Hugging Face Trending Papers
REWIND: Uncertainty-Guided Trajectory Repair for Test-Time Reasoning
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Computation and Language
2d ago
REWIND: Uncertainty-Guided Trajectory Repair for Test-Time Reasoning
arXiv:2610.19561v1 Announce Type: new Abstract: An early mistake in the generated reasoning can constrain all subsequent reasoning. Repeated-generation methods, like MCMC-based approaches, attempt to...
arXiv AI
Aug 26
Selective Regenerative Decoding: Trajectory-Level Intervention for Inference-Time Reasoning
Selective Regenerative Decoding (SRD) is a new inference-time decoding method that improves large language model reasoning by allowing segment-level intervention on candidate trajectories. Instead of discarding or keeping entire trajectories, SRD selectively refines only the degraded suffix while preserving useful prefixes, leading to higher expected trajectory quality and better sample efficiency. Experiments on MATH500, GPQA Diamond, HotpotQA, and AlpacaEval show that SRD matches Best-of-N accuracy with fewer generated tokens and outperforms speculative rejection in low‑compute settings.
arXiv AI
Jun 2
Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance
arXiv:2606. 00305v1 Announce Type: cross Abstract: On-Policy Distillation (OPD) improves large language model reasoning by training a student model on trajectories sampled from its own policy under teacher supervision.
Hugging Face Trending Papers
Jun 17
Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation
Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes KL divergence toward a privileged target distribution. However, because this supervision is generated via uncontrolled sampling, it provides no diagnostic insight into the model's specific errors or corrective guidance for its individual failure patterns.
arXiv Machine Learning
Jun 18
Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation
arXiv:2606. 18844v1 Announce Type: new Abstract: Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes KL divergence toward a privileged target distribution.
arXiv Machine Learning
Sep 10
Stable-MM-R1: Anchoring Multimodal Reasoning Dynamics via Entropy-Guided Stratification
The paper introduces Stable-MM-R1, a framework that stabilizes reinforcement learning for multimodal reasoning by addressing training instability and entropy collapse. It proposes Potential‑Aware Query Mining (PAQM) to filter data toward high‑potential samples and Hybrid Stratified Replay (HSR) to restructure batches using path entropy and reward stratification, reusing stability anchors and hard negatives. The method demonstrates superior performance on complex reasoning tasks compared to strong baselines.