Core Space Mixture
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging
arXiv:2603.00573v2 Announce Type: replace Abstract: Large language models (LLMs) achieve remarkable performance on diverse downstream and domain-specific tasks via parameter-efficient fine-tuning (PEFT). However, existing PEFT methods, particularly MoE-LoRA architectures, suffer from limited parameter efficiency and coarse-grained adaptation due to the proliferation of LoRA experts and instance-level routing. To address these issues, we propose Core Space Mixture of LoRA (\textbf{CoMoL}), a...
Folded Transport MCMC: Certifiable Quotient Posterior Computation for Symmetric Bayesian Models
arXiv:2606.04307v1 Announce Type: new Abstract: Bayesian models with finite symmetry - mixture models with exchangeable components, structural identification with closely-spaced modes - define posteriors that are invariant under a group of label permutations, creating redundant multimodality that degrades MCMC convergence diagnostics. We introduce Folded Transport MCMC (FolT-MCMC), which performs inference directly on the quotient posterior by constructing an independence sampler on the...
Sinkhorn Normalization of Diffusion Kernels
arXiv:2507.06161v2 Announce Type: replace Abstract: Smoothing a signal based on local neighborhoods is a core operation in machine learning and geometry processing. On well-structured domains such as vector spaces and manifolds, the Laplace operator derived from differential geometry offers a principled approach to smoothing via heat diffusion, with strong theoretical guarantees. However, constructing such Laplacians requires a carefully defined domain structure, which is not always available.
Human-Like Neural Nets by Catapulting
Human-like Neural Nets by Catapulting Speculative proposal to create artificial neural nets with human-like performance by high-learning-rate/regularization training of overparameterized NNs to trigger catapulting/grokking. Over-parameterization as a route to true generalization would resolve many outstanding mysteries of artificial versus natural intelligence. There are many mysteries about deep learning and human intelligence, but we could describe the biggest anomaly this way: why are...
Light-induced quantum friction of carbon nanotubes in water
Abstract Friction slows down moving objects at both macroscopic and microscopic scales1. At the electronic level, quantum friction describes direct transfer of momentum between a liquid and the electrons of a solid2. Owing to its microscopic nature, this phenomenon remains experimentally challenging to capture3.
Shantell Sans
The Story of Shantell Sans Shantell Sans mixes variable axes for Weight, Italic, Informality, and Bounce to deliver a wide array of font styles, from friendly, readable, everyday typographic workhorses to striking, high-energy, experimental styles meant especially for animation. This is the story behind its inspiration and creation. Shantell Martin, Artist One of my first relationships with words was back in elementary school.
A 10 year old Xeon is all you need (for 26B-A4B MTP Drafters without GPU)
A 10 year old Xeon is all you need 17 minutes read The previous post covered getting Gemma 4’s MTP drafters quantized and paired with a verifier. This one is about running the result on a machine that has no business running it. I have a recycled server.
Future Power Rankings: How all 68 Power 4 college football teams stack up
Projecting a college football program's future is harder than ever. Rosters and fortunes change dramatically and championship pathways are more open than ever. The assets that make a program great in 2026 might not be there in 2027.
The iPhone's Last Stand
Listen to this post: Apple fans would, for years and years, sneer at Microsoft’s penchant for talking about products that may or may not ship, deriding them as vaporware. After Apple’s bungled 2024 launch of Apple Intelligence and new Siri, however, vaporware is fair game, and just in time for this Article. Project Solara Last week, at its annual Build developer conference, Microsoft put forth a vision for a new ecosystem of hardware devices under the banner of Project Solara: The concept —...