PPaperPicks

Tejaswini Pedapati

14 papers at tracked venues · 11 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. AI Steerability 360: A Toolkit for Steering Large Language Models
  2. OjaKV: Context-Aware Online Low-Rank KV Cache Compression
  3. ZoomR: Memory Efficient Reasoning through Multi-Granularity Key Value Retrieval
  4. Differentiable Prompt Learning for Vision Language Models
  5. EpMAN: Episodic Memory AttentioN for Generalizing to Longer Contexts
  6. EvalAssist: Insights on Task-Specific Evaluations and AI-Assisted Judgment Strategy Preferences
  7. EvalAssist: LLM-as-a-Judge Simplified
  8. From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers
  9. Granite Guardian: Comprehensive LLM Safeguarding
  10. Large Language Models can Become Strong Self-Detoxifiers
  11. STAR: Spectral Truncation and Rescale for Model Merging
  12. TOPJoin: A Context-Aware Multi-Criteria Approach for Joinable Column Search
  13. TabSketchFM: Sketch-Based Tabular Representation Learning for Data Discovery Over Data Lakes
  14. NeuroPrune: A Neuro-inspired Topological Sparse Training Algorithm for Large Language Models