The Archive

RL method for robotic throwing in cluttered environments using potential field representations to balance basket attraction and obstacle avoidance.

Theoretical analysis proving neural networks exponentially outperform NTK on compositional tasks, quantifying Fourier vs. architectural complexity trade-offs.

ActionCache accelerates Vision-Language-Action models for real-time robotic deployment by caching and refining intermediate denoising steps without retraining.

Agentic systems turn model reasoning into action through multi-step workflows that combine inference, tool use, code execution, retrieval, orchestration, and... Agentic systems turn model reasoning into action through multi-step workflows that combine inference, tool use, code execution, retrieval, orchestration, and result handling. As these systems scale across the AI factory, performance depends not only on GPU acceleration, but also on the CPU work that happens between model steps. Across the creation and deployment of an agentic system… Source

Domain-adapted Sentence Transformers automate cloud security compliance mapping using 13k synthetic training pairs from five European standards.

TopoBrick uses agentic topology sampling on building knowledge graphs for zero-shot IoT forecasting without training or fixed covariates.

Physics-Informed Neural Networks learn finite-dimensional embeddings of PDE solution families via multihead architecture with orthogonalization penalties.

Framework for responsible personalisation in human-robot interaction examining ethical risks from embodied agents across lifecycle and interaction contexts.

Code agent framework for automated software verification outperforms fixed proof strategies, proving larger fraction of Coq theorems than prior LLM approaches.

Dictionary learning interpretability module decomposes end-to-end autonomous driving models into causal semantic concepts for safety analysis.

First large-scale evaluation of LLM uncertainty estimation across 22 languages and model sizes, comparing nine methods on multilingual MCQA.

DT-Guard uses reasoning-active training to build efficient LLM safety guardrails that detect concealed intent without excessive latency.

Dithered Gaussian mechanism improves differential privacy efficiency by discretizing outputs instead of noise, avoiding floating-point vulnerabilities.

Token-based dual-view fusion framework for breast cancer classification from mammography using prompt-based vision model adaptation.

UI2App benchmark evaluates LLM-generated web applications on interaction fidelity, not just visual rendering, using image-driven inputs.

Quantum-inspired hybrid system for automated music harmony generation combines candidate exploration with rule-based optimization.

Quantitative Gaussian-process convergence theory for infinite-width neural networks provides finite-width error bounds architecture-agnostic.

Cross-lingual transfer from Sinhala improves Dhivehi speech recognition using continual pre-training for low-resource language.

Kernel-based operator learning derives budget allocation conditions balancing training pairs, input observations, and output resolution.

SkillReranker improves agent skill selection by decomposing tasks and reranking candidates, addressing semantic ambiguity and skill applicability.

Proposes native meta-architecture embedding application-layer cognitive protocols via structural tension loss function for stateful LLM behavior.

Graph-based model of early language acquisition in children using spreading activation on semantic networks across four languages.

VendorBench-100 unified benchmark comparing 36 deepfake detectors across commercial APIs, vision-language models, and open-source methods.

Neural likelihood approximation framework for high-dimensional Bayesian inverse problems in scientific computing.

TOFFEE system generates synthetic data agent trajectories for LLM adaptation to enterprise SQL and analytics workflows.

The AirGo A6 are available in multiple designs including several transparent color options. | Image: Solos Solos announced a new version of its AirGo smart glasses, one that forgoes cameras for a sleeker design and an AI assistant that relies on voice interactions. Last year's AirGo A5 weighed 36 to 40 grams depending on the frame style, but the new AirGo A6 weigh around 19 grams. Part of the weight savings comes from thinner temple arms housing speakers, batteries, and other electronics. For comparison, the new Meta Glasses announced last month weigh around 54 to nearly 60 grams depending on...

PAC-Bayesian analysis of quantum circuit generalization showing entanglement inflates effective complexity in quantum RL.

Spider 2.0-AIFunc benchmark of 465 text-to-SQL instances covering AI-native SQL functions on Snowflake platform.

Canopy heterogeneous graph foundation model integrating 6.9M biotech nodes for metabolic engineering strain design.