Showing 2026Show all
3 papers · 1 filter
cs.LG2026
Not All Ranks Are Equal: Budget-Aware LoRA Merging Across Tasks
Avinash Amballa, Yashas Malur Saidutta, Wenbo Li +2
Merging low-rank adapters (LoRAs) promises to eliminate the overhead of swapping task-specific weights at inference time. However, existing merging methods assume every layer needs…
cs.CL2026
Latent Personal Memory: Represent personal memory as dynamic soft prompts
Debrup Das, Avinash Amballa, Yashas Malur Saidutta +3
Personalizing large language models (LLMs) requires encoding long-term, user-specific behavioral patterns in a way that is computationally efficient, scalable, and compatible with…
cs.CL2026
Doc-to-Atom: Learning to Compile and Compose Memory Atoms
Xingjian Diao, Wenbo Li, Yashas Malur Saidutta +3
Long input sequences are central to document understanding and multi-step reasoning in Large Language Models, yet the quadratic cost of attention makes inference both memory-intens…