https://validator.w3.org/feed/docs/rss2.html VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding with Frozen Vision-Language Models LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Data ORBITALIF: An Efficient Spiking Federated Learning Framework for Onboard Cloud Removal Mechanistic Circuit Identification for Controllable Data Generation Deep learning aging marker from retinal images unveils sex-specific clinical and genetic signatures SA-RSQ: A Versatile Sparse Representation Framework for Multi-modal Recommender Systems What Transfers from Text to Vision? Capability Scaling Laws and Transfer Dynamics for VLMs Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection SDoH-Aware Narrative Anchoring Bias in Medical LLMs for Trustworthy Clinical Decision Support Triplet2Track: A Hierarchical System with Object-Centric Representations for Reliable Long-Horizon Manipulation DPRM: A Plug-in Doob h transform-induced Token-Ordering Module for Discrete Diffusion Models AI-based worker guidance in assembly and disassembly operations using multimodal ego/exo-centric data capture and structured task knowledge Reinforcing the World’s Edge: A Continual Learning Problem in the Multi-Agent-World Boundary Telco-GAIA: Bilingual Benchmark for Agents in Telecom Domain Shaping the Evolutionary Dynamics of Robot Morphology via Adaptive Control Learning PatchWrite: One Line, Not One Section — Compile-Gated, Validity-Preserving Editing for AI-Drafted Manuscripts Divisive Normalization Shapes Low-Rank Slow Manifolds for Continuous Working Memory E2LLM: Towards Efficient LLM Serving in Heterogeneous Edge/Fog Environments AI Alignment and Fiduciary Obligation Atom Learning Model (ALM): how a real classroom got tokenised KVBoost: Chunk-Level Key-Value Cache Reuse with Deviation-Guided Recomputation for Efficient Large Language Model Inference Quantifying replication fidelity of unnatural base pairs using nanopore sequencing SuTRA : Structurally-Unified Tokenization with Root Awareness LENS: In-Context Search via Latent Evidence Exploration over Dynamic Raw Documents PSK at WMT 2026 MIST: Task-Specialized QLoRA Adapters for Multilingual Summarization and Question Answering Separating Covariate Shift from Mechanism Change with Two Discriminators: CJSD, a Conditional Discrepancy with an Exact Covariate-Concept Decomposition SDAD: Spec-Driven Agentic Development for the AI-Native SDLC Towards Query-Agnostic RAG Evaluation via Query Coverage and Claim Verifiability Beyond End-to-End Success: Diagnosing Failures in Long-Horizon Security LLM Agents CoST: Semantic-Aware Urban Understanding via Spatial-Temporal Alignment Skillware: A Software Ontology and Engineering Lifecycle for Persistent Behavioral Artifacts STAR-OPD: Structured Aspect-Cascade-Aware On-Policy Reward Distillation for ABSA Quadruple Extraction Too Sure to Be Safe: Model Calibration for Reliable Log Anomaly Detection Finite-Horizon Input-Output Dynamics of Minibatch Perturbations in AdamW CoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning DA-WAM: Decision-Aligned Future Latents for Driving World Models Cross-Model Memory Transfer via Target-Side Reader Adaptation Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges Denoising-Aware Inversion: Revealing Privacy Risks in Noise-Protected Text Embeddings Change Point–Aware Evaluation and Re-Calibration of PPG-Based Blood Pressure Estimation MotoSafety: Edge-AI with Learned Temporal Importance for Two-Wheeler Collision Risk Assessment Under Time Pressure Position: Collusion Risks Among AI Reasoning Agents Justify Certification Requirements for Making Market Decisions ALPaCA: Adapting Llama for Pathology Context Analysis to enable slide-level question answering Provenance grounds trust in autonomous science Self-supervised image denoising and restoration method for atomic force microscopy Investors’ sneak peak: can this AI tool spot the science that will lead to patents? Active Inference as Context Acquisition for AI Agents From Student Risk Prediction to SC2R: Semantics-Constrained Counterfactual Recourse for Educational Decision Support Fuzzy-MoE: Interpretable Regime-Conditioned Expert Routing for Non-Stationary Multivariate Time Series Forecasting