collaborators

14 papers

cs.CV2026

VSAS-Bench: Real-Time Evaluation of Visual Streaming Assistant Models

Pavan Kumar Anasosalu Vasu, Cem Koc, Fartash Faghri +6

Streaming vision-language models (VLMs) continuously generate responses given an instruction prompt and an online stream of input frames. This is a core mechanism for real-time vis…

cs.CL2026

Pretraining with hierarchical memories: separating long-tail and common knowledge

Hadi Pouransari, David Grangier, C Thomas +2

The impressive performance gains of modern language models currently rely on scaling parameters: larger models store more world knowledge and reason better. Yet compressing all wor…

cs.CL2025

Learning from Self Critique and Refinement for Faithful LLM Summarization

Ting-Yao Hu, Hema Swetha Koppula, Hadi Pouransari +3

Large Language Models (LLMs) often suffer from hallucinations: output content that is not grounded in the input context, when performing long-form text generation tasks such as sum…

cs.LG2025

CPEP: Contrastive Pose-EMG Pre-training Enhances Gesture Generalization on EMG Signals

Wenhui Cui, Christopher Sandino, Hadi Pouransari +7

Hand gesture classification using high-quality structured data such as videos, images, and hand skeletons is a well-explored problem in computer vision. Leveraging low-power, cost-…

cs.CL2025

Datasets, Documents, and Repetitions: The Practicalities of Unequal Data Quality

Alex Fang, Hadi Pouransari, Matt Jordan +4

Data filtering has become a powerful tool for improving model performance while reducing computational cost. However, as large language model compute budgets continue to grow, the…

cs.CL2025

Learning to Reason for Hallucination Span Detection

Hsuan Su, Ting-Yao Hu, Hema Swetha Koppula +7

Large language models (LLMs) often generate hallucinations -- unsupported content that undermines reliability. While most prior works frame hallucination detection as a binary task…