LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs
Paper • 2606.06286 • Published • 7
Urro
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
View all activity
Organizations
upvoted 7
papers 1 day ago
Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction
Paper • 2606.05769 • Published • 5
OPRD: On-Policy Representation Distillation
Paper • 2606.06021 • Published • 6
Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents
Paper • 2605.30159 • Published • 6
MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery
Paper • 2606.06473 • Published • 4
Towards Truly Multilingual ASR: Generalizing Code-Switching ASR to Unseen Language Pairs
Paper • 2606.05846 • Published • 3
Latent Reasoning with Normalizing Flows
Paper • 2606.06447 • Published • 5
upvoted 3
papers 2 days ago
STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations
Paper • 2606.05165 • Published • 3
Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning
Paper • 2606.04923 • Published • 37
Audio Interaction Model
Paper • 2606.05121 • Published • 101
upvoted 10
papers 3 days ago
Self-Distilled Policy Gradient
Paper • 2606.04036 • Published • 20
MemTrain: Self-Supervised Context Memory Training
Paper • 2606.03197 • Published • 16
Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling
Paper • 2606.03102 • Published • 13
Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training Traces
Paper • 2605.29288 • Published • 9
Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging
Paper • 2606.01717 • Published • 20
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
Paper • 2606.03979 • Published • 24
World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning
Paper • 2606.03603 • Published • 29
KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks
Paper • 2606.03458 • Published • 52
From Activation to Causality: Discovery of Causal Visual Representations in the Human Brain
Paper • 2605.23895 • Published • 51
TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL
Paper • 2606.01599 • Published • 17