Test-Time Scaling Makes Overtraining Compute-Optimal
Paper • 2604.01411 • Published • 22
Urro PRO
urroxyz
AI & ML interests
computational linguistics major 🤖🔎🔠i am autistic. if i come off rude, i probably didn't mean to. please feel free to ask me for clarification.
Recent Activity
updated a collection about 4 hours ago
HUMAN-WRITTEN & LEGALLY-SOURCED* upvoted a paper about 6 hours ago
Test-Time Scaling Makes Overtraining Compute-Optimal upvoted a paper about 6 hours ago
Token Warping Helps MLLMs Look from Nearby ViewpointsOrganizations
upvoted 11
papers about 6 hours ago
Token Warping Helps MLLMs Look from Nearby Viewpoints
Paper • 2604.02870 • Published • 28
Self-Distilled RLVR
Paper • 2604.03128 • Published • 145
Less Detail, Better Answers: Degradation-Driven Prompting for VQA
Paper • 2604.04838 • Published • 11
Mimic Intent, Not Just Trajectories
Paper • 2602.08602 • Published • 10
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
Paper • 2604.04921 • Published • 90
Adam's Law: Textual Frequency Law on Large Language Models
Paper • 2604.02176 • Published • 161
REAM: Merging Improves Pruning of Experts in LLMs
Paper • 2604.04356 • Published • 3
DARE: Diffusion Large Language Models Alignment and Reinforcement Executor
Paper • 2604.04215 • Published • 18
In-Place Test-Time Training
Paper • 2604.06169 • Published • 18
MARS: Enabling Autoregressive Models Multi-Token Generation
Paper • 2604.07023 • Published • 21
upvoted a paper 5 days ago
upvoted 4
papers 6 days ago
COSMOS: Predictable and Cost-Effective Adaptation of LLMs
Paper • 2505.01449 • Published • 4
SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models
Paper • 2403.07384 • Published • 3
Less is More: Improving LLM Alignment via Preference Data Selection
Paper • 2502.14560 • Published • 1
What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning
Paper • 2312.15685 • Published • 17
upvoted 2
papers 7 days ago
upvoted 2
collections 8 days ago