Interpretability & Mechanistic Interp

Audio embeddings capture physical damping properties far better than single visual frames, and this gap is partially bridgeable through audio-to-vision distillation.

Neural networks preferentially learn low-frequency sinusoidal patterns due to the inherent graded structure of their gradient descent dynamics, explained by an orthogonal polynomial framework.

Concept interventions can actively worsen model predictions, and existing "benign leakage" criteria fail to prevent this, necessitating new training objectives.

Specialized experts in MoE LLMs, not dense model neurons, are the key to interpretable and controllable personalization.

Prioritizing upstream causal drivers over downstream effects, Causal Integrated Gradients accurately attributes model predictions along known causal pathways at scale.

LLM reasoning failures are often misdiagnosed by standard probes, with even specialized probes failing to pinpoint the exact faulty step more reliably than trace length.

A single forward pass now reveals which input variables matter for PFN predictions, achieving exact FDR control and outperforming lasso, BART, and other methods on sparse nonlinear regression.

SAE features are more compositional than random projections, but pairwise interactions are still essential for accurate behavioral steering.

Language model states are not static points but possess dynamic "native reference frames" that can be approximated to unlock near-perfect interpretability and steerability.

Visual generation supervision injects significant, yet often inaccessible, knowledge into UMMs, requiring novel alignment strategies to unlock its full potential for text-based reasoning.

Humanoid robot control policies can be generated directly from their neural weights using diffusion models, unlocking new avenues for policy synthesis and understanding.

A single reward for multiple retrieval actions is a bottleneck; CASI unlocks precise within-set credit assignment, boosting agent performance by 3.51% in production.

Actively repelling uncertain features during representation learning slashes extreme segmentation errors in ambiguous anatomical boundaries by 22x, even without sacrificing overall accuracy.

For star-free languages, transformers learn best when attention weights lag behind output layer updates, defying intuitive feature learning theories.

LLMs can learn to manipulate their own internal activations, but this control is limited and often mimicked by external generation.

Foundation models trained on synthetic order flow perform amortized Bayesian inference, decoding latent market regimes with surprising accuracy and outperforming traditional methods for simulator calibration.

Globally optimized Boolean rule sets are now achievable with explicit control over accuracy-sparsity trade-offs, thanks to a novel MILP formulation that drastically cuts down on integer variables.

Visualize KANs like never before: directly manipulate B-spline control points and see gradient descent rewire activation functions in real-time.

SAEs can achieve near-optimal reconstruction with orders of magnitude less data than typically used, but recovering specific, reproducible features demands significantly more.

Language models encode task information in hidden states *before* their unembedding matrix can express it, suggesting current developmental timelines are misleading.

Sparse autoencoders unlock a shared, interpretable coordinate system for matching symbols across diverse AI systems, outperforming dense baselines by up to 45 points.

Conditional flow models frequently hallucinate non-additive scientific interactions, even when overall prediction accuracy appears high.

Transformer weight-space learning is now invariant to the full, rich symmetry group of attention heads and token embeddings.

Prompt adaptation methods don't just change what LLMs say, they fundamentally rewire *how* they compute, with distinct mechanisms for text optimization, prompt tuning, and prefix tuning.

Explanations from Natural Language Autoencoders can identify their target activation but fail to discriminate it from plausible rivals, suggesting current training paradigms may not yield robust oversight tools.

A grid-based world model can achieve 89% out-of-view object recall and outperform a Kalman tracker in view, but a node-based approach offers drastically superior memory efficiency and robustness to unmodeled velocities.

Pruning LLMs while preserving their influence functions is now over 28x faster and more effective, unlocking better data selection for downstream tasks.

A simple post-hoc geometric calibration method recovers lost out-of-domain capabilities and boosts in-domain performance after SFT, even on large, diverse models.

Weak interactive feedback can dynamically steer LLMs to the correct similarity criterion for test-time decisions, unlocking significant performance gains beyond static mixtures.

Sparse autoencoders recover known factors 80% better by training in the data's generative space, not its scaled readout space.

LLM judges can be recalibrated to align with human preferences by probing their sensitivity to evaluative biases, even without explicit rubric criteria.

Adam's implicit bias offers a practical defense against training data reconstruction attacks, unlike SGD and Muon which leave reconstructible fingerprints.

Multilingual LMs encode a universal color-language geometry, but not a universal color-perception geometry, with perceptual grounding fading in later layers.

LLM decoder states exhibit distinct informational and geometric compartments, enabling principled layer selection for speculative decoding that surpasses heuristic approaches.

MLLMs possess an intrinsic "S-Space" that acts as a spatial workspace, encoding object coordinates and enabling viewpoint transformations, even under non-spatial queries.

Source-side training dynamics, not just current values or training time, prospectively predict OOD degradation, even across model architectures.

Standard Shapley values are brittle; interval-valued Shapley values reveal their true robustness landscape in tree models.

A score-based method accelerates cluster DAG learning from interventions by two orders of magnitude, matching state-of-the-art edge recovery even on dense graphs.

Unifying factual support, counterfactual sensitivity, and exemplar tolerance reveals how GNNs truly reason about molecular properties, not just predict them.

Interpretable archetypes emerge from discrete data using a principled likelihood framework, unlocking insights in genomics and microbiome analysis previously inaccessible to standard AA.

Dynamic critic pessimism, guided by geometric disagreement, unlocks superior locomotion learning and efficiency in off-policy actor-critic methods.

Spectral analysis reveals that increasing latent dimensions in Koopman autoencoders improves dynamics learning by concentrating learned eigenvalues in low-residual regions, not just by reducing one-step prediction error.

Probes can now detect subtle, unverbalized LLM deception with near-perfect accuracy, even when the model's true intentions are hidden from external observation.

LLMs can be steered to reliably interpret complex genomic variants by grounding their reasoning in deterministic biological computations and evidence verification, avoiding hallucinated TF binding changes and fabricated experimental support.

Neural networks can learn interpretable, polytope-based latent representations that preserve performance and enable direct VQ training.

LLMs can attribute responsibility and blame, but their reasoning is incomplete and varies with model scale, with specific attribution dimensions demonstrably encoded in their latent spaces.

A 10x increase in AI time horizon is significantly easier for AI development in the 2-30 minute task range than for tasks outside this sweet spot.

Action chunking unlocks temporally interpretable decision trees that match neural network performance with up to 80% fewer parameters.

Most recalibration methods fail to guarantee calibration for critical outcomes, but this new approach ensures predictions are trustworthy even when focusing on rare or extreme events.

Most gradient-based methods fail to reliably attribute learned behaviors in online RL, with simple fluency metrics often proving more predictive than complex attribution techniques.