arXiv Machine Learning
Jul 3
Certified World Models: Predictability Across Configuration, Horizon, and Resolution
arXiv:2606. 13092v3 Announce Type: replace Abstract: Scale buys interpolation; structure buys certifiable transfer.
Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability
arXiv:2608. 10172v1 Announce Type: new Abstract: Mechanistic interpretability explains models by identifying circuits inside them, but has no way to tell whether a circuit is a property of the model or an artifact of the method that found it.
Related stories
arXiv AI
Jul 1
Why Do Few-Step Text Latents Fail When Image Latents Work? Non-Commitment at Sharp Categorical Readouts
arXiv:2606. 30705v1 Announce Type: cross Abstract: Deterministic few-step generation succeeds on continuous image latents but collapses to incoherent text on continuous text latents, and we show the cause is geometric rather than a training or scaling deficiency: a smooth, regularity-limited deterministic map cannot resolve a discrete branch choice before a sharp categorical readout, so few-step failure is governed by decoder sharpness, not transport accuracy.
arXiv Machine Learning
Jun 8
Predictable Compression Failures: Order Sensitivity and Information Budgeting for Evidence-Grounded Binary Adjudication
arXiv:2509. 11208v3 Announce Type: replace-cross Abstract: Transformers used for evidence-grounded binary adjudication (e.
arXiv Machine Learning
Jul 15
Constructed Reality, Contested Priors: Decoupling and the Architecture of Cognitive Relapse Under the Free Energy Principle
arXiv:2607. 11958v1 Announce Type: new Abstract: Under the free energy principle, a predictive system does not observe reality directly; it maintains a generative model of the world and experiences that model's best current hypothesis.
Hugging Face Trending Papers
3d ago
Fiber Fingerprints of Hidden Learning-State Dynamics
A learning system can occupy execution states that are indistinguishable under every declared present-behavior readout yet respond differently to future training. We formalize this through fiber fingerprints: controlled future-learning response laws restricted to present-behavior equivalence classes.
arXiv AI
Jul 14
When Does Depth Survive Composition? Compute--Quality Regimes in Latent World Models
arXiv:2607. 10203v1 Announce Type: cross Abstract: Adaptive-compute world models -- early-exit or mixture-of-depths predictors that spend variable depth per step -- assume depth buys better predictions and can be routed adaptively.
arXiv Machine Learning
1d ago
Fiber Fingerprints of Hidden Learning-State Dynamics
arXiv:2608. 15976v1 Announce Type: new Abstract: A learning system can occupy execution states that are indistinguishable under every declared present-behavior readout yet respond differently to future training.
arXiv Machine Learning
Jul 9
Fingerprint, Not Blueprint: How Positional Schemes Set the Default Spectral Algebra of Attention
arXiv:2607. 06621v1 Announce Type: new Abstract: The pre-softmax score of an attention head is a bilinear form $score(i,j) = x_i^T M x_j$ in a learned operator $M = W_q^T W_k$.
arXiv AI
Jul 15
Adaptive Compute in Latent World Models: When Depth Helps, Hurts, or Doesn't Matter
arXiv:2607. 10203v2 Announce Type: replace-cross Abstract: Adaptive-compute world models -- early-exit or mixture-of-depths predictors that spend variable depth per step -- assume depth buys better predictions and can be routed adaptively.
arXiv AI
Jul 15
Sensitivity to Subjective Expected Utility Maximization: A Methodological Study, with an Illustrative Application to LLM Decision-Making
arXiv:2607. 11920v1 Announce Type: cross Abstract: Evaluating decisions made under uncertainty is hard when labeled outcomes are scarce, costly, or confounded with luck.
arXiv Machine Learning
Jul 28
Beyond ICA: Identifiability by Symmetry Breaking
arXiv:2607. 23182v1 Announce Type: cross Abstract: We prove the identifiability of deep generative models (DGMs) with piecewise-affine (PWA) decoders and Gaussian mixture model (GMM) priors, in a purely unsupervised setting.
arXiv Machine Learning
Aug 10
PRISM: Principled Reference Identification for Schrodinger Bridge Model
arXiv:2608. 06893v1 Announce Type: new Abstract: Schr\"odinger bridge models restore a clean signal from a degraded observation by following the conditional bridges of a reference process, yet this reference is chosen heuristically, typically white noise with a hand-tuned schedule.