PPaperPicks

Truyen Tran

Deakin University, Center for Pattern Recognition and Data Analyticss (PRaDA), Geelong, Australia

16 papers at tracked venues · 8 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Continual Safety Alignment via Gradient-Based Sample Selection
  2. Do Domain-specific Experts exist in MoE-based LLMs?
  3. Rethinking Deep Alignment Through the Lens of Incomplete Safety Learning
  4. Robust SDE Parameter Estimation Under Missing Time Information Setting
  5. Learning Structural Causal Models from Ordering: Identifiable Flow Models
  6. Navigating Social Dilemmas with LLM-based Agents via Consideration of Future Consequences
  7. Navigating Social Dilemmas with LLM-based Agents via Consideration of Future Consequences
  8. Planner-Refiner: Dynamic Space-Time Refinement for Vision-Language Alignment in Videos
  9. Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language Models
  10. Rapid Selection and Ordering of In-Context Demonstrations via Prompt Embedding Clustering
  11. Score-Based Integrated Gradient for Root Cause Explanations of Outliers
  12. SimSMoE: Toward Efficient Training Mixture of Experts via Solving Representational Collapse
  13. Diversifying Training Pool Predictability for Zero-shot Coordination: A Theory of Mind Approach
  14. Revisiting the Dataset Bias Problem from a Statistical Perspective
  15. Root Cause Explanation of Outliers under Noisy Mechanisms
  16. Unified Compositional Query Machine with Multimodal Consistency for Video-based Human Activity Recognition