ResRL decouples shared semantics between positive and negative responses in LLM reinforcement learning via SVD-based projection residuals, outperforming baselines including NSR by up to 9.4% on math reasoning benchmarks.
Token-level direct preference optimization
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
MSDDA derives a closed-form optimal reverse denoising distribution for multi-objective diffusion alignment that is exactly equivalent to step-level RL fine-tuning with no approximation error.
TIPO applies preference-intensity weighting and padding gating to stabilize preference optimization for privacy personalization in mobile GUI agents, yielding higher alignment and distinction metrics than prior methods.
citing papers explorer
-
ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning
ResRL decouples shared semantics between positive and negative responses in LLM reinforcement learning via SVD-based projection residuals, outperforming baselines including NSR by up to 9.4% on math reasoning benchmarks.
-
Step-level Denoising-time Diffusion Alignment with Multiple Objectives
MSDDA derives a closed-form optimal reverse denoising distribution for multi-objective diffusion alignment that is exactly equivalent to step-level RL fine-tuning with no approximation error.
-
Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization
TIPO applies preference-intensity weighting and padding gating to stabilize preference optimization for privacy personalization in mobile GUI agents, yielding higher alignment and distinction metrics than prior methods.
- TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching