Bounded knowledge map

Recent connections

Explicit wiki links among recent Model Releases entries.

90 nodes · 3 links. The server bounds this neighbourhood, so the browser never downloads or simulates the complete wiki graph.

Search nodesMinimum links 0Zoom 100%

90 nodes · 3 links shown. Hover or focus to isolate neighbours; select a node to open its source entry.

Linked entries

3 shown

Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference→UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference

Benchmarking Time Series Generation Methods for Privacy-Preserving Forecasting→Seq2Synth: Benchmarking Temporal Fidelity in Synthetic Sequential Tabular Data

SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation→Test-Time Self-Evolving GUI Visual Grounding via Reflection-Guided On-Policy Self-Distillation

Model Releases

90 shown

Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference1 UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference1 Seq2Synth: Benchmarking Temporal Fidelity in Synthetic Sequential Tabular Data1 Benchmarking Time Series Generation Methods for Privacy-Preserving Forecasting1 Test-Time Self-Evolving GUI Visual Grounding via Reflection-Guided On-Policy Self-Distillation1 SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation1 FormStruct-Bench:A Hierarchical and Diagnostic Benchmark for Table-Form Document Structure Recognition Reasoning Shortcuts and Value Symmetries: What Symmetry Permits, Architecture Realizes, and Optimization Selects Measure the Sim-to-Real Gap: Designing an Affordable Real-World Benchmark Platform for Reinforcement Learning in AIoT Systems Nutrition Data Infrastructure for the AI Era: Operationalizing FAIR for Agent-Mediated Research REDAgentBench: Executable Red Teaming and Faithful Measurement of LLM Agent Systems Idea for a deepseek-v4-flash-0731 backed automated research workflow to be leveraged via qwen3.6/3.8 27b for difficult tasks that require highly technical, not easy to find information.The Truth Stays in the Family: Enhancing Contextual Grounding via Inherited Truthful Heads in Model Lineages TEASR: Training-Efficient Any-Step Diffusion Transformer for Real-World Image Super-Resolution VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?A variational Bayes approach to inference for low-dimensional parameters in high-dimensional linear regression Implicit representations are dead. Long live explicit primitives!Tested Nemotron 3.5 Lightning locally on coding, Hermes Agent and agentic work ENTLORE: A Graph-Grounded Benchmark for Latent Organizational Reasoning in Enterprise Question Answering Flex-pi: A Multi-Stream World-Action Model with Compute Flexibility Cost-Efficient Estimation of General Abilities Across Benchmarks ReRound: Reconstructive Rounding to Resolve Midpoint Ambiguity in Calibration-Free LLM Quantization b10375 InSight-doc: Agentic Visual Perception for Long-Document Understanding Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation DegradeQuery: Counterfactual Tuple Pretraining for Context-Aware PROTAC Degradation Prediction Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique b10373 We have her dash camera which shows they are lying. The agents are wearing body cameras and should have dash cameras of their own. If what t…myMediWhisper: Construction of Burmese Medical Speech Corpus and Whisper Fine-Tuning for Clinical Dialogue ASR Significance and Stability Analysis of Gene-Environment Interaction using GxEStat Navigation Alone Is Not Enough: Evaluating Explanatory Assistive UI Agents HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Models Do LLM Recommenders Know When They're Hallucinating? Auditing Confidence Calibration in Catalog Faithfulness HoosierHelp: Benchmarking LLM Agents for Social Service Navigation Rethinking LLM Verification: Evidence Structure, Uncertainty, and Selective Refinement Towards Efficient Reasoning in LLM-Based Recommender Systems via Model Merging DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation UserToolBench: A User-Profile-Hidden Benchmark for Personalized Decision Making in Tool-Use LLMs Everyone else is talking about