arXiv Machine Learning
Aug 12
Iterative Erasure Count Is Not an Affine-Invariant Concept Dimension
arXiv:2608. 10566v1 Announce Type: cross Abstract: How many directions does a neural representation use to encode a concept?
Iterative Erasure Count Is Not an Affine-Invariant Concept Dimension
How many directions does a neural representation use to encode a concept? A common answer repeatedly erases probe directions and reports the stopping count or cumulative removed rank.
Related stories
arXiv AI
Aug 13
Low-Interaction-Rank Learning: Unifying Multiplicative Dual-Encoder Heads
arXiv:2608. 11661v1 Announce Type: cross Abstract: A multiplicative dual-encoder network computes a real-valued output for a pair of inputs as the inner product of their separate encodings.
arXiv Machine Learning
Sep 14
The Rank the Task Demands: A Causal Rank Law for Matrix Memories Trained on Group Composition
arXiv:2609. 12259v1 Announce Type: new Abstract: Matrix-valued memories make rank the natural budget of a learned representation: the number of independent directions a state spans bounds what it can bind, compose, and track.
arXiv Machine Learning
Jul 8
Geometric Stability: The Missing Axis of Representations
arXiv:2601. 09173v5 Announce Type: replace Abstract: Representational similarity analysis and related methods compare the internal geometries of neural networks, but they measure only alignment between spaces, leaving a blind spot -- whether a representation's structure is reliably recoverable, not merely similar.
arXiv Machine Learning
Jun 5
Dead Directions: Geometric Singular Learning
arXiv:2606. 05957v1 Announce Type: new Abstract: Singular learning theory and information geometry have studied the same parameter spaces in mostly separate vocabularies: the former computes Bayesian invariants in resolved coordinates, the latter works in original coordinates under a non-degeneracy assumption that overparameterised models routinely violate.
arXiv AI
Jul 9
The Rank-One Corner: How Much Value Equivalence Does a Task Need from a World Model?
arXiv:2607. 06640v1 Announce Type: cross Abstract: A learned world model is usually judged by how faithfully it reconstructs its observations or predicts reward, as though quality were something the model simply has or lacks.
arXiv Computer Vision
Sep 2
Teaching Vision-Language Models to Use the Scale They Are Given: Label-Free Equivariance Training for Metric Physical Reasoning
The paper introduces EquiSD, a label‑free training method that exploits scale equivariance to improve metric grounding in vision‑language models. By projecting model predictions onto a scale‑equivariant family and fine‑tuning on the resulting targets, EquiSD boosts a 3B model’s median response slope from 0.66 to 0.94 and raises mean relative accuracy by 9.2 points across simulated scales, with positive transfer to real QuantiPhy videos.
Hugging Face Trending Papers
Sep 23
Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces
Methods operating on Vision Transformer (ViT) feature spaces typically rely on Euclidean distance or cosine similarity. This assumes that every direction is equally meaningful, but there is no reason...
arXiv Machine Learning
Sep 24
Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces
arXiv:2609.27988v1 Announce Type: cross Abstract: Methods operating on Vision Transformer (ViT) feature spaces typically rely on Euclidean distance or cosine similarity. This assumes that every direc...
Hugging Face Trending Papers
Sep 1
Teaching Vision-Language Models to Use the Scale They Are Given: Label-Free Equivariance Training for Metric Physical Reasoning
Metric questions about video require vision-language models to use supplied real-world references to convert visual measurements into physical units. Yet we find that current models use this scale inf...
arXiv Computer Vision
3d ago
PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos
arXiv:2609.38377v1 Announce Type: new Abstract: Evaluating the physical consistency of generated videos remains a fundamental challenge. Existing approaches rely on off-the-shelf vision-language mode...
arXiv Machine Learning
Sep 23
Intrinsic Interaction Geometry Controls the Low-Rank Complexity of Softmax Attention
arXiv:2608.28150v2 Announce Type: replace Abstract: How much matrix rank is required to preserve every bounded value output of normalized softmax attention? We study the unrestricted maximum-row-\(\e...