3 papers
cs.AI2026
Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models
Xingang Guo, Jing Gu, Brian Jang +26
Humans perceive far more in a scene than what is explicitly depicted: a single glance captures past causes and future trajectories; a quick peek determines if a vehicle can fit bet…
cs.CL2026
Exact semantic readout from compressed vector representations
Daniel Quigley
We characterize when compressed vector representations admit exact linear or affine readouts of a finite lexicon's truth conditions: one fixed map per predicate, sending each entit…
cs.AI2026
SteerDuplex: Steerable Duplex Speech Dialogue Models
Utkarsh Tyagi, Ramaneswaran Selvakumar, Advait Gosai +13
Full-duplex spoken dialogue models support low-latency turn taking, interruption handling, and backchanneling, yet a key capability remains underexplored: steerability, the ability…