Bounded knowledge map

Recent connections

Explicit wiki links among recent Model Releases entries.

Browse all entries

90 nodes · 1 links. The server bounds this neighbourhood, so the browser never downloads or simulates the complete wiki graph.

Search nodesMinimum links 0Zoom 100%

90 nodes · 1 links shown. Hover or focus to isolate neighbours; select a node to open its source entry.

Linked entries

1 shown

Oido: Open-Vocabulary Speech Recognition on a $5 Microcontroller without a Neural Accelerator→An Input-Dependent Readout Phase for Resonant Sequence Models

Model Releases

90 shown

An Input-Dependent Readout Phase for Resonant Sequence Models1 Oido: Open-Vocabulary Speech Recognition on a $5 Microcontroller without a Neural Accelerator1 When LiDAR Fades, Radar Takes Over: LiDAR Reliability-Aware Adaptive Localization Under Airborne Obscurants Taking Tokenization off the Host for Agentic LLM Serving GeoFitBench-LLM: A Benchmark for Assessing Large Language Models' Capabilities in Geospatial Data Requirements Elicitation for Geo-Analytic Tasks Evolving Creatives with Clicks: CTR-Driven Advertising image Editing via Attribute Disentanglement and Preference Alignment APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces 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 Does Financial Speech Need Continual Learning Regularization? A Study of EWC and mini-KFAC on Earnings Call ASR EarLog: Opportunistic Ear Physiology Sensing toward Personalized Hearing Risk Awareness Algebraic Integer Quantization for Machine Learning Applications MolP2SBench: Do LLMs Really Reason from Molecular Properties to Structure?Can Language Models Play the Wikipedia Game?Trainable Quantum-Native Language Models: Dissipative Memory, Capacity Limits, and Hardware Validation Looking Under the Streetlight: Evaluation in Generative Molecular Dynamics GraphDecisionBench: Benchmarking System One Models on Graph Tasks Behind-the-Meter Photovoltaic Visibility from Net Smart Meters: Deployment Regimes and Operational Insights TabMF: Learning Dataset Representations with Tabular Foundation Models Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective Knowing When to Stop: Efficient Context Processing via Latent Sufficiency Signals A Baseline Assessment for the Agentic Web Technology Stack MathVis: Can AI Reason through Drawing? A Benchmark for Mathematical Figure Generation DiffMorphGrasp: A Diffusion Framework Conditioned on Hand Morphology for Cross-Embodiment Grasp Generation CoGameReg: Cooperative-Game-Based Collaborative Semi-Supervised Regression for Seismic Reservoir Property Prediction Amortized Counterfactual Prediction with Graph Neural Networks Private and Distributionally Robust Federated Multiclass Classification EmoGavel: Grounding-Aware Reinforcement Learning with Verifiable Rewards for Multimodal Emotion Preference Learning Data-Adaptive Mahalanobis Metric Learning for Cross-Head Attention in Transformers CAST: Credit Alignment for Cross-Tokenizer On-Policy Distillation VQIL: Visible Quantum Interference Learning for Perturbation Response Ranking on Graphs Transformer-based In-Context Score Operator Learning for Diffusion Models Local Diagnostics of Learned Event Representations for Anomaly Detection at the HL-LHC MS-GLA: Multi-Scale Gated Linear Attention for Addressing Representational Bottlenecks via Multi-Temporal Resolution I made an open-source AI leaderboard that shows the best models your machine can run Self-Preservation in Language Models REFLECT: Role-Aware Detection of Sentiment, Emotion, Politeness, and Formality Constrained Probabilistic Numerics: Gaussian Process Solvers for Linear PDEs under Linear Inequality Constraints Evo^2: Evolving the Evolver through Weight-Harness Co-Evolution ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents ManeuverFlow: Maneuver Hypothesis Generation with Future Evidence for Trajectory Evaluation and Refinement in End-to-End Autonomous Driving When VLMs Destroy What They Know: Spatial Representations Fall Below Lexical Priors Unreliable Narrator Framing as a Cost-effective Mechanism for Satire Explanation of Australian and American Satirical News b11562 Hitting-Time Bounds for Asynchronous Q-Learning AgentTune: A Unified Training Lifecycle for Tool-Using LLM Agents Market Impact Estimation via Causal Foundation Models What Should Embodied Agents Remember? Benchmarking and Evaluating Memory Modality for Embodied Agents Weight Clustering Reveals the Importance of Relative Rank in Large Language Models GeopoliticalQA: Benchmarking Retrieval and Generation over Intelligence Reports Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoning Scalable Circuit Learning for Interpreting Large Language Models Unsupervised Multimodal Reward Modeling Humanize Olympiad Agents: A Multi-Session Workflow for Olympiad Problem Solving with Solve, Review, Wiki, Verify Neurograf v1: An End-to-End Romanian-First Language Model Family BT-Agent: Deploying Onboard Robot Agents with Behavior Trees and Multi-Fidelity Evaluation AlphaNIST: Emergent Assembly Skills from Binary Task Rewards DualQuant: Dual-scale Calibration-free Weight-and-Activation Quantization for LLMs UkrMeme: Multimodal Explainable Persuasion Detection in Ukrainian Memes From Pixels to Privacy-Sensitive Features: An Information-Theoretic Framework for Reconstruction Bounds TreeHCA: Hindsight-Guided Exploration and Credit Assignment for Multi-Turn LLM Agents Human and LLM Facilitation in Collaborative Design Meetings: A Computational Behavioral Comparison Mixture of Many Zero-Compute Experts: A High-Rate Quantization Theory Perspective Why Heavy-Tailed Weight Spectra Predict Model Quality b11563 Quality, Not Just Outcome: A Structural Scoring Framework for Selecting Coding-Agent Trajectories for Supervised Fine-Tuning Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QA Spanning Diffusion and Flow-based Posterior Sampling via Exact Gaussian Conditioning Data-driven Optimal Sensor Placement for Aerosol Monitoring in the UK AutoBio+: Benchmarking Dexterous Manipulation with Dynamic Experimental Phenomena in Realistic Laboratories MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agents Scalable Learning of Determinantal Point Processes with Kernel-Structured Interactions Towards Easier-to-Tune Training Algorithms: New Results from AlgoPerf BLEND: Balancing Personalization vs. Generalization in Federated Vision-Language Models Task Context Shapes Component Roles in Language Models Inverse Synthesis of Shock Time Series from Shock Response Spectra Using Ensembles of Conditional Variational Autoencoders Localized Generative Design of Ship Hulls with Diffusion Models and High-Fidelity Assessment MENTOR: Learning from Failure with On-Policy Pedagogical Intervention b11560 Mind the Spatial Gap: A Benchmark for Geospatial Reasoning and Constrained Spatial Editing Rethinking the Roles of Diffusion and Decoding: Predictive-State Flows for Parallel Language Generation SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle Planning with Transformers: Chain of Computation and Structured Context Windows SmolWAM: A Latent World-Action Model for Robotic Manipulation on Edge Devices Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMs Inject a Turn, Not a Token: Learning Where to Redirect LLM Reasoning for Self-Correction PlacePulse: Learning Transferable Place Representations from Structural Geographic Data Qwen3.8-Flash-Next on six 3090s with vLLM: 7 users at 262k, 6.5k t/s prefill, 57 t/s decode solo / 206 t/s aggregate with all 7 generating. Fixes for the upstream included.Defence against the dark arts of distillation: Unsupervised discovery of subliminal learning