Submitted by CodeGoat24 62 Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning · 9 authors 79 4
Submitted by fenfan 33 USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning · 8 authors 244 2
Submitted by ztwang 29 MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers · 11 authors 10 2
Submitted by shujian2025 16 TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning · 10 authors 3
Submitted by hammh0a 9 Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection · 4 authors 2
Submitted by taesiri 6 CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification · 5 authors 14 2
Submitted by Incomple 6 Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD · 5 authors 1 2
Submitted by XionghuiWang 5 OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning · 6 authors 4
Submitted by taesiri 3 Dress&Dance: Dress up and Dance as You Like It - Technical Preview · 4 authors 2
Submitted by taesiri 2 OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models · 4 authors 2
Submitted by HuBohy 1 Social-MAE: A Transformer-Based Multimodal Autoencoder for Face and Voice · 5 authors 2