4 papers
SearchWiki: Learning to Build and Navigate Knowledge Wikis for Active Information Seeking
Guransh Singh, Vishwajeet Kumar, Arkadeep Acharya +3
Flat retrieval-augmented generation treats a corpus as a bag of chunks, discarding document hierarchy and cross document structure. We introduce SearchWiki, a harness framework tha…
AEGIS: Anchor-Enforced Gradient Isolation for Knowledge-Preserving Vision-Language-Action Fine-Tuning
Guransh Singh
Fine-tuning pre-trained Vision-Language Models (VLMs) for robotic manipulation introduces a fundamental stability-plasticity dilemma: continuous flow-matching action experts backpr…
StutterFuse: Mitigating Modality Collapse in Stuttering Detection with Jaccard-Weighted Metric Learning and Gated Fusion
Guransh Singh, Md Shah Fahad
Stuttering detection breaks down when disfluencies overlap. Existing parametric models struggle to distinguish complex, simultaneous disfluencies (e.g., a 'block' with a 'prolongat…
EnzyCLIP: A Cross-Attention Dual Encoder Framework with Contrastive Learning for Predicting Enzyme Kinetic Constants
Anas Aziz Khan, Md Shah Fahad, Priyanka +2
Accurate prediction of enzyme kinetic parameters is crucial for drug discovery, metabolic engineering, and synthetic biology applications. Current computational approaches face lim…