3 papers
cs.LG2026
RaMP: Runtime-Aware Megakernel Polymorphism for Mixture-of-Experts
Vyom Sharma, Debajyoti Datta
The optimal kernel configuration for Mixture-of-Experts (MoE) inference depends on both batch size and the expert routing distribution, yet production systems dispatch from batch s…
cs.HC2026
Perfecting Human-AI Interaction at Clinical Scale. Turning Production Signals into Safer, More Human Conversations
Subhabrata Mukherjee, Markel Sanz Ausin, Kriti Aggarwal +24
Healthcare conversational AI agents shouldn't be optimized only for clean benchmark accuracy in production-first regime; they must be optimized for the lived reality of patient con…
cs.LG2026
ManifoldKV: Training-Free KV Cache Compression via Euclidean Outlier Detection
Debajyoti Datta, Trishala Neeraj, Bibek Paudel +2
Long-context inference is constrained by KV-cache memory, which grows linearly with sequence length; KV-cache compression therefore hinges on reliably selecting which past tokens t…