δ-mem: Efficient Online Memory for Large Language Models
Paper • 2605.12357 • Published • 120
Joel Wang
joelhenwang
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
δ-mem: Efficient Online Memory for Large Language Models upvoted a paper 3 days ago
Process Rewards with Learned Reliability upvoted a paper 3 days ago
Co-Evolving Policy DistillationOrganizations
upvoted 20
papers 3 days ago
Process Rewards with Learned Reliability
Paper • 2605.15529 • Published • 51
Co-Evolving Policy Distillation
Paper • 2604.27083 • Published • 65
Self-Distilled Agentic Reinforcement Learning
Paper • 2605.15155 • Published • 108
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
Paper • 2605.11609 • Published • 189
Learning to Discover at Test Time
Paper • 2601.16175 • Published • 45
Reinforcement Learning via Self-Distillation
Paper • 2601.20802 • Published • 47
Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting
Paper • 2601.02151 • Published • 115
Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs
Paper • 2601.08763 • Published • 150
Improving Data and Reward Design for Scientific Reasoning in Large Language Models
Paper • 2602.08321 • Published • 44
SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
Paper • 2602.13515 • Published • 45
Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning
Paper • 2602.01058 • Published • 45
Length-Unbiased Sequence Policy Optimization: Revealing and Controlling Response Length Variation in RLVR
Paper • 2602.05261 • Published • 53
BitDance: Scaling Autoregressive Generative Models with Binary Tokens
Paper • 2602.14041 • Published • 54
HyTRec: A Hybrid Temporal-Aware Attention Architecture for Long Behavior Sequential Recommendation
Paper • 2602.18283 • Published • 57
SLA2: Sparse-Linear Attention with Learnable Routing and QAT
Paper • 2602.12675 • Published • 59
Experiential Reinforcement Learning
Paper • 2602.13949 • Published • 75
F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare
Paper • 2602.06717 • Published • 75
Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models
Paper • 2602.12036 • Published • 94
Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text
Paper • 2601.22975 • Published • 112