8 citations · 21 across the 11 of their papers we have counts for
Showing 2026Show all
3 papers · 1 filter
cs.LG2026
PAGE: Partition-Aware Gated KV-Cache Eviction
Pankaj Kumar, Subhankar Mishra
KV-cache eviction can do more than compress. In long-context LLMs, keeping only some cached tokens sometimes matches or exceeds full-cache accuracy, because many redundant prefill…
cs.CL2026
Query-Side Attacks on GNN-Based KGQA: Tracing Failures from Entity Linking to Answer Generation
Pankaj Kumar, Subhankar Mishra
GNN-based Knowledge Graph Question Answering (KGQA) pipelines process queries through four discrete stages: entity linking, subgraph retrieval, GNN reasoning, and answer generation…
cs.AI2026
Attacking Graph Foundation Models Through Their Shared Representation
Pankaj Kumar, Subhankar Mishra
A graph foundation model generalizes across graph domains by mapping every input into one shared representation before any task reasoning. We call this map the alignment layer, the…