Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations.

[BibT_eX]

[DOI]

Abhilekh Borah

Chhavi Sharma

CoRR, June, 2025

AdversariaL attacK sAfety aLIgnment(ALKALI): Safeguarding LLMs through GRACE: Geometric Representation-Aware Contrastive Enhancement- Introducing Adversarial Vulnerability Quality Index (AVQI).

[BibT_eX]

[DOI]

CoRR, June, 2025

Pruning for Performance: Efficient Idiom and Metaphor Classification in Low-Resource Konkani Using mBERT.

[BibT_eX]

[DOI]

CoRR, June, 2025

NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative Contexts.

[BibT_eX]

[DOI]

CoRR, June, 2025

Sarc7: Evaluating Sarcasm Detection and Generation with Seven Types and Emotion-Informed Techniques.

[BibT_eX]

[DOI]

CoRR, June, 2025

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs.

[BibT_eX]

[DOI]

CoRR, May, 2025

Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation.

[BibT_eX]

[DOI]

CoRR, May, 2025

Advancing Uto-Aztecan Language Technologies: A Case Study on the Endangered Comanche Language.

[BibT_eX]

[DOI]

CoRR, May, 2025

Deconstructing Bias: A Multifaceted Framework for Diagnosing Cultural and Compositional Inequities in Text-to-Image Generative Models.

[BibT_eX]

[DOI]

CoRR, May, 2025

Rosetta-PL: Propositional Logic as a Benchmark for Large Language Model Reasoning.

[BibT_eX]

[DOI]

Shaun Lee Baek

Shaun Esua-Mensah

Cyrus Tsui

Sejan Vigneswaralingam

CoRR, May, 2025

Incorporating a Deep Neural Network into Moving Horizon Estimation for Embedded Thermal Torque Derating of an Electric Machine.

[BibT_eX]

[DOI]

CoRR, April, 2025

TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Models.

[BibT_eX]

[DOI]

CoRR, March, 2025

Pause-Tuning for Long-Context Comprehension: A Lightweight Approach to LLM Attention Recalibration.

[BibT_eX]

[DOI]

CoRR, February, 2025

Safe Reinforcement Learning-based Control for Hydrogen Diesel Dual-Fuel Engines.

[BibT_eX]

[DOI]

CoRR, February, 2025

YINYANG-ALIGN: Benchmarking Contradictory Objectives and Proposing Multi-Objective Optimization based DPO for Text-to-Image Alignment.

[BibT_eX]

[DOI]

CoRR, February, 2025

Rosetta-PL: Propositional Logic as a Benchmark for Large Language Model Reasoning.

[BibT_eX]

[DOI]

Shaun Lee Baek

Shaun Esua-Mensah

Cyrus Tsui

Sejan Vigneswaralingam

Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization.

[BibT_eX]

[DOI]

Aishwarya Naresh Reganti

Aman Chadha

Proceedings of the Findings of the Association for Computational Linguistics, 2025

YinYang-Align: A new Benchmark for Competing Objectives and Introducing Multi-Objective Preference based Text-to-Image Alignment.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024

DINOv2: Learning Robust Visual Features without Supervision.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2024

The Brittleness of AI-Generated Image Watermarking Techniques: Examining Their Robustness Against Visual Paraphrasing Attacks.

[BibT_eX]

[DOI]

CoRR, 2024

An Introduction to Vision-Language Modeling.

[BibT_eX]

[DOI]

CoRR, 2024

Text Quality-Based Pruning for Efficient Training of Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM.

[BibT_eX]

[DOI]

CoRR, 2024

ε-ViLM : Efficient Video-Language Model via Masked Video Modeling with Semantic Vector-Quantized Tokenizer.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, 2024

Demystifying CLIP Data.

[BibT_eX]

[DOI]

Christoph Feichtenhofer

Proceedings of the Twelfth International Conference on Learning Representations, 2024

A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions.

