TSP reframes secure code generation as a tree-structured self-play process that supplies dense on-policy signals at vulnerability-prone nodes, yielding higher security pass rates and cross-language generalization than SFT or unstructured self-play.
Understanding the performance gap between online and offline alignment algorithms
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 3
method 1
citation-polarity summary
representative citing papers
Response times modeled as drift-diffusion processes enable consistent estimation of population-average preferences from heterogeneous anonymous binary choices.
Certain errors in proxy rewards for policy gradient methods can be benign or beneficial by preventing policies from stalling on outputs with mediocre ground truth rewards, enabling improved RLHF metrics and reward design insights.
POP bootstraps post-training signals for open-ended LLM tasks by synthesizing rubrics during self-play on pretraining corpus, yielding performance gains on Qwen-2.5-7B across healthcare QA, creative writing, and instruction following.
SAM 3D reconstructs 3D objects from single images with geometry, texture, and pose using human-model annotated data at scale and synthetic-to-real training, achieving 5:1 human preference wins.
High-entropy minority tokens drive RLVR gains, so restricting gradients to the top 20% maintains or improves performance over full updates on Qwen3 models, especially larger ones.
RLFTSim uses RL fine-tuning on a pre-trained model with a balanced reward to align traffic simulator rollouts to real data distributions and distill goal-conditioned controllability, reporting SOTA realism on the Waymo Open Motion Dataset.
Mujica-MyGo decomposes multi-turn RAG interactions via multi-agent workflows and applies minimalist policy gradient optimization to improve performance on QA benchmarks while avoiding long-context problems.
GRPO-SG is a sharpness-guided token-weighted variant of GRPO that downweights high-gradient tokens to stabilize optimization and improve generalization in reinforcement learning with verifiable rewards.
citing papers explorer
-
Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs
TSP reframes secure code generation as a tree-structured self-play process that supplies dense on-policy signals at vulnerability-prone nodes, yielding higher security pass rates and cross-language generalization than SFT or unstructured self-play.
-
Response Time Enhances Alignment with Heterogeneous Preferences
Response times modeled as drift-diffusion processes enable consistent estimation of population-average preferences from heterogeneous anonymous binary choices.
-
When Errors Can Be Beneficial: A Categorization of Imperfect Rewards for Policy Gradient
Certain errors in proxy rewards for policy gradient methods can be benign or beneficial by preventing policies from stalling on outputs with mediocre ground truth rewards, enabling improved RLHF metrics and reward design insights.
-
Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text
POP bootstraps post-training signals for open-ended LLM tasks by synthesizing rubrics during self-play on pretraining corpus, yielding performance gains on Qwen-2.5-7B across healthcare QA, creative writing, and instruction following.
-
SAM 3D: 3Dfy Anything in Images
SAM 3D reconstructs 3D objects from single images with geometry, texture, and pose using human-model annotated data at scale and synthetic-to-real training, achieving 5:1 human preference wins.
-
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
High-entropy minority tokens drive RLVR gains, so restricting gradients to the top 20% maintains or improves performance over full updates on Qwen3 models, especially larger ones.
-
RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuning
RLFTSim uses RL fine-tuning on a pre-trained model with a balanced reward to align traffic simulator rollouts to real data distributions and distill goal-conditioned controllability, reporting SOTA realism on the Waymo Open Motion Dataset.
-
Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning
Mujica-MyGo decomposes multi-turn RAG interactions via multi-agent workflows and applies minimalist policy gradient optimization to improve performance on QA benchmarks while avoiding long-context problems.
-
Sharpness-Guided Group Relative Policy Optimization via Probability Shaping
GRPO-SG is a sharpness-guided token-weighted variant of GRPO that downweights high-gradient tokens to stabilize optimization and improve generalization in reinforcement learning with verifiable rewards.