1 citations · 1 across the 2 of their papers we have counts for
13 papers
Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets
Duc Duong, Hoang Anh Duy Le, Jianwen Xie +2
Long-context and agentic LLM workloads push the KV cache past any fixed memory budget, forcing the inference stack to permanently evict tokens at every step of a continuous-inferen…
Wisdom of Committee: Diverse Distillation from Large Foundation Models and Domain Experts
Zichang Liu, Qingyun Liu, Yuening Li +6
Knowledge distillation from foundation models to compact domain models is challenging due to substantial gaps in capacity, architecture, and modality. For example, in our experimen…
Superintelligent Retrieval Agent: The Next Frontier of Agentic Retrieval
Zeyu Yang, Qi Ma, Jason Chen +1
Retrieval-augmented agents are increasingly the interface to large knowledge bases, yet most treat retrieval as a black box: they issue exploratory queries, inspect snippets, and r…
Inference Time Context Sparsity: Illusion or Opportunity?
Sahil Joshi, Prithvi Dixit, Agniva Chowdhury +5
Sparsity has long been a central theme in LLM efficiency, but its role in context processing remains unresolved. As LLM workloads shift toward longer contexts and agentic interacti…
SOCKET: SOft Collision Kernel EsTimator for Sparse Attention
Sahil Joshi, Agniva Chowdhury, Wyatt Bellinger +5
Exploiting sparsity during long-context inference is key to scaling large language models, as attention dominates the cost of autoregressive decoding. Sparse attention reduces this…
Scout Before You Attend: Sketch-and-Walk Sparse Attention for Efficient LLM Inference
Hoang Anh Duy Le, Sahil Joshi, Zeyu Yang +2
Self-attention dominates the computational and memory cost of long-context LLM inference across both prefill and decode phases. To address this challenge, we introduce Sketch&Walk…