2 papers
cs.CV2026
Swift Sampling: Selecting Temporal Surprises via Taylor Series
Dahye Kim, Bhuvan Sachdeva, Karan Uppal +3
While most frames in long-form video are redundant, the critical information resides in temporal surprises: moments where the actual visual features deviate from their predicted ev…
cs.CV2026
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…