…Ziyu Guo , , , Abstract ATLAS presents a visual reasoning framework that combines agentic operations and latent representations using functional tokens, enabling efficient training and improved performance on complex benchmarks. AI-generated summary Visual…
…Strong cross-generator generalization — Trained on a single 4-class ProGAN split, MDMF reaches 95.65 average AUROC on the ImageNet benchmark (9 generators spanning diffusion, GAN, and AR families) and remains…
…semantic and quality questions, which are then evaluated by a general MLLM to provide reliable and interpretable feedback. Extensive experiments demonstrate that AlphaGRPO yields robust improvements across multimodal generation benchmarks, including GenEval…
…This produces dense, continuous multi-view maps that allow visual priors and gradients to flow much more reliably. Architecture-wise, we use a TinyViT image encoder and a two-stage SDG decoder…
…Across three model families and multiple factual QA benchmarks, RL yields ~27% average relative gains, surpassing both training- and inference-time baselines alike. Mechanistically, RL primarily redistributes probability mass over existing knowledge…
…a frontier LLM is used only for intent understanding, while large scale retrieval and relevance scoring are delegated to customized corpora and lightweight models. Evaluated on the PaSaMaster Benchmark across 38 scientific…
…rollout trajectories , and further explore reinforcement learning via a lightweight pipeline that parallelizes rollouts across per-task sandboxes .To support reliable evaluation, we further construct ClawGym-Bench , a benchmark of 200 instances…
…into a pretrained VLM and training it with standard reconstruction objectives , we find that the learned sparse latent features naturally capture attack-relevant signals. These features enable reliable classification of whether an…
…Three case studies on embodied navigation show that self-evolution improves generation reliability, generated environments substantially improve embodied agent performance that generalizes to unseen benchmarks, and co-evolution yields an 18-point…
…Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing (2026) HippoCamp: Benchmarking Contextual Agents on Personal Computers (2026) VisionCreator: A Native Visual-Generation Agentic Model with Understanding, Thinking, Planning and Creation…