Ahmad Beirami

31 papers · 2017–2025 · 12 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🏃 Academic Marathon (8) 🐝 Cross-Pollinator (14) 🌈 Renaissance Researcher (6) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (47) 🌍 Conference Polyglot (12) 💎 Century Club (31) ⚡ Prolific Year (6) 🗃️ Keyword Collector (97) 🔥 Unstoppable (6) 📈 Trend Setter

Conferences

ICLR (7) ICML (6) EMNLP (4) NIPS (3) AISTATS (2) COLING (2) NAACL (2) ACL (1) CVPR (1) EACL (1) IJCNLP (1) JMLR (1)

Top co-authors

Alborz Geramifard (5) Tian Li (5) Satwik Kottur (4) Virginia Smith (4) Chinnadhurai Sankar (4) Ananda Theertha Suresh (4) Maziar Sanjabi (3) Ziteng Sun (3) Jacob Eisenstein (3) Paul Crook (3)

Keywords

large language model (4) dialogue system (3) zero-shot learning (2) dialog state tracking (2) video-grounded dialogue (2) transfer learning (2) diagnostic dataset (2) multi-step reasoning (2) reward model (2) multimodal learning (1) text generation (1) batch normalization (1) gradient-based optimization (1) toxicity detection (1) temporal reasoning (1) data augmentation (1) data poisoning (1) multimodal interaction (1) prompt learning (1) language model alignment (1)

Papers

InfAlign: Inference-aware language model alignment ICML 2025

Fundamental Limits of Perfect Concept Erasure AISTATS 2025

Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment CVPR 2025

Improving Neutral Point-of-View Generation with Data- and Parameter-Efficient RL EMNLP 2025

Block Verification Accelerates Speculative Decoding ICLR 2025

Safety Alignment Should be Made More Than Just a Few Tokens Deep ICLR 2025

Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment ICLR 2025

Generalization and Robustness of the Tilted Empirical Risk ICML 2025

Theoretical guarantees on the best-of-n alignment policy ICML 2025

Controlled Decoding from Language Models ICML 2024

Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment EMNLP 2024

FRAPPÉ: A Group Fairness Framework for Post-Processing Everything ICML 2024

Enhancing Group Fairness in Online Settings Using Oblique Decision Forests ICLR 2024

Improving Robustness via Tilted Exponential Layer: A Communication-Theoretic Perspective AISTATS 2024

Gradient-Based Language Model Red Teaming EACL 2024

On Tilted Losses in Machine Learning: Theory and Applications JMLR 2023

Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts NIPS 2023

SpecTr: Fast Speculative Decoding via Optimal Transport NIPS 2023

Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting EMNLP 2023

Robust Conversational Agents against Imperceptible Toxicity Triggers NAACL 2022

Database Search Results Disambiguation for Task-Oriented Dialog Systems NAACL 2022

Know Thy Strengths: Comprehensive Dialogue State Tracking Diagnostics EMNLP 2022

DVD: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue IJCNLP 2021

Tilted Empirical Risk Minimization ICLR 2021

Ditto: Fair and Robust Federated Learning Through Personalization ICML 2021

DVD: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue ACL 2021

Rényi Fair Inference ICLR 2020

Situated and Interactive Multimodal Conversations COLING 2020

Resource Constrained Dialog Policy Learning Via Differentiable Inductive Logic Programming COLING 2020

Fair Resource Allocation in Federated Learning ICLR 2020

On Optimal Generalizability in Parametric Learning NIPS 2017