7 papers
Residual Visual Credit Optimization: Conserved Evidence Routing for Multimodal Reinforcement Learning
Lin Qiu, Yao Liu, Diyi Hu +6
Reinforcement learning with verifiable rewards scales multimodal reasoning, but an outcome reward says how much a trajectory is worth, not how that value should be spread over the…
SVR-R1: Bootstrapping Multi-modal Reasoning with Self-verification in Reinforcement Learning
Mingyuan Wu, Jingcheng Yang, Shengyi Qian +11
We introduce Self-Verified Reasoner (SVR-R1), a multi-turn RL framework that turns a model's own verification into a learning signal for multimodal reasoning. For each query, the m…
Detecting AI-Generated Content on Social Media with Multi-modal Language Models
Chenyang Yang, Shen Yan, Yibo Yang +13
Generative AI has enabled the creation of photorealistic images and videos that are increasingly disseminated on social media, often used for spam, misinformation, manipulation, an…
GISTBench: Evaluating LLM User Understanding via Evidence-Based Interest Verification
Iordanis Fostiropoulos, Muhammad Rafay Azhar, Abdalaziz Sawwan +8
We introduce GISTBench, a benchmark for evaluating Large Language Models' (LLMs) ability to understand users from their interaction histories in recommendation systems. Unlike trad…
RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization
Zhaoning Yu, Will Su, Leitian Tao +9
Reinforcement learning with human-annotated data has boosted chain-of-thought reasoning in large reasoning models, but these gains come at high costs in labeled data while falterin…
RecoWorld: Building Simulated Environments for Agentic Recommender Systems
Fei Liu, Xinyu Lin, Hanchao Yu +12
We present RecoWorld, a blueprint for building simulated environments tailored to agentic recommender systems. Such environments give agents a proper training space where they can…
CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning
Hao Yu, Zhuokai Zhao, Shen Yan +7
The rapid advancement of large vision-language models (LVLMs) has driven significant progress in multimodal tasks, enabling models to interpret, reason, and generate outputs across…