7 papers
One Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models
Aditya Sharma, Divya Saxena
Contrastive vision-language models learn shared embedding spaces by aligning matched image-text pairs, yet their representations remain separated by a modality gap. Prior work repo…
When Prompts Ignore Structure: Graph-Based Attribute Reasoning for Calibrated VLMs
Tanay Sodha, Aditya Sharma, Ramya Hebbalaguppe +2
Reliable confidence estimation remains a key limitation of test-time adaptation in vision-language models (VLMs), where prompt tuning improves zero-shot accuracy but often degrades…
Rotate2Think: Geometric Priming via Orthogonal Rotation to Improve Language Model Reasoning
Aditya Sharma, Christopher J. Pal, Amal Zouaq
Reasoning models achieve strong performance on challenging tasks by generating explicit intermediate reasoning traces before producing a final answer. Yet the internal structure of…
Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards
Luis Lara, Aristides Milios, Zhi Hao Luo +5
An AI system for professional floor plan design must precisely control room dimensions and areas while respecting the desired connectivity between rooms and maintaining functional…
G-Loss: Graph-Guided Fine-Tuning of Language Models
Aditya Sharma, Vinti Agarwal, Rajesh Kumar
Traditional loss functions, including cross-entropy, contrastive, triplet, and su pervised contrastive losses, used for fine-tuning pre-trained language models such as BERT, operat…
Losing Visual Needles in Image Haystacks: Vision Language Models are Easily Distracted in Short and Long Contexts
Aditya Sharma, Michael Saxon, William Yang Wang
We present LoCoVQA, a dynamic benchmark generator for evaluating long-context extractive reasoning in vision language models (VLMs). LoCoVQA augments test examples for mathematical…
Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2)
Michael Saxon, Fatima Jahara, Mahsa Khoshnoodi +3
With advances in the quality of text-to-image (T2I) models has come interest in benchmarking their prompt faithfulness -- the semantic coherence of generated images to the prompts…