Phillip Howard

53 papers A* 6A 1Journal 34Unranked 12
YearRankTypeTitle / Venue / Authors
2026 J jnl
Cultural Counterfactuals: Evaluating Cultural Biases in Large Vision-Language Models with Counterfactual Examples.
CoRR
Phillip Howard, Xin Su, Kathleen C. Fraser
2026 J jnl
DreamReader: An Interpretability Toolkit for Text-to-Image Models.
CoRR
Nirmalendu Prakash, Narmeen Oozeer, Michael Lan, Luka Samkharadze, Phillip Howard, Roy Ka-Wei Lee, Dhruv Nathawani, Shivam Raval, Amirali Abdullah
2026 A* conf
Learning from Reasoning Failures via Synthetic Data Generation.
AAAI
Gabriela Ben Melech Stan, Estelle Aflalo, Avinash Madasu, Vasudev Lal, Phillip Howard
2025 J jnl
A Semantic Parsing Framework for End-to-End Time Normalization.
CoRR
Xin Su, Sungduk Yu, Phillip Howard, Steven Bethard
2025 — conf
Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders.
CVPR Workshops
Matthew Lyle Olson, Musashi Hinck, Neale Ratzlaff, Changbai Li, Phillip Howard, Vasudev Lal, Shao-Yen Tseng
2025 J jnl
Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders.
CoRR
Matthew Lyle Olson, Musashi Hinck, Neale Ratzlaff, Changbai Li, Phillip Howard, Vasudev Lal, Shao-Yen Tseng
2025 J jnl
Benchmark on Peer Review Toxic Detection: A Challenging Task with a New Dataset.
CoRR
Man Luo, Bradley Peterson, Rafael Gan, Hari Ramalingame, Navya Gangrade, Ariadne Dimarogona, Imon Banerjee, Phillip Howard
2025 J jnl
Cultural Awareness in Vision-Language Models: A Cross-Country Exploration.
CoRR
Avinash Madasu, Vasudev Lal, Phillip Howard
2025 J jnl
DPO Learning with LLMs-Judge Signal for Computer Use Agents.
CoRR
Man Luo, David Cobbley, Xin Su, Shachar Rosenman, Vasudev Lal, Shao-Yen Tseng, Phillip Howard
2025 — conf
Debias Your Large Multi-Modal Model at Test-Time via Non-Contrastive Visual Attribute Steering.
ICCVW
Neale Ratzlaff, Matthew Lyle Olson, Musashi Hinck, Shao-Yen Tseng, Vasudev Lal, Phillip Howard
2025 J jnl
Investigating the Robustness of Retrieval-Augmented Generation at the Query Level.
CoRR
Sezen Perçin, Xin Su, Syed Sha Qutub, Phillip Howard, Aleksei Kuvshinov, Leo Schwinn, Kay-Ulrich Scholl
2025 J jnl
Is Your Paper Being Reviewed by an LLM? A New Benchmark Dataset and Approach for Detecting AI Text in Peer Review.
CoRR
Sungduk Yu, Man Luo, Avinash Madusu, Vasudev Lal, Phillip Howard
2025 — conf
LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression.
NAACL (Findings)
Souvik Kundu, Anahita Bhiwandiwalla, Sungduk Yu, Phillip Howard, Tiep Le, Sharath Nittur Sridhar, David Cobbley, Hao Kang, Vasudev Lal
2025 J jnl
LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression.
CoRR
Souvik Kundu, Anahita Bhiwandiwalla, Sungduk Yu, Phillip Howard, Tiep Le, Sharath Nittur Sridhar, David Cobbley, Hao Kang, Vasudev Lal
2025 J jnl
Learning from Reasoning Failures via Synthetic Data Generation.
CoRR
Gabriela Ben Melech Stan, Estelle Aflalo, Avinash Madasu, Vasudev Lal, Phillip Howard
2025 — conf
Probing the Representational Power of Sparse Autoencoders in Vision Models.
ICCVW
Matthew L. Olson, Musashi Hinck, Neale Ratzlaff, Changbai Li, Phillip Howard, Vasudev Lal, Shao-Yen Tseng
2025 J jnl
Probing the Representational Power of Sparse Autoencoders in Vision Models.
