Vision-Language (VL) reasoning requires a model to both extract relevant and accurate information from an image (visual reasoning, VR), and to infer the answer from it (language reasoning, LR). Reinforcement learning with verifiable rewards typically trains both through a single chain-of-thought with a final-answer rew...
Raja Kumar, Rajat Koner, Ritwick Chaudhry et al.· 1 citation
DSV-Mem is introduced, a benchmark for evaluating Dense Stateful Visual Memory and a generation harness that produces evaluation suites by decoupling state-transition synthesis from conversation filling, and analysis surfaces findings show state evolution, particularly the number of governing updates, is the dominant t...
Ji-Ke Zhong, Ritwick Chaudhry, Xuan-Bai Chen et al.· 0 citations
ALoDLM is introduced, which replaces uniform computation with token-adaptive latent recurrence, and retains fast parallel decoding, yielding a strong quality-efficiency trade-off among evaluated autoregressive and diffusion models under optimized inference engines.
Lian-Cheng Fang, Zhuo-Wei Li, Youngeun Kim et al.· 1 citation
ReaLVR is proposed, which brings visual-evidence supervision to the model's own free-running latent trajectories, and is the first to scale visual reasoning in latent space, showing that the framework continues to deliver robust improvements at frontier model scales up to 235B.
Xi Xiao, Tian-Chen Zhao, Youngeun Kim et al.· arXiv.org· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.