Showing cs.LGShow all
2 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.LG2025
CoPE: A Lightweight Complex Positional Encoding
Avinash Amballa
Recent studies have demonstrated the effectiveness of position encoding in transformer architectures. By incorporating positional information, this approach provides essential guid…