100 active frozen predictions, ranked by signal-fusion score. Outcome windows are still open, so these rows are awaiting outcome evidence rather than true/false resolution.
| # | Paper · arxiv id | Domain | Signal Fusion | Predicted | Frozen | Lineage | Outcome |
|---|---|---|---|---|---|---|---|
| 100 | 98$\times$ Faster LLM Routing Without a Dedicated GPU: Flash Attention, Prompt Compression, and Near-Streaming for the vLLM Semantic Router 2603.12646v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 99 | ACD-U: Asymmetric co-teaching with machine unlearning for robust learning with noisy labels 2603.07166v1 | cs.RO | 95.0 | 2026-05-31 | 2026-05-31 | unverifiable | P |
| 98 | Polyglot-Lion: Efficient Multilingual ASR for Singapore via Balanced Fine-Tuning of Qwen3-ASR 2603.16184v1 | cs.RO | 95.0 | 2026-05-31 | 2026-05-31 | unverifiable | P |
| 94 | Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training 2603.12255v1 | cs.RO | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 93 | Heterogeneous Vertiport Selection Optimization for On-Demand Air Taxi Services: A Deep Reinforcement Learning Approach 2601.21316v1 | cs.CV | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 92 | SentiAvatar: Towards Expressive and Interactive Digital Humans 2604.02908v1 | cs.LG | 95.0 | 2026-05-31 | 2026-05-31 | unverifiable | P |
| 88 | Advancing Automated Algorithm Design via Evolutionary Stagewise Design with LLMs 2603.07970v1 | cs.CV | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 87 | KG-Hopper: Empowering Compact Open LLMs with Knowledge Graph Reasoning via Reinforcement Learning 2603.21440v1 | cs.AI | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 84 | Exploring Open-Vocabulary Object Recognition in Images using CLIP 2603.05962v1 | cs.LG | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 83 | MDER-DR: Multi-Hop Question Answering with Entity-Centric Summaries 2603.11223v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 80 | IRIS: Intersection-aware Ray-based Implicit Editable Scenes 2603.15368v1 | cs.CV | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 79 | Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace 2605.10913v1 | cs.CL | 95.0 | 2026-05-31 | 2026-05-31 | unverifiable | P |
| 77 | Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation 2604.05150v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 76 | EVE: Verifiable Self-Evolution of MLLMs via Executable Visual Transformations 2604.18320v1 | cs.AI | 95.0 | 2026-05-31 | 2026-05-31 | unverifiable | P |
| 75 | CAST-CKT: Chaos-Aware Spatio-Temporal and Cross-City Knowledge Transfer for Traffic Flow Prediction 2602.05133v1 | cs.RO | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 74 | Operating-Layer Controls for Onchain Language-Model Agents Under Real Capital 2604.26091v1 | cs.RO | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 71 | Coherent Human-Scene Reconstruction from Multi-Person Multi-View Video in a Single Pass 2603.12789v1 | cs.LG | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 69 | IoT-Brain: Grounding LLMs for Semantic-Spatial Sensor Scheduling 2604.08033v1 | cs.LG | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 67 | ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection 2604.11790v1 | cs.AI | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 65 | Action-Aware Generative Sequence Modeling for Short Video Recommendation 2604.25834v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 64 | ML-Embed: Inclusive and Efficient Embeddings for a Multilingual World 2605.15081v1 | cs.RO | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 63 | QDTraj: Exploration of Diverse Trajectory Primitives for Articulated Objects Robotic Manipulation 2604.22551v1 | cs.LG | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 62 | Agent Control Protocol: Admission Control for Agent Actions 2603.18829v1 | cs.CV | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 60 | CoRefine: Confidence-Guided Self-Refinement for Adaptive Test-Time Compute 2602.08948v1 | cs.LG | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 58 | Training-Free Test-Time Contrastive Learning for Large Language Models 2604.13552v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 56 | Nautilus Compass: Black-box Persona Drift Detection for Production LLM Agents 2605.09863v1 | cs.AI | 95.0 | 2026-05-31 | 2026-05-31 | unverifiable | P |
| 55 | AtlasOCR: Building the First Open-Source Darija OCR Model with Vision Language Models 2604.08070v1 | cs.CV | 95.0 | 2026-05-31 | 2026-05-31 | unverifiable | P |
