Not All Ranks Are Equal: Budget-Aware LoRA Merging Across Tasks
Paper • 2609.22237 • Published • 7
Avinash Amballa
AvinashAmballa
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
Not All Ranks Are Equal: Budget-Aware LoRA Merging Across Tasks commentedon a paper 28 days ago
Quasi-random Multi-Sample Inference for Large Language Models commentedon a paper 28 days ago
LS-GAN: Human Motion Synthesis with Latent-space GANsOrganizations
None yet
upvoted a paper 1 day ago
commented 4
papers 28 days ago
Quasi-random Multi-Sample Inference for Large Language Models
Paper • 2411.06251 • Published • 1 •
1
LS-GAN: Human Motion Synthesis with Latent-space GANs
Paper • 2501.01449 • Published • 1 •
1
CoPE: A Lightweight Complex Positional Encoding
Paper • 2508.18308 • Published • 2 •
1
Latent Personal Memory: Represent personal memory as dynamic soft prompts
Paper • 2606.20911 • Published • 1 •
1
authored a
paper about 1 month ago
submitted a
paper to Daily Papers about 1 month ago
upvoted 6
papers about 2 months ago
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA
Paper • 2608.09819 • Published • 113
Stealing Reasoning Traces from Proprietary LLM APIs
Paper • 2608.09867 • Published • 120
SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring
Paper • 2608.09802 • Published • 74
LatentPress: Context Compression Beyond Text and Vision
Paper • 2609.01507 • Published • 27
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
Paper • 2609.01437 • Published • 88
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Paper • 2609.02749 • Published • 148
authored a
paper 2 months ago
upvoted a paper 2 months ago
upvoted an article 3 months ago
Article
What We Learned by Reproducing 2,200 papers from ICML
abidlabs
• • 120 upvoted a paper 5 months ago
upvoted an article 6 months ago
Article
🤗 PEFT welcomes new merging methods
smangrul, sayakpaul
• • 31 upvoted a paper 7 months ago
upvoted a paper 8 months ago