building ASI to like monopolize b2b saas and Elon is talking about building a kardashev II sentient sun When Visual Signals Mislead: A Mechanistic Study of Attribute Hallucination in Vision-Language Models Is There Really a Camouflaged Object? Towards Realistic Camouflaged Object Detection FaithformBench: Benchmarking Faithfulness of Mathematical Chain-of-Thought Autoformalisation Mapping and Measuring the Behavioral Evolution of Large Language Models Putting sign language AI into users’ hands Neural Introspection Gating for Adaptive KV-Cache Reuse in Vision-Language-Action Models On Solomonoff Induction in Large Language Models and the Limits of Self-Improving: The Singularity Is Not Near Without Symbolic Model Synthesis E^3mo-Bench: A Scalable Benchmark for Multimodal Evoked and Expressed Emotion Understanding via Bayesian Pairwise Alignment Stream Forcing: Constructing Unified Training Trajectory for Robust Streaming Video Generation Exploration-Driven Personalized Federated Reinforcement Learning via Intrinsic Motivation Measuring Semantic Abstractness of SAE Features via Nonlocality pi-SUB: A Physics-Informed Synthetic Underwater Benchmark Dataset for Underwater Image Enhancement GeoSeg-OV: Bridging Geospatial Gaps with Structural Guidance for Open-Vocabulary Remote Sensing Segmentation Benchmarking LLM-Guided Control-Plane Policies for Backend Fault Isolation in HAProxy TACTICL: Task-Aware Compression of Tabular ICL Models Can Released LLM Vocabularies Support Token-Level Estimation of Hidden Corpora?Putting Registers to Work: Task Registers for Token Pruning in Vision Transformers Edge Phoneme Recognition for Children's Speech through Age-Aware Training b10369 Derivative Computation in PINNs: Automatic Differentiation, Finite Differences and Beyond No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding Ahrefs launches AI agent workspace Letaido for marketers and agencies MAD-HOI: Masked Autoregressive Diffusion for Generating Articulated Hand Object Interactions from Text Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes On the Limitations of Cross-Lingual Consistency in Multilingual Text-to-image Generation Diffract: Spectral View of LLM Domain Adaptation Optimized Sequential Testing for Binary Ensemble Classifiers GESTO: Human-Centric Spatio-Temporal Memory for Reasoning in Dynamic Scenes SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks V-FiLLM: Verified Financial LLM Reasoning Benchmark Is This Your Final Answer? Cross-Contextual Consistency as a Measure of LLM Credibility Towards Unified Dynamic Face Landmark Detection Vision-Language-Motion Maps: An Open-Vocabulary, Uncertainty-Aware, Queryable Motion Attribute for 3D Scene Maps Bridging Severe Cross-Modal Misalignment: End-to-End Visible-Infrared Object Detection via Explicit Feature-Domain Affine Registration ComBodied Agents: a New Paradigm of Human-Centric Agentic AI ReLTEx: Reliable LLM-based Taxonomy Expansion Curate Before You Connect: Identity and Ontology Tagging in a Production Knowledge Graph AIFS-TC: A simple correction competitive with the operational frontier for tropical cyclone intensity forecasting Fast and Memory-Efficient Wavelet Convolutions via I/O-Aware Reformulation TemMed-Bench: Evaluating Temporal Medical Image Reasoning in Vision-Language Models Static in Frames, Dynamic in Events: Rethinking Features in Event Cameras as Motion Cues SAR2Agri: Learning SAR Intensity Representations for Agricultural Monitoring Locally Deployable Small Language Models for Emergency Department Decision Support: A Systematic Benchmark of Fine-Tuning Strategies A HamNoSys-Guided Dataset and Baselines for Fine-Grained Isolated Handshape Recognition in Sign Language What unique, custom QOL upgrades have you given your local agents?CHORUS: Complementary Experts for High-Coverage Testbench Stimulus Generation DACRI: Decision-Aware Causal Intervention Ranking for Critical Supply Chains KKL Observer Synthesis for Nonlinear Systems via Physics-Informed Learning HyperShape: Hyperelasticity Across Diverse Shapes Cracks in the Foundation: Seemingly Minor Architectural Choices Impact Long Context Extension