2 citations · 3 across the 9 of their papers we have counts for
9 papers
How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning
Qian Yang, Ankur Sikarwar, Huy Le +4
Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they reason in language and discard the fine-grained geometry the task requires. Thinking with i…
Communicating about Space: Language-Mediated Spatial Integration Across Partial Views
Ankur Sikarwar, Debangan Mishra, Sudarshan Nikhil +2
Humans build shared spatial understanding by communicating partial, viewpoint-dependent observations. We ask whether Multimodal Large Language Models (MLLMs) can do the same, align…
The Promise of RL for Autoregressive Image Editing
Saba Ahmadi, Rabiul Awal, Ankur Sikarwar +8
While image generation techniques are now capable of producing high-quality images that respect prompts which span multiple sentences, the task of text-guided image editing remains…
Decoding the Enigma: Benchmarking Humans and AIs on the Many Facets of Working Memory
Ankur Sikarwar, Mengmi Zhang
Working memory (WM), a fundamental cognitive process facilitating the temporary storage, integration, manipulation, and retrieval of information, plays a vital role in reasoning an…
Learning to Learn: How to Continuously Teach Humans and Machines
Parantak Singh, You Li, Ankur Sikarwar +7
Curriculum design is a fundamental component of education. For example, when we learn mathematics at school, we build upon our knowledge of addition to learn multiplication. These…
Can Machines Imitate Humans? Integrative Turing-like tests for Language and Vision Demonstrate a Narrowing Gap
Mengmi Zhang, Elisa Pavarino, Xiao Liu +20
As AI becomes increasingly embedded in daily life, ascertaining whether an agent is human is critical. We systematically benchmark AI's ability to imitate humans in three language…
Learning to See the Elephant in the Room: Self-Supervised Context Reasoning in Humans and AI
Xiao Liu, Soumick Sarker, Ankur Sikarwar +4
Humans rarely perceive objects in isolation but interpret scenes through relationships among co-occurring elements. How such contextual knowledge is acquired without explicit super…
When Can Transformers Ground and Compose: Insights from Compositional Generalization Benchmarks
Ankur Sikarwar, Arkil Patel, Navin Goyal
Humans can reason compositionally whilst grounding language utterances to the real world. Recent benchmarks like ReaSCAN use navigation tasks grounded in a grid world to assess whe…
On the Efficacy of Co-Attention Transformer Layers in Visual Question Answering
Ankur Sikarwar, Gabriel Kreiman
In recent years, multi-modal transformers have shown significant progress in Vision-Language tasks, such as Visual Question Answering (VQA), outperforming previous architectures by…