5 papers
Is the Judge Its Twin? Post-training makes a model's writing more predictable but barely moves its taste, as a judge, toward predictable writing
Arman Nik Khah, Arvin Bahreini
Language models now routinely grade other language models. If post-training makes a model's writing more predictable, it may also teach the same model, as a judge, to reward predic…
Easy to Catch a Liar, Hard to Clear an Honest One: Language Models Diagnosing a Corrupted Reward Channel from a Verified Record
Arman Nik Khah
An agent that learns from rewards has to trust whatever reports those rewards. When the reports suddenly change, either the world changed or the reporter broke. From the reports al…
Detectable Only Where It Is Confounded: What Verified Duplication Counts Say About Membership Evidence in Language Models
Arman Nik Khah
When a language model finds a sentence unusually cheap to predict, it is tempting to conclude that the sentence was in its training data. Almost every published test of that infere…
Meaning over Motion: A Semantic-First Approach to 360° Viewport Prediction
Arman Nik Khah, Arvin Bahreini, Ravi Prakash
Ultra-high-resolution 360-degree video streaming is severely constrained by the massive bandwidth required to deliver immersive experiences. Current viewport prediction techniques…
Listen to the Unexpected: Self-Supervised Surprise Detection for Efficient Viewport Prediction
Arman Nik Khah, Ravi Prakash
Adaptive streaming of 360-degree video relies on viewport prediction to allocate bandwidth efficiently. Current approaches predominantly use visual saliency or historical gaze patt…