Key papers

• Training Data Efficiency in Multimodal Process Reward Models (2026)
  Jinyuan Li et al.
  1.94
• TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models (2026)
  Chansung Park et al.
  1.94
• ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning (2026)
  Ruizhong Qiu et al.
  1.94
• LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning (2026)
  Jianing Wang et al.
  1.94
• OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks (2026)
  Wenbo Hu et al.
  1.94
• GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification (2026)
  Wangjie Gan et al.
  1.94
• Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why (2026)
  Mohammadreza Armandpour et al.
  1.94
• Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR (2026)
  Chongyu Fan et al.
  1.94
• Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration (2026)
  Zili Wang et al.
  1.94
• Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention (2026)
  Jing Huang et al.
  1.94
• MAAT: Multi-phase Adapter-Aware Targeted Unlearning (2026)
  Suryash Yagnik et al.
  1.94
• Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training (2026)
  Michal Chudoba et al.
  1.94
• STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability (2026)
  Haipeng Luo et al.
  1.94
• Reinforcement Learning via Value Gradient Flow (2026)
  Haoran Xu et al.
  1.83
• LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories (2026)
  Zhanhao Liang et al.
  1.83
• DynaMoE: Dynamic Token-Level Expert Activation with Layer-Wise Adaptive Capacity for Mixture-of-Experts Neural Networks (2026)
  Gökdeniz Gülmez
  1.78
• Stabilizing Reinforcement Learning for Diffusion Language Models (2026)
  Jianyuan Zhong et al.
  1.78
• Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations (2026)
  Wei Liu et al.
  1.72
• Online Causal Kalman Filtering for Stable and Effective Policy Optimization (2026)
  Shuo He et al.
  1.72
• FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading (2025)
  Guojun Xiong et al.
  1.28
• Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models (2025)
  Thomas Winninger et al.
  1.28
• Simple Semi-supervised Knowledge Distillation from Vision-Language Models via texttt{D}ual-texttt{H}ead texttt{O}ptimization (2025)
  Seongjae Kang et al.
  1.28
• QVGen: Pushing the Limit of Quantized Video Generative Models (2025)
  Yushi Huang et al.
  1.28
• FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA (2025)
  Seanie Lee et al.
  1.28
• GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning (2025)
  Yeonjoon Jung et al.
  1.28
• Meta-Adaptive Prompt Distillation for Few-Shot Visual Question Answering (2025)
  Akash Gupta et al.
  1.28
• Efficient Machine Unlearning via Influence Approximation (2025)
  Jiawei Liu et al.
  1.28
• On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification (2025)
  Yongliang Wu et al.
  1.28
• Towards a Unified View of Large Language Model Post-Training (2025)
  Xingtai Lv et al.
  1.28
• ΔL Normalization: Rethink Loss Aggregation in RLVR (2025)
  Zhiyuan He et al.
  1.28
• Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning (2025)
  Zhaoyang Chu et al.
  1.28
• Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective (2025)
  Siwei Wang et al.
  1.28
• GRPO-MA: Multi-Answer Generation in GRPO for Stable and Efficient Chain-of-Thought Training (2025)
  Hongcheng Wang et al.
  1.28
• DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing (2025)
  Zihan Zhou et al.
  1.28
• DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning (2025)
  Yifan Wang et al.
  1.28
• MemMamba: Rethinking Memory Patterns in State Space Model (2025)
  Youjin Wang et al.
  1.28
• The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation (2025)
  Farid Bagirov et al.
  1.28
• Alchemist: Unlocking Efficiency in Text-to-Image Model Training via Meta-Gradient Data Selection (2025)
  Kaixin Ding et al.
  1.28
• The Role of Pseudo-labels in Self-training Linear Classifiers on High-dimensional Gaussian Mixture Data (2022)
  Takashi Takahashi
  —
• Interpretability at Scale: Identifying Causal Mechanisms in Alpaca (2023)
  Zhengxuan Wu et al.
  —
• Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts (2023)
  Ganesh Jawahar et al.
  —
• Hyper-Connections (2024)
  Defa Zhu et al.
  —
• Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models (2024)
  Seyedmorteza Sadat et al.
  —