PPaperPicks

Niloy Ganguly

26 papers at tracked venues · 12 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Benchmarking the Energy Savings with Speculative Decoding Strategies
  2. Learning Faster with Better Tokens: Parameter-Efficient Vocabulary Adaptation for Specialized Text Summarization
  3. Brevity is the soul of sustainability: Characterizing LLM response lengths
  4. Building Trustworthy AI Models for Medicine: From Theory to Applications
  5. Disinformation and Misinformation in the Age of Generative AI
  6. Efficient Continual Pre-training of LLMs for Low-resource Languages
  7. Evaluation of LLMs in Medical Text Summarization: The Role of Vocabulary Adaptation in High OOV Settings
  8. ExPERT: Modeling Human Behavior Under External Stimuli Aware Personalized MTPP
  9. Introducing Spotlight: A Novel Approach for Generating Captivating Key Information from Documents
  10. LLM Meets Diffusion: A Hybrid Framework for Crystal Material Generation
  11. Label-semantics Aware Generative Approach for Domain-Agnostic Multilabel Classification
  12. MutantPrompt: Prompt Optimization via Mutation Under a Budget on Modest-sized LMs
  13. Periodic Materials Generation using Text-Guided Joint Diffusion Model
  14. Program of Thoughts for Financial Reasoning: Leveraging Dynamic In-Context Examples and Generative Retrieval
  15. Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Models
  16. Adaptive BPE Tokenization for Enhanced Vocabulary Adaptation in Finetuning Pretrained Language Models
  17. Beyond Accuracy: Investigating Error Types in GPT-4 Responses to USMLE Questions
  18. Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs
  19. IVP-VAE: Modeling EHR Time Series with Initial Value Problem Solvers
  20. Instruction-Guided Bullet Point Summarization of Long Financial Earnings Call Transcripts
  21. MEDVOC: Vocabulary Adaptation for Fine-tuning Pre-trained Language Models on Medical Text Summarization
  22. On The Persona-based Summarization of Domain-Specific Documents
  23. Order-Based Pre-training Strategies for Procedural Text Understanding
  24. Parameter-Efficient Instruction Tuning of Large Language Models For Extreme Financial Numeral Labelling
  25. Self-SLAM: A Self-supervised Learning Based Annotation Method to Reduce Labeling Overhead
  26. Unlocking Efficiency: Adaptive Masking for Gene Transformer Models