| 53 | Flowr -- Scaling Up Retail Supply Chain Operations Through Agentic AI in Large Scale Supermarket Chains 2604.05987v1 | cs.LG | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 52 | Debiased Model-based Representations for Sample-efficient Continuous Control 2605.11711v1 | cs.AI | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 51 | A Swap-Adversarial Framework for Improving Domain Generalization in Electroencephalography-Based Parkinson's Disease Prediction 2602.10528v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 49 | SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills 2604.06550v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 48 | MoRight: Motion Control Done Right 2604.07348v1 | cs.RO | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 47 | ClawEnvKit: Automatic Environment Generation for Claw-Like Agents 2604.18543v1 | cs.CV | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 45 | LightSplat: Fast and Memory-Efficient Open-Vocabulary 3D Scene Understanding in Five Seconds 2603.24146v1 | cs.LG | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 43 | Hunting CUDA Bugs at Scale with cuFuzz 2603.12485v1 | cs.RO | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 42 | EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing 2603.14916v1 | cs.AI | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 39 | Unleashing Video Language Models for Fine-grained HRCT Report Generation 2603.12469v1 | cs.LG | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 37 | Graph Neural Operator Towards Edge Deployability and Portability for Sparse-to-Dense, Real-Time Virtual Sensing on Irregular Grids 2604.01802v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 36 | Fine-tuning RoBERTa for CVE-to-CWE Classification: A 125M Parameter Model Competitive with LLMs 2603.14911v1 | cs.AI | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 33 | HiSpatial: Taming Hierarchical 3D Spatial Understanding in Vision-Language Models 2603.25411v1 | cs.CV | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 32 | GLiNER2-PII: A Multilingual Model for Personally Identifiable Information Extraction 2605.09973v1 | cs.CV | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 31 | FAME: Force-Adaptive RL for Expanding the Manipulation Envelope of a Full-Scale Humanoid 2603.08961v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 30 | Contextualizing Sink Knowledge for Java Vulnerability Discovery 2604.01645v1 | cs.CL | 95.0 | 2026-05-31 | 2026-05-31 | unverifiable | P |
| 24 | JobMatchAI An Intelligent Job Matching Platform Using Knowledge Graphs, Semantic Search and Explainable AI 2603.14558v1 | cs.CV | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 23 | Toward Complex-Valued Neural Networks for Waveform Generation 2603.11589v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 22 | ACPV-Net: All-Class Polygonal Vectorization for Seamless Vector Map Generation from Aerial Imagery 2603.16616v1 | cs.RO | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 21 | OpenClaw-RL: Train Any Agent Simply by Talking 2603.10165v1 | cs.CV | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 20 | Efficient Protein Optimization via Structure-aware Hamiltonian Dynamics 2601.11012v1 | cs.RO | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 19 | CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies 2604.24622v1 | cs.CV | 95.0 | 2026-05-31 | 2026-05-31 | unverifiable | P |
| 17 | DyWeight: Dynamic Gradient Weighting for Few-Step Diffusion Sampling 2603.11607v1 | cs.RO | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 16 | From Understanding to Erasing: Towards Complete and Stable Video Object Removal 2604.01693v1 | cs.LG | 95.0 | 2026-05-31 | 2026-05-31 | unverifiable | P |
| 15 | Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations 2604.26805v1 | cs.CV | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 14 | VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects 2604.16272v1 | cs.AI | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 12 | SGI: Structured 2D Gaussians for Efficient and Compact Large Image Representation 2603.07789v1 | cs.AI | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 10 | MetaboNet: The Largest Publicly Available Consolidated Dataset for Type 1 Diabetes Management 2601.11505v1 | cs.LG | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 9 | A New Dataset and Framework for Robust Road Surface Classification via Camera-IMU Fusion 2601.20847v1 | cs.AI | 95.0 | 2026-05-31 | 2026-05-31 | unverifiable | P |
| 7 | WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching 2603.24836v1 | cs.CV | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 5 | InCoder-32B: Code Foundation Model for Industrial Scenarios 2603.16790v1 | cs.CV | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 4 | Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction 2604.27221v1 | cs.AI | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 3 | Woosh: A Sound Effects Foundation Model 2604.01929v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 1 | Memento-Skills: Let Agents Design Agents 2603.18743v1 | cs.CV | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |