mHC: A Manifold-Constrained Framework to Stabilize and Scale Hyper-Connections in Neural Networks
Recently, studies exemplified by Hyper-Connections (HC) have extended the ubiquitous residual connection paradigm established over the past decade by expanding the residual stream width and…
Read the full articleYou might also wanna read
Long-Context Fine-Tuning with Limited VRAM
arXiv:2607.15105v1 Announce Type: new Abstract: Parameter-efficient fine-tuning reduces model and optimizer memory, but dense attention stil
Semantic-Based Distributed Learning for Diverse and Discriminative Representations
In large-scale distributed scenarios, increasingly complex tasks demand more intelligent collaboration across networks, requiring the joint
New preprint:
New preprint: Random network structure stabilizes neural manifolds We’re excited to share our new work on representational drift. doi.org/10
A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design
arXiv:2607.09084v1 Announce Type: new Abstract: The rapid expansion of large-scale AI models has led to significant performance breakthrough
Efficient Hyperparameter Optimization for Autonomous Driving Models with AMD Instinct GPU Partitioning
For automotive OEMs and Tier-1 suppliers, developing production-grade perception models presents a significant bottleneck: achieving the acc
Unlocking the Manifold: How IGL Redefines Learning in AI
Intrinsic Green's Learning offers a breakthrough by modeling functions on manifolds with linear PDEs. This approach promises efficiency and
Comments
Sign in to join the conversation.
No comments yet. Be the first.