Which AI stories has SIREN scored in this window? · Which AI news tags have SIREN pages? · Which AI tags has SIREN scored stories about?
What has SIREN scored about Post-training?
Post-training method and product stories scored in the newsroom or archive — coverage counts, not a capability forecast. A tag page lists scored stories whose title or summary matched a published needle — not a probability of harm and not a ranking of the companies named.
Which scored stories are tagged Post-training in this window?
- APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation 47.5
- What behaviors does a model actually learn in RL? [P] 27.5
- One Task, Many Interfaces: Simple Cross-Interface Consistency Training Improves LLM Agent Robustness 32.3
- Manacá-1B-Instruct-2: Reproducible Safety Alignment for a Native Brazilian-Portuguese LLM. Negative DPO Results, a Controlled Composition Scan, and a Silent Failure Mode of the LLM Judge 32.3
- ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models 39.7
Which AI stories has SIREN scored in this window?
Which older scored stories are tagged Post-training?
Kept in the permanent archive after they left the live window. Still scored stories — not a forecast.
- Is a second MSc worth it? [D] 23.9
- How compute time has shifted from pretraining to post-training over the last 2 years 19.8
- DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training 42.0
- Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards 40.8
- Predicting Alignment Generalization with Value Representations 27.1
- Gains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective 42.4
- On-Policy Distillation with Negative-Policy Rollouts 41.0
- Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation 35.9
- EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution 27.0
- Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models 27.0
- Layerwise Error Attribution for Fast and Robust Mixed-Precision Post-Training Quantization 26.6
- DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation 38.5
Which older AI stories has SIREN kept in the archive?
What questions do people actually ask?
What has SIREN scored about Post-training?
68 scored stories match this published needle on SIREN (5 in the live window, 63 older in the archive). Post-training method and product stories scored in the newsroom or archive — coverage counts, not a capability forecast.
Which scored stories are tagged Post-training in this window?
5 scored stories matched this published needle in the current window. A tag page lists headlines — not a topic doom score.
Which older scored stories are tagged Post-training?
Kept in the permanent archive after they left the live window. Still scored stories — not a forecast.
Which other tags have scored stories?
Other published tags that clear the substance gate, each linking What has SIREN scored about that tag?
Does SIREN publish a Post-training doom score?
No. Activity tempo, not probability of harm. A tag page lists matching headlines — not a probability of harm and not a ranking of the companies named.