The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
The paper introduces EvidenceConnect, a data‑synthesis framework that generates training examples by zooming into related image regions to create questions requiring comparison, aggregation, or chaining of visual evidence. By retaining only reference answers agreed upon by independent vision‑language models and discarding questions that survive region ablation, the authors train base VLMs with RLVR to produce Zooming without Zooming v2 (ZwZ2). Although the synthesized data are not benchmark‑specific, ZwZ2 shows improvements across fine‑grained and spatial perception, embodied spatial reasoning, multimodal long‑context understanding, multimodal agent tasks, and general visual reasoning, demonstrating that strengthening the shared capability of connecting evidence yields more generalizable multimodal perception.
VideoLVR introduces a method for multimodal large language models to maintain visual grounding during chain-of-thought reasoning by constructing latent visual evidence from local video regions at relevant moments. It uses a visual token prediction objective that unifies visual evidence reconstruction and text generation, allowing models to interleave text tokens with latent visual states. The approach is further extended with reinforcement learning, treating visual tokens as actions and optimizing policies with final-answer rewards, thereby improving video understanding without expanding the multimodal context.
arXiv:2506.09557v2 Announce Type: replace-cross Abstract: While Multimodal Large Language Models (MLLMs) demonstrate impressive performance in benign scenarios, their cognitive reliability deteriorat...
arXiv:2608. 10954v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) demonstrate impressive performance in benign scenarios, their cognitive reliability deteriorates significantly in complex scenes under adverse conditions.
The paper introduces ViMoD, a lightweight framework that dynamically manages visual memory for multimodal large language models. ViMoD uses Deformable Aggregation of Region-wise Tokens (DART) to create content‑adaptive coarse representations linked to recoverable fine tokens, and Temporal Routing for Adaptive Contextual Evidence (TRACE) to anticipate and adjust evidence needs during reasoning. On the Qwen3‑VL‑4B model, ViMoD achieves superior performance across eight reasoning benchmarks with only a 20% visual token budget and minimal additional parameters.
arXiv:2610.27341v1 Announce Type: new Abstract: Vision-language models (VLMs) have advanced rapidly in multimodal reasoning, yet they remain limited on tasks requiring fine-grained understanding of s...