5 papers
Understanding Task Transfer in Vision-Language Models
Bhuvan Sachdeva, Karan Uppal, Abhinav Java +1
Vision-Language Models (VLMs) perform well on multimodal benchmarks but lag behind humans and specialized models on visual perception tasks like depth estimation or object counting…
FrugalRAG: Less is More in RL Finetuning for Multi-Hop Question Answering
Abhinav Java, Srivathsan Koundinyan, Nagarajan Natarajan +1
Reinforcement learning (RL) based on the final answer's reward has driven recent progress in small language models (SLMs) on reasoning-heavy tasks such as math and code. However, a…
Characterizing Deep Research: A Benchmark and Formal Definition
Abhinav Java, Ashmit Khandelwal, Sukruta Midigeshi +6
Information tasks such as writing surveys or analytical reports require complex search and reasoning, and have recently been grouped under the umbrella of \textit{deep research} --…
Towards Efficient Exemplar Based Image Editing with Multimodal VLMs
Avadhoot Jadhav, Ashutosh Srivastava, Abhinav Java +4
Text-to-Image Diffusion models have enabled a wide array of image editing applications. However, capturing all types of edits through text alone can be challenging and cumbersome.…
LEAST: "Local" text-conditioned image style transfer
Silky Singh, Surgan Jandial, Simra Shahid +1
Text-conditioned style transfer enables users to communicate their desired artistic styles through text descriptions, offering a new and expressive means of achieving stylization.…