TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration
Paper • 2604.14116 • Published • 9
Urro PRO
urroxyz
AI & ML interests
computational linguistics major 🤖🔎ðŸ”
i am autistic. if i come off rude, i probably didn't mean to. please feel free to ask me for clarification.
Recent Activity
upvoted a paper about 6 hours ago
TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration upvoted a paper about 6 hours ago
TIP: Token Importance in On-Policy Distillation upvoted a paper about 6 hours ago
Exploration and Exploitation Errors Are Measurable for Language Model AgentsOrganizations
upvoted 5
papers about 6 hours ago
TIP: Token Importance in On-Policy Distillation
Paper • 2604.14084 • Published • 10
Exploration and Exploitation Errors Are Measurable for Language Model Agents
Paper • 2604.13151 • Published • 21
From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space
Paper • 2604.14142 • Published • 23
Target Policy Optimization
Paper • 2604.06159 • Published • 19
upvoted a collection about 8 hours ago
upvoted 14
papers 1 day ago
Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
Paper • 2601.18734 • Published • 5
Towards Active Synthetic Data Generation for Finetuning Language Models
Paper • 2512.00884 • Published • 1
Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities
Paper • 2501.12147 • Published • 1
Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation
Paper • 2402.18191 • Published • 1
SCAR: Efficient Instruction-Tuning for Large Language Models via Style Consistency-Aware Response Ranking
Paper • 2406.10882 • Published • 2
LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning
Paper • 2505.07437 • Published • 1
The Best Instruction-Tuning Data are Those That Fit
Paper • 2502.04194 • Published • 2
BARE: Combining Base and Instruction-Tuned Language Models for Better Synthetic Data Generation
Paper • 2502.01697 • Published • 1
Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models
Paper • 2402.13064 • Published • 51
Beyond Random Sampling: Efficient Language Model Pretraining via Curriculum Learning
Paper • 2506.11300 • Published • 2
DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining
Paper • 2305.10429 • Published • 5
Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness
Paper • 2604.12373 • Published • 7
Accelerating Speculative Decoding with Block Diffusion Draft Trees
Paper • 2604.12989 • Published • 5
BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation
Paper • 2604.09497 • Published • 26