arXiv AI July 28, 2026 By Tibor Sloboda

Sheaf-Laplacian Obstruction and Projection Hardness for Cross-Modal Compatibility on a Modality-Independent Site

arXiv:2604. 07632v2 Announce Type: replace-cross Abstract: Cross-modal representations vary in how easily they can be aligned, and compatibility is generally non-transitive: two modalities may align through an intermediate modality at lower complexity than through a direct map.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

multimodal

arXiv Machine Learning

Jun 5

The ASE-LSE Disagreement Landscape: An End-to-End Characterisation of Extremes and Structural Drivers

arXiv:2605. 22346v2 Announce Type: replace-cross Abstract: Two of the most widely used methods for analysing graph data, Adjacency Spectral Embedding and Laplacian Spectral Embedding, often produce different results when applied to the same graph.

By Minh Triet Pham, Ian Gallagher

rag

arXiv AI

Jul 22

Cross-Dialect Generalization Without Retraining: Benchmarks and Evaluation of Schema-Derived Constrained Decoding for MLIR

arXiv:2607. 18254v1 Announce Type: new Abstract: Multi-Level Intermediate Representation (MLIR) underlies modern ML compiler infrastructure (TensorFlow, JAX/StableHLO, PyTorch Inductor, IREE), yet appears only in trace amounts in code-LM pretraining corpora.

By Plawan Kumar Rath

fine-tuning benchmarks

arXiv Machine Learning

Sep 1

Converse and Collision-Based Achievability for Node Localization with Hybrid Distance-Spectral Graph Positional Encodings

arXiv:2608.30152v1 Announce Type: new Abstract: Graph positional encodings are widely used in graph neural networks and graph Transformers, yet it remains unclear when the code itself can identify no...

By Zimo Yan, Yifan Li, Hao Li, Zheng Xie, Chang Liu, Zheming Tu, Yuan Wang

llms efficiency

arXiv Machine Learning

Jul 9

Restricted Dynamic Geometric Complexity: Certificates for Structured Preconditioning

arXiv:2607. 07204v1 Announce Type: cross Abstract: Optimization geometrodynamics views optimizer state as evolving geometry.

By Zavier Li

benchmarks

arXiv Machine Learning

Jul 1

Fora: From Weight-Space to Function-Space Protection in Capability-Preserving Fine-Tuning

arXiv:2606. 31092v1 Announce Type: new Abstract: Full fine-tuning adapts large language models to new tasks but can erode capabilities they already possess.

By Rui Zhou, Tianci Xie

llms fine-tuning benchmarks

arXiv Machine Learning

Sep 23

Block-Level Weight-Space Structure Persists Under Post-Training: An Empirical Study Across LLM Families

arXiv:2609.26147v1 Announce Type: new Abstract: Modern LLMs are deployed as families of post-trained variants (base, instruct, chat, code) derived from a shared set of pre-trained weights. We present...

By Zhaohui Wang

llms benchmarks

One email a morning, machine-written

Related stories

The ASE-LSE Disagreement Landscape: An End-to-End Characterisation of Extremes and Structural Drivers

Cross-Dialect Generalization Without Retraining: Benchmarks and Evaluation of Schema-Derived Constrained Decoding for MLIR

Converse and Collision-Based Achievability for Node Localization with Hybrid Distance-Spectral Graph Positional Encodings

Restricted Dynamic Geometric Complexity: Certificates for Structured Preconditioning

Fora: From Weight-Space to Function-Space Protection in Capability-Preserving Fine-Tuning

Block-Level Weight-Space Structure Persists Under Post-Training: An Empirical Study Across LLM Families