Ankur Sikarwar

How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning

Qian Yang, Ankur Sikarwar, Huy Le, Le Zhang et autres

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 images aims to fix this by generating an intermediate thinking-image, but recent work shows the visual evidence …

How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning

Qian Yang, Ankur Sikarwar, Huy Le, Le Zhang et autres

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 images aims to fix this by generating an intermediate thinking-image, but recent work shows the visual evidence …

Learning to See the Elephant in the Room: Self-Supervised Context Reasoning in Humans and AI

Mengmi Zhang, Xiao Liu, Soumick Sarker, Ankur Sikarwar et autres

sg, us (code pays fourni par la source)

Communicating about Space: Language-Mediated Spatial Integration Across Partial Views

Ankur Sikarwar, Debangan Mishra, Sudarshan Nikhil, Ponnurangam Kumaraguru et autres

Humans build shared spatial understanding by communicating partial, viewpoint-dependent observations. We ask whether Multimodal Large Language Models (MLLMs) can do the same, aligning distinct egocentric views through dialogue to form a coherent, allocentric mental model of a shared environment. To study this …

Communicating about Space: Language-Mediated Spatial Integration Across Partial Views

Ankur Sikarwar, Debangan Mishra, Sudarshan Nikhil, Ponnurangam Kumaraguru et autres

Humans build shared spatial understanding by communicating partial, viewpoint-dependent observations. We ask whether Multimodal Large Language Models (MLLMs) can do the same, aligning distinct egocentric views through dialogue to form a coherent, allocentric mental model of a shared environment. To study this …

The Promise of RL for Autoregressive Image Editing

Saba Ahmadi, Rabiul Awal, Ankur Sikarwar, Amirhossein Kazemnejad et autres

us, ca, sg, gb, Algérie (code pays fourni par la source)

Learning to Learn: How to Continuously Teach Humans and Machines

Parantak Singh, You Li, Ankur Sikarwar, Weixian Lei et autres

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 and other concepts must be mastered before our first algebra lesson, which also reinforces our …

sg, us (code pays fourni par la source)

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 and decision-making tasks. Robust benchmark datasets that capture the multifaceted nature of WM are crucial for the effective development …

Decoding the Enigma: Benchmarking Humans and AIs on the Many Facets of Working Memory

Ankur Sikarwar, Mengmi Zhang

Learning to Learn: How to Continuously Teach Humans and Machines

Parantak Singh, You Li, Ankur Sikarwar, Weixian Lei et autres

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 and other concepts must be mastered before our first algebra lesson, which also reinforces our …

Learning to See the Elephant in the Room: Self-Supervised Context Reasoning in Humans and AI

Xiao Liu, Ankur Sikarwar, Gabriel Kreiman, Zenglin Shi et autres

Humans rarely perceive objects in isolation but interpret scenes through relationships among co-occurring elements. How such contextual knowledge is acquired without explicit supervision remains unclear. Here we combine human psychophysics experiments with computational modelling to study the emergence of contextual reasoning. Participants …

Can Machines Imitate Humans? Integrative Turing-like tests for Language and Vision Demonstrate a Narrowing Gap

Mengmi Zhang, Giorgia Dellaferrera, Ankur Sikarwar, Marcelo Armendáriz et autres

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 tasks (image captioning, word association, conversation) and three vision tasks (color estimation, object detection, attention …