We have 11 of 394 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Long-context language models support ever longer context windows, and evaluations typically treat context length as the main indicator of difficulty. However, context length alone cannot explain why models fail on long-context tasks that require reasoning over complex information. Contexts of equal length can pose very...
Across a diverse set of domains, it is demonstrated that imperfect competition successfully sustains necessary agent profit margins while maintaining high task success rates at low costs.
Abstract Background Large language models (LLMs) are increasingly demonstrating the potential to reach human-level performance in generating clinical summaries from patient-clinician conversations. LLMs are usually evaluated against clinical summaries that focus mainly on patients’ biology and not on their biography (e...
This work investigates strategic diversity, or substantive variation among approaches to a problem, as an alternative principle for constructing self-training data with two sampling methods: GROOT, a new method which constructs a hierarchical tree of approaches and samples distinct paths, and Verbalized Sampling, adapt...
This hybrid system uses large language models to propose and ground visual elements, estimate their salience to the narrative, and generate compressed realizations, which makes better decisions than prompted LLMs about what to describe and when to describe it.
This work uses Reinforced Self-Training (ReST) to train the model to achieve high reward and shows this leads to a steerable policy that changes its behavior predictably conditioned on the provided costs, leading to higher reward and accuracy.
A training-free, two-step method that identifies the tables needed to answer a question from a pixel-compressed context, and then reasons over those at native resolution, with no accuracy loss.
This work introduces a new formulation of AD generation in which models must jointly decide what to describe and when to do it, and presents REFRAMED, a high-quality dataset of 2,023 videos that span 3,302 scenes from 206 movies, with professional AD transcripts, professional subtitles and aligned screenplays.
Dynamic Heterogeneous Character Networks are introduced, which organize long novels into temporally localized heterogeneous graphs that align characters with their textual contexts, and GraphLit is proposed, a self-supervised learning framework that learns rich literary representations through a masked graph autoencode...
Experiments across three domains show that Pandora's Router matches the routing quality of exhaustive estimation, while querying the expensive estimator far less often.
Routing policies for multi-model systems are evaluated almost exclusively on task accuracy and inference cost. We argue that two properties, orthogonal to performance, determine whether routing is meaningful. First, the society of actors must be behaviourally differentiated: if all actors respond identically, routing i...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
