Agentic Learner with Grow-and-Refine Multimodal Semantic Memory
Paper • 2511.21678 • Published • 13
specimba PRO
specimba
AI & ML interests
None yet
Recent Activity
liked a model 1 day ago
mradermacher/Neona-12B-i1-GGUF liked a model 1 day ago
tensorblock/kyx0r_Neona-12B-GGUF liked a model 1 day ago
mradermacher/Neona-12B-GGUFOrganizations
upvoted 14
papers 4 days ago
The perpetual motion machine of AI-generated data and the distraction of ChatGPT-as-scientist
Paper • 2312.00818 • Published • 1
More Context, Less Distraction: Visual Classification by Inferring and Conditioning on Contextual Attributes
Paper • 2308.01313 • Published • 10
Reducing Distraction in Long-Context Language Models by Focused Learning
Paper • 2411.05928 • Published • 1
CraniMem: Cranial Inspired Gated and Bounded Memory for Agentic Systems
Paper • 2603.15642 • Published • 2
EMBER: Autonomous Cognitive Behaviour from Learned Spiking Neural Network Dynamics in a Hybrid LLM Architecture
Paper • 2604.12167 • Published • 1
Human-Like Lifelong Memory: A Neuroscience-Grounded Architecture for Infinite Interaction
Paper • 2603.29023 • Published • 1
D-MEM: Dopamine-Gated Agentic Memory via Reward Prediction Error Routing
Paper • 2603.14597 • Published • 1
The Missing Knowledge Layer in Cognitive Architectures for AI Agents
Paper • 2604.11364 • Published • 1
MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents
Paper • 2604.04853 • Published • 1
SuperLocalMemory V3: Information-Geometric Foundations for Zero-LLM Enterprise Agent Memory
Paper • 2603.14588 • Published • 3
SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems
Paper • 2604.04514 • Published • 6
DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data
Paper • 2604.19859 • Published • 51
Sapiens2
Paper • 2604.21681 • Published • 18
upvoted 4
papers 5 days ago
GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
Paper • 2604.26752 • Published • 93
ClawGym: A Scalable Framework for Building Effective Claw Agents
Paper • 2604.26904 • Published • 47
Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding
Paper • 2604.26779 • Published • 12
BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs
Paper • 2504.18415 • Published • 52
upvoted an article 5 days ago
Article
The Pharmome Map: a comprehensive public dataset for drug-target interaction modeling
•
15
upvoted a paper 6 days ago