A reinforcement-learning agent that picks high-error trajectory segments during consistency distillation improves few-step text-to-image generation on FLUX and SDXL.
Dynamic Sampling that Adapts: Self-Aware Iterative Data Persistent Optimization for Mathematical Reasoning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
In mathematical reasoning, data selection strategies predominantly rely on static, externally defined metrics, which fail to adapt to the evolving capabilities of models during training. This misalignment limits the efficiency of Supervised Fine-Tuning and Reinforcement Learning. To bridge this gap, we introduce SAI-DPO (Self-Aware Iterative Data Persistent Optimization), a dynamic sampling framework that aligns training data with the model's intrinsic competence. SAI-DPO operationalizes two novel metrics: Knowledge Semantic Alignment for targeting domain weaknesses, and Self-Aware Difficulty, derived from pass rates and reasoning path characteristics, to gauge instance complexity relative to the model's current state. By iteratively recalibrating the data distribution based on real-time feedback, SAI-DPO dynamically aligns training samples with the model's evolving competence, ensuring the data remains strictly relevant to the model's current capability level. Extensive experiments on eight benchmarks (including AIME24 and AMC23) demonstrate that SAI-DPO outperforms static baselines at most nearly 6 points, achieving state-of-the-art efficiency with significantly less data.
years
2026 4representative citing papers
The Efficiency Frontier framework models LLM context management as a deployment-aware optimization problem balancing performance, token cost, and amortized preprocessing, with HotpotQA experiments showing 25% token reduction and over 50% cost savings for compression in high-performance regimes.
An SCM-GRPO framework grounds multi-hop reasoning in structural dependency graphs and optimizes chain length via rule-based RL, outperforming baselines on HoVer and EX-FEVER.
FAST uses a Temporal-Spatial-Temporal structure with attention and Mamba modules plus learnable embeddings to achieve better accuracy on traffic prediction tasks than previous models.
citing papers explorer
-
Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning
A reinforcement-learning agent that picks high-error trajectory segments during consistency distillation improves few-step text-to-image generation on FLUX and SDXL.
-
The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management
The Efficiency Frontier framework models LLM context management as a deployment-aware optimization problem balancing performance, token cost, and amortized preprocessing, with HotpotQA experiments showing 25% token reduction and over 50% cost savings for compression in high-performance regimes.
-
Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization
An SCM-GRPO framework grounds multi-hop reasoning in structural dependency graphs and optimizes chain length via rule-based RL, outperforming baselines on HoVer and EX-FEVER.
-
FAST: A Synergistic Framework of Attention and State-space Models for Spatiotemporal Traffic Prediction
FAST uses a Temporal-Spatial-Temporal structure with attention and Mamba modules plus learnable embeddings to achieve better accuracy on traffic prediction tasks than previous models.