3 papers
cs.CV2026
MINERVA-Cultural: A Benchmark for Cultural and Multilingual Long Video Reasoning
Darshan Singh, Arsha Nagrani, Kawshik Manikantan +6
Recent advancements in video models have shown tremendous progress, particularly in long video understanding. However, current benchmarks predominantly feature western-centric data…
cs.CL2024
IdentifyMe: A Challenging Long-Context Mention Resolution Benchmark for LLMs
Kawshik Manikantan, Makarand Tapaswi, Vineet Gandhi +1
Recent evaluations of LLMs on coreference resolution have revealed that traditional output formats and evaluation metrics do not fully capture the models' referential understanding…
cs.CL2024
Major Entity Identification: A Generalizable Alternative to Coreference Resolution
Kawshik Manikantan, Shubham Toshniwal, Makarand Tapaswi +1
The limited generalization of coreference resolution (CR) models has been a major bottleneck in the task's broad application. Prior work has identified annotation differences, espe…