8 citations · 8 across the 3 of their papers we have counts for
5 papers
DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation
Karn Tiwari, Varnith Chordia, Prathosh A P
On-policy distillation (OPD) has emerged as a widely used paradigm for post-training large language models, reducing the train--test mismatch of conventional distillation by superv…
Spectral Query-Key Product Weight Steering for Training-Free VLM Hallucination Mitigation
Karn Tiwari, Varnith Chordia, Prathosh A P
Vision-language models (VLMs) often generate fluent but visually unsupported descriptions, especially by mentioning objects absent from the image. We propose QK Product Steering, a…
Mind the Time: Temporally-Controlled Multi-Event Video Generation
Ziyi Wu, Aliaksandr Siarohin, Willi Menapace +5
Real-world videos consist of sequences of events. Generating such sequences with precise temporal control is infeasible with existing video generators that rely on a single paragra…
STRIVE: Scene Text Replacement In Videos
Vijay Kumar B G, Jeyasri Subramanian, Varnith Chordia +4
We propose replacing scene text in videos using deep style transfer and learned photometric transformations.Building on recent progress on still image text replacement,we present e…
Large Scale Multimodal Classification Using an Ensemble of Transformer Models and Co-Attention
Varnith Chordia, Vijay Kumar BG
Accurate and efficient product classification is significant for E-commerce applications, as it enables various downstream tasks such as recommendation, retrieval, and pricing. Ite…