Which AI stories has SIREN scored in this window? · Which AI story kinds have SIREN pages? · Which AI story kinds has SIREN scored?
What has SIREN scored as Papers?
Research papers and preprints this index scored. Kind is the collector label on each scored item — not a judgement about quality or harm.
2120Scored stories (live + archive)
139In live window
1981Older in archive
Which scored papers are in this window?
- Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation 54.6
- LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation 51.2
- ActionOPD: Distilling Decisions, Not Tokens 50.9
- LensErase: A Foundation Model for Erase Anything 50.0
- Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory 49.8
- Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation 48.7
- Hybrid Reasoning Agents 48.4
- KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization 48.4
- APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation 47.5
- Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents 47.2
- HumanoidToolBench: Benchmarking Humanoid Tool Use from Selection to Mobile Execution 46.6
- Towards Agentic Robots: Model, Data, Environment, and Harness 46.6
- More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning 45.5
- τ-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions 45.5
- RAR: Rate-Adaptive Rollout for Time-Consistent Interactive World Models 45.0
- Efficient Scene-Text Refinement via Pixel-Space Grouped Image Generation 45.0
- DecisionRobust: Benchmarking Robustness for JEV Style Decision Models Across Text and Vision 44.9
- GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning 44.4
- G^3VLA: Geometric Inductive Bias for Vision-Language-Action Models 44.4
- SkillMarker: A KGW-Based Watermarking Method for Agent Skill Ownership Verification 43.0
- Are We Testing Too Much? A Survey of Benchmark Compression for Efficient Evaluation of Large Language Models 43.0
- TextVerifier: Seeing Beyond Recognition to Verify Chinese Text Rendering 43.0
- Long-Horizon RL Needs Muon 43.0
- Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following 41.9
- Exploring the Limits of Combinatorial Generalization in Embodied Manipulation 41.9
- SafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving 41.9
- VITAL: From Visual Motion to Precise Action 41.9
- Physical Time as a Missing Dimension of Robot Policy Memory Dynamics 41.9
- What Makes a Social Agent's Interactions Effective? Learning from Verifiable Outcomes in Paired Worlds 41.9
- Acting Through Registers 41.9
- MimicX: Policy-in-the-Loop Supervision Refinement for Video-Driven Humanoid Motion Tracking 40.5
- Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards 40.5
- Diff Diffusion: Predicting Edit Paths with Diffusion Models for Efficient Code Editing 40.5
- SWEeper-Bench: Can Agents Discover Bugs in Interactive Software? 40.5
- MA-Bench: Measuring Operational Planning in Language Models 38.0
- Modeling and Understanding Neural Weights of Humanoid Policies with Diffusion 32.4
- Hierarchical Residual Policy Learning for Real-World Mobile Manipulation with Sparse Human Guidance 32.4
- Co-Evolving Acting and Forecasting for Language Agents 32.4
- Your Transformer Is Secretly Elastic 32.3
- Price of Anarchy of First-Price Auctions in Agentic Markets 32.3
99 more on Which AI stories has SIREN scored in this window?.
Which older scored papers are kept?
Kept in the permanent archive after they left the live window. Still scored stories — not a forecast.
- Private, offline and yours: how to search the literature with local AI systems 20.9
- Award-winning microscopy image disqualified over AI use 20.9
- RSI-Anything: Unlocking Recursive Self-Improvement with World Models 48.3
- Machine learning analysis of cilia driven particle transport distinguishes primary ciliary dyskinesia from normal cilia 20.9
- Hidden signals in sleep can predict future health 20.9
- I told ChatGPT to ‘continue’ — it went too far 23.9
- ETSAM: effectively segmenting cell membranes in cryo-electron tomograms 19.2
- One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts 35.1
- OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning 38.4
- Pumpire: Unified Benchmark for Metric Distance Estimation 39.1
- Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching 42.8
- Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict 35.1
Which older AI stories has SIREN kept in the archive?
What questions do people actually ask?
What has SIREN scored as Papers?
2120 scored stories carry the Papers collector label on SIREN (139 in the live window, 1981 older in the archive). Research papers and preprints this index scored.
Which scored papers are in this window?
139 scored stories carry the Papers collector label in the current window. Kind is a label — not a kind doom score.
Which older scored papers are kept?
Kept in the permanent archive after they left the live window. Still scored stories — not a forecast.
Which other kinds have scored stories?
Other collector kinds that clear the substance gate, each linking What has SIREN scored as that kind?
Does SIREN publish a Papers doom score?
No. Activity tempo, not probability of harm. A kind page lists scored stories with that collector label — not a judgement about quality or harm.