The Archive

DP-GRAMS recovers density modes under differential privacy constraints via noisy mean-shift on Hölder-class distributions, advancing theory without direct AI systems application.

SignMuon applies sign compression to Muon optimizer but exhibits theoretical convergence failures; explores limits of error feedback in matrix-aware optimization.

Freeze-then-select method decouples PDE discovery from neural optimization via structured field adapters and Stability-Validated Weak Selection for sparse observations.

GQ-FSL combines stochastic quantization with federated split learning to reduce energy consumption in edge DNN deployment on resource-constrained mobile devices.

FDD-ON ontology standardizes fault detection/diagnostics for HVAC systems, addressing interoperability and domain knowledge representation for building maintenance applications.

Iterated learning experiments show language compositionality emerges from frequency-structured meaning spaces under transmission bottlenecks.

Now a text prompt is all it takes to generate reality-warping images using Google Earth's satellite, aerial, and 3D imagery, like these images generated by Digital Digging's Henk van Ess that show "refugees near the Mexican border" and a bomb crater near a hospital in Gaza. Google responded to Digital Digging's AI-altered images, saying, "We take misinformation seriously - every image created with Nano Banana in Google Earth includes the SynthID digital watermark, so if someone is unsure about an image, they can ask the Gemini app or use Lens in Search to see if the image was AI-generated." I...

AgentHPOBench evaluates LLM agents on sequential hyperparameter optimization across 30 ML tasks, assessing experimental interpretation and adaptive decisions.

Proposes Socratic Test framework for automated, multimodal conversational assessment integrating dynamic assessment and Bloom's taxonomy.

CENDRe method extracts temporal and spectral concepts from CNN time-series models via joint frequency-domain analysis and improved localization.

Analyzes when on-policy interaction and value functions improve imitation learning over behavior cloning under representational constraints.

Introduces EPC score metric for evaluating XAI explanation fidelity by balancing feature sparsity and model performance preservation.

Snapchat has adjusted it recommendation systems to ensure that only videos created by real people are eligible for Spotlight recommendations, taking a stance against AI slop.

WCM world critic model for Vision-Language-Action RL uses observation history supervision to improve robotic manipulation post-training.

QASP predicts per-query recall curves via supervised regression to derive adaptive vector search policies without iterative invocations.

Several record labels, including the big three - Universal Music Group, Sony Music, and Warner Music Group - have proposed rules regarding chart eligibility for AI songs. In short, they wouldn't be. The proposal goes quite a bit further than a labeling proposal put forth by the RIAA, the International Federation of the Phonographic Industry (IFPI), SAG-AFTRA, and others. That would create a set of standardized labels for AI-generated and AI-assisted music. The labels' proposal would require songs be clearly labeled, but it would also keep them off international charts unless they met specific...

FriendBench evaluates 26 multimodal LLMs on dyadic familiarity inference from video; top models match human performance but via different mechanisms.

Proposes optimization-path organization framework for parameter-efficient LLM fine-tuning reducing catastrophic forgetting across heterogeneous task sequences.

Policy gradient convergence analysis for multi-armed bandits in continuous-time RL with diffusion environments; regret bounds derived.

Study of out-of-distribution detection degradation in continual learning systems; proposes mitigation strategies for OOD forgetting.

ResKV: KV cache compression method using residual statistics for fixed-budget long-context inference without permanent token discarding.

TraceViT: looped visual reasoner for ARC benchmark trained with step-by-step transformation supervision using programmatic task rewriting.

Vision-language models exhibit sycophancy that undermines epistemic vigilance in cooperative tasks; detects inconsistencies with prior beliefs.

Apple CEO Tim Cook envisions users being able to buy more compute for Siri AI via Apple's existing iCloud+ subscriptions.

DungeonBench: tactical reasoning benchmark for D&D combat covering geometry, timing, resources, rule interactions with 2014 SRD mechanics.

MOT-SR: LLM-based symbolic regression with data analysis mechanisms and multi-objective optimization for scientific equation discovery.

LEMUR: multi-objective RL from preference feedback without requiring well-specified reward functions for each objective.

Mathematical proof: counterexample to 2015 Lacoste-Julien/Jaggi polytope conjecture regarding pyramidal width under vertex insertion.

COntExt: framework for automated ontology extension from structured operational metric definitions using domain knowledge extraction.

AMTFV introduces agentic verification for LLM math answers via mathematical tool flows, decoupling modeling from implementation.