AI Wiki — Knowledge Base

Cross-Behavior Policy Optimization: Unified Learning from Offline Demonstrations and On- and Off-Policy Rollouts via a Shared Regression Target

arXiv:2610.12830v1 Announce Type: new Abstract: Reasoning post-training draws on offline demonstrations and policy-generated rollouts, yet conventional supervised fine-tuning (SFT) followed by reinfor

model-releasesarxiv-cs-lg

12 Oct 2026

Search: “model-releases”

RADAR: Rubric-Aware Dependency and Redundancy Analysis for LLM-as-Judge Evaluation

A Baseline Assessment for the Agentic Web Technology Stack

A Categorical Atlas of Parameter-Efficient Fine-Tuning: Cones, Orbits, and Gauges

A Sampling Complexity-aware Framework for Discrete-time Fractional-Order Dynamical System Identification

A Scalable Learned Iterative Solver for Nonlinear MPC via Temporal Decomposition

AdaC-GRPO: Towards Mastering Long-Horizon Visual Sudoku Puzzles via Adaptive Curriculum Learning

Adaptive DHiSparse: Speculative Decoding over a Load-Adaptive KV Hierarchy

AgentSWE: Can Coding Agents Build the Agent You Actually Want?

AgentTune: A Unified Training Lifecycle for Tool-Using LLM Agents

Algebraic Integer Quantization for Machine Learning Applications

AlphaNIST: Emergent Assembly Skills from Binary Task Rewards

AMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosis

Amortized Counterfactual Prediction with Graph Neural Networks

An all-transistor physical-learning transformer can be trained to perform in-context learning

An Input-Dependent Readout Phase for Resonant Sequence Models

APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces

Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMs

AudioTETRIS: Token Elimination via Transitional Importance Signals for Efficient Audio LLMs

AutoBio+: Benchmarking Dexterous Manipulation with Dynamic Experimental Phenomena in Realistic Laboratories

Bayesian dynamic scheduling of multipurpose batch processes under incomplete look-ahead information

Behind-the-Meter Photovoltaic Visibility from Net Smart Meters: Deployment Regimes and Operational Insights

Beyond Temporal Proximity: Explanatory World Models for Credit Assignment in Reinforcement Learning

Bistable by Construction: Wall-Clock-Calibrated State Monitors Have No Moment-Detection Regime at Agent Cadence

BLEND: Balancing Personalization vs. Generalization in Federated Vision-Language Models

BLiMPPI: Benchmark of Linguistic Minimal Pairs for Polarity Items

BLOKS: Scaling Kernel Solvers with Sketched Block Preconditioning

BT-Agent: Deploying Onboard Robot Agents with Behavior Trees and Multi-Fidelity Evaluation

Byzantine-Resilient Federated Large Language Model via Hypergraph Message Passing

Can Language Models Play the Wikipedia Game?

CAST: Credit Alignment for Cross-Tokenizer On-Policy Distillation

CoBe: A Benchmark For Conversational Counterfactual Text Editing

CoGameReg: Cooperative-Game-Based Collaborative Semi-Supervised Regression for Seismic Reservoir Property Prediction

Collaborative Learning and Reasoning over Model Slices

Constrained Probabilistic Numerics: Gaussian Process Solvers for Linear PDEs under Linear Inequality Constraints

Constructing Pareto Frontiers of Optimal Reasoning Termination Methods for Overthinking in Reasoning Models

CORE-Seg: Reasoning-Driven Segmentation for Complex Lesions via Reinforcement Learning

Cross-Behavior Policy Optimization: Unified Learning from Offline Demonstrations and On- and Off-Policy Rollouts via a Shared Regression Target

DAG Structure Learning with Node-Varying Heavy-Tailed Disturbances

Data-Adaptive Mahalanobis Metric Learning for Cross-Head Attention in Transformers

Data-driven Optimal Sensor Placement for Aerosol Monitoring in the UK

DEAF: A Benchmark for Diagnostic Evaluation of Acoustic Faithfulness in Audio Language Models

Defence against the dark arts of distillation: Unsupervised discovery of subliminal learning

Deploying RDMA for Large-Scale Inference and Training Workloads

DiffMorphGrasp: A Diffusion Framework Conditioned on Hand Morphology for Cross-Embodiment Grasp Generation

Does Financial Speech Need Continual Learning Regularization? A Study of EWC and mini-KFAC on Earnings Call ASR

Does Learning Recurrent Networks Matter in Partially Observable RL?

Don't Guess, Just Ask: Evaluating Interactive Requirement Clarification for Repository-Level Software Development

DRYLAB-Bench: Benchmarking the Biosecurity Risk of Agentic LLM Mutation Design