[BibT_eX]

[DOI]

Adriana Romero-Soriano

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023

E-ViLM: Efficient Video-Language Model via Masked Video Modeling with Semantic Vector-Quantized Tokenizer.

[BibT_eX]

[DOI]

CoRR, 2023

Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning.

[BibT_eX]

[DOI]

CoRR, 2023

Alexa, play with robot: Introducing the First Alexa Prize SimBot Challenge on Embodied AI.

[BibT_eX]

[DOI]

CoRR, 2023

Alexa Arena: A User-Centric Interactive Platform for Embodied AI.

[BibT_eX]

[DOI]

CoRR, 2023

Alexa Arena: A User-Centric Interactive Platform for Embodied AI.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

MAViL: Masked Audio-Video Learners.

[BibT_eX]

[DOI]

Christoph Feichtenhofer

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Shimmy: Accelerating Inter-Container Communication for the IoT Edge.

[BibT_eX]

[DOI]

Proceedings of the IEEE Global Communications Conference, 2023

Flap: Fast Language-Audio Pre-Training.

[BibT_eX]

[DOI]

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023

2022

CH-MARL: A Multimodal Benchmark for Cooperative, Heterogeneous Multi-Agent Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, 2022

PISA: PoIncaré Saliency-Aware Interpolative Augmentation.

[BibT_eX]

[DOI]

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

Tweet Based Reach Aware Temporal Attention Network for NFT Valuation.

[BibT_eX]

[DOI]

Ramit Sawhney

Megh Thakkar

Ritesh Soun

Atula Tejaswi Neerkaje

Vasu Sharma

Dipanwita Guhathakurta

Sudheer Chava

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2022, 2022

2019

Induced Attention Invariance: Defending VQA Models against Adversarial Attacks.

[BibT_eX]

[DOI]

Vasu Sharma

Ankita Kalra

Louis-Philippe Morency

Proceedings of the Visually Grounded Interaction and Language (ViGIL), 2019

Multimodal Behavioral Markers Exploring Suicidal Intent in Social Media Videos.

[BibT_eX]

[DOI]

Louis-Philippe Morency

Proceedings of the International Conference on Multimodal Interaction, 2019

Community Regularization of Visually-Grounded Dialog.

[BibT_eX]

[DOI]

Akshat Agarwal

Swaminathan Gurumurthy

Vasu Sharma

Mike Lewis

Katia P. Sycara

Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, 2019

2018

Mind Your Language: Learning Visually Grounded Dialog in a Multi-Agent Setting.

[BibT_eX]

[DOI]

Akshat Agarwal

Swaminathan Gurumurthy

Vasu Sharma

Katia P. Sycara

CoRR, 2018

Cyclegen: Cyclic consistency based product review generator from attributes.

[BibT_eX]

[DOI]

Proceedings of the 11th International Conference on Natural Language Generation, 2018

BioAMA: Towards an End to End BioMedical Question Answering System.

[BibT_eX]

[DOI]

Proceedings of the BioNLP 2018 workshop, Melbourne, Australia, July 19, 2018, 2018

2017

Segmentation Guided Attention Networks for Visual Question Answering.

[BibT_eX]

[DOI]

Vasu Sharma

Ankita Bishnu

Labhesh Patel

Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 2017

2016

Automatic tagging and retrieval of E-Commerce products based on visual features.

[BibT_eX]

[DOI]

Vasu Sharma

Harish Karnick

Proceedings of the Student Research Workshop, 2016

2015

Analyzing Newspaper Crime Reports for Identification of Safe Transit Paths.

[BibT_eX]

[DOI]

Proceedings of the NAACL HLT 2015, The 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Denver, Colorado, USA, May 31, 2015

Image summarization using topic modelling.

[BibT_eX]

[DOI]

Proceedings of the 2015 IEEE International Conference on Signal and Image Processing Applications, 2015

A Deep Neural Network based approach for vocal extraction from songs.

[BibT_eX]

[DOI]