How LoRA Remembers? A Parametric Memory Law for LLM Finetuning
Paper • 2605.30260 • Published • 41
dooho lee
BlueYellowGreen
AI & ML interests
None yet
Recent Activity
upvoted a paper 4 days ago
How LoRA Remembers? A Parametric Memory Law for LLM FinetuningOrganizations
None yet
upvoted 6
papers 4 days ago
CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation
Paper • 2605.25378 • Published • 61
Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments
Paper • 2605.30280 • Published • 137
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Paper • 2605.29801 • Published • 142
SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer
Paper • 2605.30409 • Published • 36
Representation Forcing for Bottleneck-Free Unified Multimodal Models
Paper • 2605.31604 • Published • 57
upvoted a paper 8 days ago
upvoted 2
papers 9 days ago
upvoted 6
papers 10 days ago
π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
Paper • 2605.14678 • Published • 104
DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards
Paper • 2605.21467 • Published • 204
StepAudio 2.5 Technical Report
Paper • 2605.23463 • Published • 49
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
Paper • 2605.21573 • Published • 108
Rethinking Cross-Layer Information Routing in Diffusion Transformers
Paper • 2605.20708 • Published • 109
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Paper • 2605.23904 • Published • 221
upvoted 2
papers 14 days ago
upvoted an article 14 days ago
Article
Training-Free Reasoning at 88.89% on GPQA Diamond: How Darwin Family Hit Frontier Scores Without a Single Gradient Step
FINAL-Bench
• • 18 upvoted 2
papers 15 days ago