CoRR
Matthew Lyle Olson, Musashi Hinck, Neale Ratzlaff, Changbai Li, Phillip Howard, Vasudev Lal, Shao-Yen Tseng
2025 A* conf
Pruning the Paradox: How CLIP's Most Informative Heads Enhance Performance While Amplifying Bias.
EMNLP
Avinash Madasu, Vasudev Lal, Phillip Howard
2025 J jnl
Quantifying Interpretability in CLIP Models with Concept Consistency.
CoRR
Avinash Madasu, Vasudev Lal, Phillip Howard
2025 A* conf
SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs.
ICML
Xin Su, Man Luo, Kris W. Pan, Tien Pei Chou, Vasudev Lal, Phillip Howard
2025 — conf
Training-Free Mitigation of Language Reasoning Degradation After Multimodal Instruction Tuning.
AAAI Spring Symposia
Neale Ratzlaff, Man Luo, Xin Su, Vasudev Lal, Phillip Howard
2025 A* conf
Transformer-Based Temporal Information Extraction and Application: A Review.
EMNLP
Xin Su, Phillip Howard, Steven Bethard
2025 J jnl
Transformer-Based Temporal Information Extraction and Application: A Review.
CoRR
Xin Su, Phillip Howard, Steven Bethard
2025 — conf
Uncovering Bias in Large Vision-Language Models at Scale with Counterfactuals.
NAACL (Long Papers)
Phillip Howard, Kathleen C. Fraser, Anahita Bhiwandiwalla, Svetlana Kiritchenko
2024 J jnl
Debias your Large Multi-Modal Model at Test-Time with Non-Contrastive Visual Attribute Steering.
CoRR
Neale Ratzlaff, Matthew Lyle Olson, Musashi Hinck, Estelle Aflalo, Shao-Yen Tseng, Vasudev Lal, Phillip Howard
2024 J jnl
Debiasing Large Vision-Language Models by Ablating Protected Attribute Representations.
CoRR
Neale Ratzlaff, Matthew Lyle Olson, Musashi Hinck, Shao-Yen Tseng, Vasudev Lal, Phillip Howard
2024 J jnl
Distill-SynthKG: Distilling Knowledge Graph Synthesis Workflow for Improved Coverage and Efficiency.
CoRR
Prafulla Kumar Choubey, Xin Su, Man Luo, Xiangyu Peng, Caiming Xiong, Tiep Le, Shachar Rosenman, Vasudev Lal, Phil Mui, Ricky Ho Yin Chan, Phillip Howard, Chien-Sheng Wu
2024 J jnl
Is Your Paper Being Reviewed by an LLM? Investigating AI Text Detectability in Peer Review.
CoRR
Sungduk Yu, Man Luo, Avinash Madasu, Vasudev Lal, Phillip Howard
2024 — conf
NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge.
NAACL-HLT (Findings)
Phillip Howard, Junlin Wang, Vasudev Lal, Gadi Singer, Yejin Choi, Swabha Swayamdipta
2024 — conf
NeuroPrompts: An Adaptive Framework to Optimize Prompts for Text-to-Image Generation.
EACL (Demonstrations)
Shachar Rosenman, Vasudev Lal, Phillip Howard
2024 J jnl
Quantifying and Enabling the Interpretability of CLIP-like Models.
CoRR
Avinash Madasu, Yossi Gandelsman, Vasudev Lal, Phillip Howard
2024 J jnl
SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs.
CoRR
Xin Su, Man Luo, Kris W. Pan, Tien Pei Chou, Vasudev Lal, Phillip Howard
2024 — conf
Semi-Structured Chain-of-Thought: Integrating Multiple Sources of Knowledge for Improved Language Model Reasoning.
NAACL-HLT
Xin Su, Tiep Le, Steven Bethard, Phillip Howard
2024 A* conf
SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples.
CVPR
Phillip Howard, Avinash Madasu, Tiep Le, Gustavo A. Lujan-Moreno, Anahita Bhiwandiwalla, Vasudev Lal
2024 J jnl
Training-Free Mitigation of Language Reasoning Degradation After Multimodal Instruction Tuning.
