Entities · Models
Qwen3-1.7B
14 articles tagged with this entity.
-
Max Out GRPO Signal: Adaptive Trace Prefix Control for Hard Reasoning Problems
-
Out-of-Distribution Generalization of Risk Aversion in Language Models
-
Beyond Next-Token Prediction: An RLVR Proof of Concept for Tool-Use Agents on Atlassian Workflows
-
Discovering Millions of Interpretable Features with Sparse Autoencoders
-
Sparrow: Sparse Rollout for Stable and Efficient Long-context RL of Large Language Models
-
Score $\times$ Decoder: A Unified View of Unsupervised Inference-Time Scaling for Hallucination Mitigation
-
From "Weak" Signals to Strong Models: Preference Delta Aggregation with LoRA Merging
-
ProtStructQA: A Denotation Threshold in Protein Structural Reasoning
-
ARCA: Adapter-Residual Credit Assignment When Token Signals Degenerate
-
Playing with Words, Improving with Rewards: Training Language Models for Creative Association
-
When PCOS Meets Eating Disorders: An Explainable AI Approach to Detecting the Hidden Triple Burden
-
Committed SAE-Feature Traces for Audited-Session Substitution Detection in Hosted LLMs
-
Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression
-
Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training