Soumya Suvra Ghosal
11 papers · 2023–2026 · 8 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 Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (30) π Grand Slam ποΈ Keyword Collector (56)
β
The Questioner
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
Top co-authors
Research topics
Artificial Intelligence
(10)
Core AI
(8)
Machine Learning
(7)
Deep Learning
(6)
Natural Language Processing
(5)
Learning Types Β· Deep Learning
(5)
Learning Paradigms
(4)
Learning Types Β· Machine Learning
(4)
Resources & Methods
(4)
Optimization & Theory
(3)
Application Areas
(1)
Applications
(1)
Core Methods
(1)
Generation
(1)
Models
(1)
Keywords
few-shot learning
(3)
reward model
(2)
in-context learning
(2)
low-resource language
(2)
harmful content
(1)
reinforcement learning from human feedback
(1)
cross-lingual transfer
(1)
visual reasoning
(1)
bounded rationality
(1)
feature representation
(1)
toxicity detection
(1)
safety alignment
(1)
reward function
(1)
model alignment
(1)
nearest neighbor
(1)
question answering
(1)
optimal decoding
(1)
pairwise ranking
(1)
distributionally robust optimization
(1)
subspace learning
(1)
Papers
Engagement Undermines Safety: How Stereotypes and Toxicity Shape Humor in Language Models
EACL 2026
VisRef: Visual Refocusing while Thinking Improves Test-Time Scaling in Multi-Modal Large Reasoning Models
CVPR 2026
Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time
ICML 2025
Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
ICLR 2025
Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
CVPR 2025
PromptRefine: Enhancing Few-Shot Performance on Low-Resource Indic Languages with Example Selection from related Example Banks
NAACL 2025
RELIC: Enhancing Reward Model Generalization for Low-Resource Indic Languages with Few-Shot Examples
EMNLP 2025
How to Overcome Curse-of-Dimensionality for Out-of-Distribution Detection?
AAAI 2024
IntCoOp: Interpretability-Aware Vision-Language Prompt Tuning
EMNLP 2024
Transfer Q-star : Principled Decoding for LLM Alignment
NeurIPS 2024
Distributionally Robust Optimization with Probabilistic Group
AAAI 2023