Search the full wire by company, model, lab, or keyword. Every story we have ever aggregated.
Topo² framework: persistent-homology measurement separating memorization from generalization as causally independent geometric channels in noisy-label learning.
Code-CoT introduces credit-addressable reasoning for multimodal geometry: assigns learning credit at semantic unit level rather than trajectory-level to improve VLM deduction.
Comprehensive survey of neural network optimizers in 2025–2026 covering temporal estimation, geometry, scheduling, and distributed systems.
Video diffusion models repurposed for joint geometry learning (depth, surface normals) without task-specific fine-tuning overhead.
PCMI and WACS metrics enable reference-free forced alignment evaluation for speech using self-supervised representations, supporting multilingual analysis.
NL2AGBench evaluates LLM auto-formalization of natural-language geometry problems into AlphaGeometry's domain-specific language for theorem proving.
Tool-use hallucination in agentic extraction bypasses fidelity metrics; per-dispatch instrumentation needed to catch silent failures in structured output.
Study showing Vision Transformer attention heads in multimodal LLMs specialize into object/background roles; SHS-Index metric correlates specialization with downstream performance.
Quantum federated learning framework using Bures metric geometry for mixed-state noisy quantum devices.
TTPO enables test-time policy optimization for math reasoning using asymmetric rollout analysis without ground-truth labels.
Static scanners are increasingly used to identify executable or otherwise unsafe content in machine- learning artifacts, yet conventional evaluation metrics characterize only cases where a scanner yields a usable security judgment. We evaluate ModelScan, ModelAudit, and…
LeVJEPA: first video encoder using LeJEPA collapse-free objective without architectural asymmetries, achieving efficient self-supervised pretraining.
Information floor metric separates model gap from missing context in block drafting; tests four open-weights and frontier API models.
BTS-AgentBench pipelines industrial telemetry logs into deterministic multi-turn agent tasks with 532 episodes.
Importance-scoring metric applied to Transformer attention heads for tabular data, demonstrating head-drop robustness across 40 datasets.
TraceML dataset captures 4,465 human Kaggle trajectories paired with agent traces to expose gaps in autonomous ML development beyond outcome-based metrics.
Intent-divergence gating layer prevents autonomous vehicle planning failures by detecting misalignment between language-guided intent and planned geometry before commitment.
AsymSpec: asymmetric speculative decoding for agentic LLMs that compresses verifier context while drafting on full input to reduce inference latency.
Spectral analysis detects AI-generated text by capturing signal fluctuations absent in confidence-based metrics, offering training-free scalability.
Trajectory-based framework measures game-theoretic interaction structures (simultaneous, sequential, asymmetric) in real-world vehicle dynamics.
Kolmogorov-Arnold Networks with learned edge geometry via Banach duality replaces fixed basis functions with adaptive parametrization.
FID and KID metrics hide distributional differences in generative models; visually invalid images achieve low FID scores by matching only first-two moments of reference distribution.
Geometric framework analyzes robustness of neighborhood-based fairness audits under adversarial perturbations.
FactoMap models disentangled representations with factor-space structure (domains, identifications, anisotropy) beyond Euclidean product assumptions.
Parameter-level symmetry attribution via functional sensitivity analysis determines if learned network symmetries lift to parameter space.
Data leakage in power outage prediction models inflates generalization metrics; identifies spatial, temporal, and event-based evaluation gaps.
Safety-direction penalty training mitigates reasoning-induced misalignment where chain-of-thought fine-tuning triggers harmful LLM behaviors through representation-space geometry.
ML framework for inverse design of 19x23 pixelated millimetre-wave patch antennas in 22-30 GHz band using CST simulations.
Empirical evaluation of diversity-based active learning metric spaces (K-center, K-median) for cost-effective classifier training with minimal labeled data.
Influence functions adapted for label-free data attribution and error detection in ESA's Ariel space mission spectroscopy pipelines without ground truth.