Anushka Sivakumar
4 papers · 2024–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (3) π Cross-Pollinator (12) π Renaissance Researcher (5)
πΊοΈ
Taxonomy Completionist
(19)
π£
Hot Topic Early Bird
Conferences
EMNLP (2)
ACL (1)
NIPS (1)
Top co-authors
Keywords
vision-language model
(2)
image generation
(1)
visual question answering
(1)
optimal transport
(1)
text generation
(1)
image captioning
(1)
cross-modal retrieval
(1)
hallucination mitigation
(1)
discrete diffusion
(1)
representation collapse
(1)
image-text retrieval
(1)
multimodal reasoning
(1)
discrete diffusion model
(1)
visual understanding
(1)
semantic diversity
(1)
text infilling
(1)
activation steering
(1)
fine-grained reasoning
(1)
non-autoregressive generation
(1)
generated image
(1)
Papers
Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval
ACL 2025
Flexible-length Text Infilling for Discrete Diffusion Models
EMNLP 2025
SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models
EMNLP 2025
JourneyBench: A Challenging One-Stop Vision-Language Understanding Benchmark of Generated Images
NIPS 2024