Search

Your search keyword '"Beirami, Ahmad"' showing total 82 results

Search Constraints

Start Over You searched for: Author "Beirami, Ahmad" Remove constraint Author: "Beirami, Ahmad" Publication Type Reports Remove constraint Publication Type: Reports
82 results on '"Beirami, Ahmad"'

Search Results

1. Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment

2. Generalization Error of the Tilted Empirical Risk

3. Inducing Group Fairness in Prompt-Based Language Model Decisions

4. Safety Alignment Should Be Made More Than Just a Few Tokens Deep

5. Robust Preference Optimization through Reward Model Distillation

6. Data-augmented phrase-level alignment for mitigating object hallucination

7. Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment

8. Asymptotics of Language Model Alignment

9. Block Verification Accelerates Speculative Decoding

10. Gradient-Based Language Model Red Teaming

11. Theoretical guarantees on the best-of-n alignment policy

12. Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking

13. Multi-Group Fairness Evaluation via Conditional Value-at-Risk Testing

14. FRAPPE: A Group Fairness Framework for Post-Processing Everything

15. Improving Robustness via Tilted Exponential Layer: A Communication-Theoretic Perspective

16. Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting

17. Controlled Decoding from Language Models

18. Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuning

19. Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks

20. SpecTr: Fast Speculative Decoding via Optimal Transport

21. Enhancing Group Fairness in Online Settings Using Oblique Decision Forests

22. A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models

23. Towards A Scalable Solution for Improving Multi-Group Fairness in Compositional Classification

24. Let's Do a Thought Experiment: Using Counterfactuals to Improve Moral Reasoning

25. Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts

26. Towards Robust Prompts on Vision-Language Models

27. Robust Conversational Agents against Imperceptible Toxicity Triggers

28. Know Thy Strengths: Comprehensive Dialogue State Tracking Diagnostics

29. Database Search Results Disambiguation for Task-Oriented Dialog Systems

30. Information-Theoretic Bayes Risk Lower Bounds for Realizable Models

31. Federated Learning with Heterogeneous Differential Privacy

32. Robustness through Data Augmentation Loss Consistency

33. On Tilted Losses in Machine Learning: Theory and Applications

34. Annotation Inconsistency and Entity Bias in MultiWOZ

35. A Stochastic Optimization Framework for Fair Risk Minimization

36. DVD: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue

37. Coded Machine Unlearning

38. Ditto: Fair and Robust Federated Learning Through Personalization

39. Overview of the Ninth Dialog System Technology Challenge: DSTC9

40. Resource Constrained Dialog Policy Learning via Differentiable Inductive Logic Programming

41. Centralized vs Decentralized Targeted Brute-Force Attacks: Guessing with Side-Information

42. Tilted Empirical Risk Minimization

43. Competitive Balance in Team Sports Games

44. Situated and Interactive Multimodal Conversations

45. Nonlinear Function Estimation with Empirical Bayes and Approximate Message Passing

46. Mismatched Guesswork

47. R\'enyi Fair Inference

48. On Multi-Agent Learning in Team Sports Games

49. Towards Interactive Training of Non-Player Characters in Video Games

50. Fair Resource Allocation in Federated Learning

Catalog

Books, media, physical & digital resources