🧠 AI - dungngo · Scour

Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning

🧠Neural Architecture Academic

Not Just After One: Sleep-Inspired Replay Prevents Catastrophic Forgetting After Sequential Tasks

⚡Zig Academic

Bridging the Morphology Gap: Adapting VLA Models to Dexterous Manipulation via Intent-Conditioned Fine-Tuning

🤖Robotics Academic

Preserving Plasticity in Continual Learning via Dynamical Isometry

🧠Neural Architecture Academic

The Fine-Tuning Trap: Evaluating Negative Transfer and the Role of PEFT in Sub-1B Mathematical Reasoning

🧠Neural Architecture Academic

HydraCIL: Decoupled Class-Incremental Learning through Prototype-Guided Multi-Head Classifiers

📱Edge AI Academic

Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments

📱Edge AI Academic

Continual Quadruped Robots Coordination via Semantic Skill Discovery

🤖Robotics Academic

LargeMonitor: Monitoring Online Task-Free Continual Learning via Large Pretrained Models

🧠Neural Architecture Academic

FOGO: Forgetting-aware Orthogonalization Optimizer

🧠Neural Architecture Academic

Two to Tango: Coupled Task-Reference Selection for Safe LLM Fine-tuning

⚙️LLVM Academic

PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation

🤖Robotics Academic

Bidirectional Semantic Complementary Tool Retrieval for Remote Sensing Agents

📊Embeddings Academic

No more posts from dungngo's subscribed feeds.

Scour all 25258 feeds Learn more about Feeds

Log in to enable infinite scrolling