SegAnswer trains an MLLM to generate segmentation masks instead of bounding boxes when zooming into image regions during visual reasoning, yielding consistent improvements across perception and hallucination benchmarks.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
AutoTool uses dual-mode RL to let MLLMs adaptively choose tool use or text-only reasoning, reporting 21.8% accuracy gain on V* and 44.9% efficiency gain on POPE versus baselines.
ACE uses adversarial counter-commonsense perturbations on image tokens during decoding to suppress hallucinated linguistic priors while preserving stable visual signals in MLLMs.
citing papers explorer
-
Segmentation before Answering: Pixel Grounding for MLLM Visual Reasoning
SegAnswer trains an MLLM to generate segmentation masks instead of bounding boxes when zooming into image regions during visual reasoning, yielding consistent improvements across perception and hallucination benchmarks.
-
Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning
AutoTool uses dual-mode RL to let MLLMs adaptively choose tool use or text-only reasoning, reporting 21.8% accuracy gain on V* and 44.9% efficiency gain on POPE versus baselines.
-
Not Blind but Silenced: Rebalancing Vision and Language via Adversarial Counter-Commonsense Equilibrium
ACE uses adversarial counter-commonsense perturbations on image tokens during decoding to suppress hallucinated linguistic priors while preserving stable visual signals in MLLMs.