CoRR
Neale Ratzlaff, Man Luo, Xin Su, Vasudev Lal, Phillip Howard
2024 J jnl
Uncovering Bias in Large Vision-Language Models at Scale with Counterfactuals.
CoRR
Phillip Howard, Kathleen C. Fraser, Anahita Bhiwandiwalla, Svetlana Kiritchenko
2024 J jnl
Uncovering Bias in Large Vision-Language Models with Counterfactuals.
CoRR
Phillip Howard, Anahita Bhiwandiwalla, Kathleen C. Fraser, Svetlana Kiritchenko
2023 A* conf
COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs.
NeurIPS
Tiep Le, Vasudev Lal, Phillip Howard
2023 J jnl
COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs.
CoRR
Tiep Le, Vasudev Lal, Phillip Howard
2023 — conf
Fusing Temporal Graphs into Transformers for Time-Sensitive Question Answering.
EMNLP (Findings)
Xin Su, Phillip Howard, Nagib Hakim, Steven Bethard
2023 J jnl
Fusing Temporal Graphs into Transformers for Time-Sensitive Question Answering.
CoRR
Xin Su, Phillip Howard, Nagib Hakim, Steven Bethard
2023 J jnl
NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge.
CoRR
Phillip Howard, Junlin Wang, Vasudev Lal, Gadi Singer, Yejin Choi, Swabha Swayamdipta
2023 J jnl
NeuroPrompts: An Adaptive Framework to Optimize Prompts for Text-to-Image Generation.
CoRR
Shachar Rosenman, Vasudev Lal, Phillip Howard
2023 J jnl
Probing Intersectional Biases in Vision-Language Models with Counterfactual Examples.
CoRR
Phillip Howard, Avinash Madasu, Tiep Le, Gustavo A. Lujan-Moreno, Vasudev Lal
2023 J jnl
Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples.
CoRR
Phillip Howard, Avinash Madasu, Tiep Le, Gustavo A. Lujan-Moreno, Anahita Bhiwandiwalla, Vasudev Lal
2023 J jnl
Semi-Structured Chain-of-Thought: Integrating Multiple Sources of Knowledge for Improved Language Model Reasoning.
CoRR
Xin Su, Tiep Le, Steven Bethard, Phillip Howard
2023 J jnl
Thrill-K Architecture: Towards a Solution to the Problem of Knowledge Based Understanding.
CoRR
Gadi Singer, Joscha Bach, Tetiana Grinberg, Nagib Hakim, Phillip Howard, Vasudev Lal, Zev Rivlin
2022 A conf
Cross-Domain Aspect Extraction using Transformers Augmented with Knowledge Graphs.
CIKM
Phillip Howard, Arden Ma, Vasudev Lal, Ana Paula Simões, Daniel Korat, Oren Pereg, Moshe Wasserblat, Gadi Singer
2022 J jnl
Cross-Domain Aspect Extraction using Transformers Augmented with Knowledge Graphs.
CoRR
Phillip Howard, Arden Ma, Vasudev Lal, Ana Paula Simões, Daniel Korat, Oren Pereg, Moshe Wasserblat, Gadi Singer
2022 — conf
NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation.
EMNLP (Findings)
Phillip Howard, Gadi Singer, Vasudev Lal, Yejin Choi, Swabha Swayamdipta
2022 J jnl
NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation.
CoRR
Phillip Howard, Gadi Singer, Vasudev Lal, Yejin Choi, Swabha Swayamdipta
2021 — conf
InterpreT: An Interactive Visualization Tool for Interpreting Transformers.
EACL (System Demonstrations)
Vasudev Lal, Arden Ma, Estelle Aflalo, Phillip Howard, Ana Paula Simões, Daniel Korat, Oren Pereg, Gadi Singer, Moshe Wasserblat
2018 J jnl
Distinct Variation Pattern Discovery Using Alternating Nonlinear Principal Component Analysis.
IEEE Trans. Neural Networks Learn. Syst.
Phillip Howard, Daniel W. Apley, George Runger