https://validator.w3.org/feed/docs/rss2.html Compositional Literary Primitives in Instruction-Tuned LLMs: Cross-Architectural SAE Features for Self, Style, and Affect RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades KappaPlace: Learning Hyperspherical Uncertainty for Visual Place Recognition via Prototype-Anchored Supervision Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems Metric-Gradient Projection for Stable Multi-Agent Policy Learning Nested Spatio-Temporal Time Series Forecasting Bridging Silicon and the Hippocampus: Algebro-Deterministic Memory “VaCoAl” as a Substrate for Vector-HaSH and TEM BacktestBench: Benchmarking Large Language Models for Automated Quantitative Strategy Backtesting Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew No Free Swap: Protocol-Dependent Layer Redundancy in Transformers AgentWall: A Runtime Safety Layer for Local AI Agents ClawArena: Benchmarking AI Agents in Evolving Information Environments Balancing Knowledge Distillation for Imbalance Learning with Bilevel Optimization SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering When Does Non-Uniform Replay Matter in Reinforcement Learning? Overcoming the Intrinsic Performance Limitations of MEMS IMU via Diffusion-Based Generative Learning $boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control Vision Transformer-Conditioned UNet for Domain-Adaptive Semantic Segmentation WriteSAE: Sparse Autoencoders for Recurrent State Zatom-1: Towards a Multimodal Foundation Model for 3D Molecules and Materials On the Sample Complexity of Differentially Private Policy Optimization TFGN: Task-Free, Replay-Free Continual Pre-Training Without Catastrophic Forgetting at LLM Scale De novo design of peptides localizing at the interface of biomolecular condensates XSearch: Explainable Code Search via Concept-to-Code Alignment AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning Query-Conditioned Test-Time Self-Training for Large Language Models Vision-Core Guided Contrastive Learning for Balanced Multi-modal Prognosis Prediction of Stroke IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation ENSEMBITS: an alphabet of protein conformational ensembles GraphBit: A Graph-based Agentic Framework for Non-Linear Agent Orchestration VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing Image Generators are Generalist Vision Learners The Pitfalls of KV Cache Compression Numerical exploration of the range of shape functionals using neural networks Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands A strong sustainability approach to AI development Learning the PTM code through a coarse-to-fine mechanism-aware framework Dissecting epigenetic heterogeneity in single-cell DNA methylomes with a unified framework PromoterAtlas: decoding regulatory sequences across Gammaproteobacteria using a transformer model From Baselines to Transport Geodesics: Axiomatic Attribution via Optimal Generative Flows PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering Looped SSMs: Depth-Recurrence and Input Reshaping for Time Series Classification Gradient-Free Noise Optimization for Reward Alignment in Generative Models Towards a holistic understanding of Selection Bias for Causal Effect Identification DeepSlide: From Artifacts to Presentation Delivery Q-Flow: Stable and Expressive Reinforcement Learning with Flow-Based Policy A New Technique for AI Explainability using Feature Association Map EMReady2: improvement of cryo-EM and cryo-ET maps by local quality-aware deep learning with Mamba