Som Sagar
3 papers · 2024–2026 · 2 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
❓
The Questioner
Top co-authors
Research topics
Keywords
generative model
(2)
deep reinforcement learning
(1)
reinforcement learning
(1)
human feedback
(1)
internal representation
(1)
large language model
(1)
neural network
(1)
implicit communication
(1)
failure mode
(1)
vision-language preference learning
(1)
concept generation
(1)
alignment
(1)
information theory
(1)
large-scale vision and language models
(1)
Papers
ExpressivityBench: Can LLMs Communicate Implicitly?
EACL 2026
Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks’ Internal Representations
ICML 2025
Failures Are Fated, But Can Be Faded: Characterizing and Mitigating Unwanted Behaviors in Large-Scale Vision and Language Models
ICML 2024