implicit Reward Margins
ICLR 2025
ConSiDERS-The-Human Evaluation Framework: Rethinking Human Evaluation for Generative Large Language Models
ACL 2024