187 citations · 1.6k across the 127 of their papers we have counts for
155 papers
Decentralized LLM Workflows via Sequential Auctions
Ian Gemp, Shubhendu Trivedi, Adam Fisch +7
We present a scalable framework for solving multi-step tasks through a decentralized market of self-interested agents. Prior theoretical work demonstrated that agents organized thr…
Beyond Context Length: Characterising the Difficulty of Long-Context Reasoning
Shiwen Qin, Cameron Barker, Henry Gouk +4
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…
Strategically Diverse Sampling for Self-Training
Alexander Gurung, Esmeralda S. Whitammer, Mirella Lapata
Many LLM training and inference methods, including RL and test-time scaling, depend on repeated sampling, but benefit only when the responses meaningfully differ. Self-training fac…
What, When, and How: Audio Description as Constrained Global Optimization
Igor Sterner, Mirella Lapata, Alex Lascarides +1
Audio Description (AD) makes movies accessible to blind and visually impaired audiences by narrating visual information in gaps between dialogue. Existing automatic AD systems larg…
A Table Is Worth 64 Tokens: Pixel-level Compression for Multi-Table Document Question Answering
Iñigo Alonso, Mirella Lapata
Answering questions over real-world documents requires processing long inputs that interleave text with tables. Optical context compression, which represents context as images, pro…
Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation
Adam Fisch, Shubhendu Trivedi, Fantine Huot +5
Heterogeneous AI systems composed of multiple models, architectures, harnesses, or inference-time settings can improve quality and efficiency by routing queries to the specialist w…