conftrace_

reward model

276 papers

Explore in graph

Also known as

RM

Co-occurring keywords

large language model (13587) reinforcement learning (4352) reinforcement learning from human feedback (278) language model (4599) preference learning (418) language model alignment (142) reward modeling (164) direct preference optimization (332) human feedback (161) human preference (124)

Papers

ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks EMNLP 2025
Calibrated Multi-Preference Optimization for Aligning Diffusion Models CVPR 2025
Let's Verify and Reinforce Image Generation Step by Step CVPR 2025
Rejected Dialects: Biases Against African American Language in Reward Models NAACL 2025
Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling EMNLP 2025
Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation ACL 2025
Focus-N-Fix: Region-Aware Fine-Tuning for Text-to-Image Generation CVPR 2025
Enhancing RLHF with Human Gaze Modeling EMNLP 2025
Reward Models in Deep Reinforcement Learning: A Survey IJCAI 2025
Science-T2I: Addressing Scientific Illusions in Image Synthesis CVPR 2025
Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning ACL 2025
VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward Models ICCV 2025
Google Translate’s Research Submission to WMT2025 EMNLP 2025
M-RewardBench: Evaluating Reward Models in Multilingual Settings ACL 2025
Transferring Textual Preferences to Vision-Language Understanding through Model Merging ACL 2025
AutoAlign: Get Your LLM Aligned with Minimal Annotations ACL 2025
Speculative Reward Model Boosts Decision Making Ability of LLMs Cost-Effectively ACL 2025
Boosting Policy and Process Reward Models with Monte Carlo Tree Search in Open-Domain QA ACL 2025
Understanding Impact of Human Feedback via Influence Functions ACL 2025
FloorPlan-LLaMa: Aligning Architects’ Feedback and Domain Knowledge in Architectural Floor Plan Generation ACL 2025
Free2Guide: Training-Free Text-to-Video Alignment using Image LVLM ICCV 2025
Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment ICCV 2025
reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs EMNLP 2025
Lost in the Context: Insufficient and Distracted Attention to Contexts in Preference Modeling ACL 2025
Removing Prompt-template Bias in Reinforcement Learning from Human Feedback ACL 2025