Rethinking Memory as Continuously Evolving Connectivity
Paper • 2605.28773 • Published • 27
Joel Wang
joelhenwang
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 days ago
Rethinking Memory as Continuously Evolving Connectivity liked a dataset 2 days ago
Zyphra/Zyda-2Organizations
upvoted a paper 2 days ago
liked a
dataset 2 days ago
upvoted 7
papers 2 days ago
DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning
Paper • 2605.25604 • Published • 132
HGRN2: Gated Linear RNNs with State Expansion
Paper • 2404.07904 • Published • 21
ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation
Paper • 2605.28293 • Published • 80
From Pixels to Words -- Towards Native One-Vision Models at Scale
Paper • 2605.28820 • Published • 68
MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems
Paper • 2605.28732 • Published • 37
Agent Explorative Policy Optimization for Multimodal Agentic Reasoning
Paper • 2605.28774 • Published • 79
JLT: Clean-Latent Prediction in Latent Diffusion Transformers
Paper • 2605.27102 • Published • 30
updated a
model 3 days ago
published a
model 3 days ago
upvoted 9
papers 3 days ago
Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models
Paper • 2605.26895 • Published • 17
Self-Improving Language Models with Bidirectional Evolutionary Search
Paper • 2605.28814 • Published • 54
Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling
Paper • 2604.27039 • Published • 25
Why Fine-Tuning Encourages Hallucinations and How to Fix It
Paper • 2604.15574 • Published • 25
AgriIR: A Scalable Framework for Domain-Specific Knowledge Retrieval
Paper • 2604.16353 • Published • 4
TIDE: Every Layer Knows the Token Beneath the Context
Paper • 2605.06216 • Published • 9
Long Context Pre-Training with Lighthouse Attention
Paper • 2605.06554 • Published • 31
GQLA: Group-Query Latent Attention for Hardware-Adaptive Large Language Model Decoding
Paper • 2605.15250 • Published • 13
EndPrompt: Efficient Long-Context Extension via Terminal Anchoring
Paper • 2605.14589 • Published • 17